Skip to content
BY 4.0 license Open Access Published by De Gruyter Open Access May 24, 2023

Scientometric analysis of flood forecasting for Asia region and discussion on machine learning methods

  • Peiying Li , Yanjie Zhao EMAIL logo , Muhammad Sufian EMAIL logo and Ahmed Farouk Deifalla
From the journal Open Geosciences


Flood forecast models have become better through research as they led to a lower risk of flooding, policy ideas, less human death, and less destruction of property, so this study uses Scientometric analysis for floods. In this analysis, citation-based data are used to uncover major publishing areas, such as the most prominent keywords, top best commonly used publications, the most highly cited journal articles, countries, and authors that have achieved consequent distinction in flood analysis. Machine learning (ML) techniques have played a significant role in the development of prediction systems, which have improved results and more cost-effective strategies. This study intends to give a review of ML methods such as decision trees, artificial neural networks, and wavelet neural networks, as well as a comparison of their precision, speed, and effectiveness. Severe flooding has been recognized as a significant source of massive deaths and property destruction in several nations, including India, China, Nepal, Pakistan, Bangladesh, and Sri Lanka. This study presents far more effective flood forecast approaches. This analysis is being used as a guide for experts and climate researchers when deciding which ML algorithm to utilize for a particular forecasting assignment.

1 Introduction

Floods are major weather-related phenomena that continue to generate significant economic and human losses across the world, amounting to tens of billions of dollars in annual damages and thousands of deaths [1,2]. As a result, understanding the causes of floods’ temporal change and unpredictability, as well as flood-related variables (such as precipitation, river flow, and flood loss), is both theoretical and practical [1,3]. Storms, precipitation events, relatively shallow conditions, hydraulic theories of flow, and other global circulation phenomena [4], including the linked impacts of climate, ocean, and catastrophes, have all been predicted using physically based models [5]. Physical models have shown to be capable of forecasting a wide range of flooding situations [6,7] but they often need a variety of hydro-geomorphological inputs, which has costly computing and prevents short-term prediction. Non-engineering techniques include the characteristics of innovative technology-capable algorithms to fiercely anticipate severe flooding. Flood modeling, which has lately increased significantly, has a long history of using data-driven algorithms [8]. To give improved insight, data-driven techniques of forecasting use climatological indices and hydro-meteorological characteristics. Predictive methods of autoregressive integrated moving average are one of them [9]. When comparing regional flood frequency analyses (RFFA) [10,11] to physical models, it has been observed that the more sophisticated versions are more efficient when considering computing cost and generality. Floods may be forecast using specific probabilistic models derived from historical rainfall series, if floods are considered to be probabilistic processes. Different methods like the climatic average method (CLIM) [12,13], statistical methods (QRT), multiple linear regressions (MLRs), quantile regression approaches, and the empirical orthogonal function are used for flood prediction [14,15]. Significant features of Machine learning (ML) algorithms must be taken into account while developing the algorithms. In the first instance, they are only as effective as their training, in which case the system learns how to do the objective job based on previously collected data. If the data is limited or does not cover a wide range of job variations, the learners learning is inadequate, and as a result, they are unable to efficiently perform when placed in the workplace [16]. Because of this, it is necessary to use robust data enrichment techniques such as, for example, creating a density function of sums of weights invariance evaluations or retrieving the missing factors using temporally dependent coefficients while maintaining the attributes. Complex hydrological processes, such as floods, might be effectively modeled using ML approaches [17]. There have been several reports of ML techniques, such as artificial neural networks (ANNs) [18], neuro-fuzzy, support vector machine (SVM) [19], and support vector regression (SVR) [20], being successful for both long-term and short-term flood forecasting. Furthermore, it was shown that the efficiency of ML might be enhanced by the use of hybridization with other ML approaches, soft computing approaches, numerical simulations, and physical models, among other methods and practices [21]. However, while the analytic hierarchy process (AHP) was the most widely used MCDM approach, additional MCDM methods should be investigated [22]. Recently, the AHP and analytic network process (ANP) methods were used in Brazil to conduct flood risk assessments and mapping efforts. They observed that the ANP had a higher predictive power than the AHP, which they attributed to the interdependencies across criteria. Many benefits of these novel techniques have been established, including the fact that compared to physically based models, these techniques do not need a large amount of specific knowledge on watershed features, and these models typically achieve excellent prediction accuracy [23]. There is also a lot of room for improvement in the development of new independent and hybrid models to improve the accuracy of simulated variables [24].

During June–August 1998, East Asia, particularly Northeast China, saw the worst floods on record. During this time, portions of the Nenjiang River and Songhuajiang River in Northeast China got over 400 mm of rain on average [25]. The precipitation quantity was 100–150% more than the seasonal normal in most parts of Northeast China. Heavy rains resulted in record floods and severe economic and social devastation in the affected areas [26]. With a population of about 1.46 billion people, South Asia accounts for 25% of the world’s population and spans around 3.2% of the world’s geographical area and 10% of Asia [27]. South Asia is made up of eight countries, Bangladesh, India, Bhutan, Maldives, Nepal, Afghanistan, Pakistan, and Sri Lanka, and it is home to over 40% of the world’s poor people [28,29]. The Indus, Ganges, Brahmaputra, and Meghna are the main rivers of South Asia [30]. The Kabul River is a Pakistani–Afghan river that runs through Afghanistan. It is one of the Indus’ primary tributaries. The Indus River, together with its tributaries, flows south and west before emptying into the Arabian Sea [31]. The Ganges and Brahmaputra Rivers, as well as their tributaries, run south and east into the Bay of Bengal. These rivers offer water for drinking, irrigation, hydropower production, fisheries, and inland navigation, as well as for the preservation of wetlands and biodiversity, to more than 500 million people in the area [32]. However, these rivers are also the cause of many sorts of floods, which have a negative impact on the region’s socioeconomic growth [33]. The Indus, Ganges, Brahmaputra, and Meghna are the main rivers of South Asia [34]. The Kabul River is a Pakistani–Afghan river that runs through Afghanistan [35]. It is one of the Indus primary tributaries. The Indus River, together with its tributaries, flows south and west before emptying into the Arabian Sea [36].

In order to determine the flood hazard zones, return periods must be taken into account. Different return times have made use of the Sentinel-1 Radar pictures to locate the flooded places. Sentinel-1 Radar scans were utilized to recognize flooded areas in different return times. In the current study, a method known as embedded feature selection (i.e., recursive feature elimination random forest; RFE-RF) was utilized to identify the essential features. Then, three ML neural network models were used: SVM, classification and regression tree, and model averaging [37].

The finest flood-influencing indices for identifying regions that are particularly vulnerable to floods were chosen. The DEMATEL approach, which investigates the connection among criteria and creates a network structure that is a good representation of the issue, was used to study these issues. The analytical network method was used to determine the relative significance of various flood-influencing elements (ANP) [38].

A non-structural strategy to prevent and lessen the harmful consequences of flooding includes a spatial analysis of flood susceptibility (FS). As a result, the initial study suggests a new approach for determining the FS in the Kashkan Watershed, a watershed in an area of Iran that is frequently inundated. The DEMATEL technique was employed to undertake the first interconnectivity assessment of the criteria, which included distance to residential areas, distance to stream, land use, and distance to roads. The entire network’s cause and effect components, as well as their levels of interaction, were therefore examined So that the interdependency relationships can then be used [39].

In light of ongoing urbanization and global warming, urban flood-risk modeling is a crucial tool for flood control. Nevertheless, most developing nations lack the precise data necessary to generate accurate risk maps using the techniques now in use. In order to integrate current information with softer semi-subjective information, including assessments of flood-prone areas made by citizens and susceptible areas in light of existing communities, managers and decision makers need enhanced approaches. In order to help structure the problem framework, we thus provide a novel method utilizing the semi-subjective AHP, which combines actual and perceived evaluations. In order to select a solution, this method generates pairwise comparisons, measures the consistency of decision makers’ assessments, and takes into account both main and supporting factors [40].

Due to human activity and environment interference, the steep watersheds are getting more and more threatened by severe attenuation and catastrophic floods. The design of mitigation measures, the development of local policies for prevention, and adaptation to extremes all depend on hazard mapping. This work suggests brand-new forecasting algorithms for mapping flood and erosion risk. This research depicts on how to prioritize the current sub-basins based on their vulnerability to erosion and flooding. To provide the maximum predictive performance, a comparison of the multivariate adaptive regression spline (MARS), generalized linear model (GLM), RF, flexible discriminate analyses, and their ensemble is carried out. Additionally, the most productive model was used to rank the sub-basins according to their sensitivity to erosion and flooding [41].

For the first time, this study used three novel algorithms, MDA and CART and SVM, widely utilized techniques, were combined to generate a FS model. The ensemble modeling approach is used to map sensitivity. The most essential criteria in flood vulnerability mapping were those derived from the river. The fundamental constraint of this study was the scarcity of data. Points of flooding, according to the authors’ judgment, it could be useful for doing field surveys and obtaining information. Local stakeholders should work together to improve flood location data, particularly in developing countries with a lack of data. The current study’s data suggested that a residential area at Khiyav-Chai watershed’s outlet is extremely vulnerable to flooding [42].

TOPSIS, a decision-making technique based on socioeconomic parameters such as building history, population density, building density, and socioeconomic state, was used for urban flood vulnerability research. Finally, using flood vulnerability and hazard maps, urban flood risk map for Jiroft was created. The RF model produced the most detailed map of the three models examined. According to the findings, the most critical element in urban flood risk modeling is density of urban distance to urban drainages. Flooding is most likely in locations with a high or very densely populated area, as one might assume. These findings suggest that flood risk mapping can help with priority planning in flood risk mitigation, particularly in locations with insufficient hydrological data [43].

Multi time interpolation is better for large scale flood vulnerability. The BT and RS methods are as long as ten rounds of data resampling for model testing and learning. The mean of ten runs of forecasting is then used to generate flood susceptibility maps (FSMs). This technique was used in Ardabil Province, which is located on the Caspian Sea’s coastline borders and has experienced devastating floods. To assess the precision of prediction of the presented models, true skill statistic (TSS), receiver operating characteristic (ROC), the area under the curve (AUC) of the receiver, and correlation coefficient (COR) were used [44].

Flash floods are becoming more well recognized as a common natural danger around the world. Iran was one of the most seriously affected areas by the floods. While periodic flash-flood prediction models are primarily intended models for identifying hazardous areas, fore- warning systems can contribute greatly to reducing disaster risk and strategy for adaptation and mitigation. Previous research in flash-flood threat mapping has enhanced the desire for more scale simulation. As a result, the current research proposes cutting-edge ensemble models of boosted RF and GLMBoost methodologies, as well as Bayesian linear programming model (BayesGLM) methodologies for improved performance modeling. Moreover, simulated annealing (SA) is utilized as a pre-processing method to remove superfluous factors extracted from the modeling approach [45].

1.1 Research significance

A significant study has been done in recent decades to investigate the factors that influence flood analysis with respect to climate change, and some valuable results have been reached. In the contemporary area, other assessment studies are carried out, although these are mostly manual analyses. This research examines the application of ML algorithms for flood forecasting in locations where indicators or advanced sensing devices are around. This article attempted to provide a complete overview of prior research on vulnerability, flood risks, and flood vulnerability. ML methods, based on past data, statistically describe the nonlinearity of the flood without having any knowledge of the basic physical methods and high efficiency related to physical systems with low processing costs, quick training, validation, testing, evaluation, and minimal intricacy. Furthermore, ML methods such as decision trees (DTs) accurately identify similar groups with varying susceptibility levels. This method works quickly and efficiently, and ANNs find long-term evaporation and transpiration and rainfall forecasting and present excellent abilities of ANN models. The wavelet neural networks (WNNs) develop a reliable streamflow prediction model that would be helpful in flood control efforts.

This work focused on developing countries and their strategies to cope with floods. Furthermore, the safeguards in place to alleviate the consequences of flash floods are insufficient. The study explored numerous forms of vulnerability and various vulnerability indicators and procedures for calculating the vulnerability index. The purpose of this article is to provide current flood analysis techniques, emphasizing the methodology employed. Highlighting current research goals and the essential procedures may assist in swiftly selecting the best research method and identifying critical gaps that should be addressed in future studies. This research study is divided into four sections. Section 1 introduces ML and the hydrogeological hazard as flood. Section 2 discusses the importance of research. Further, the methodology of Scientometric analysis is described in Section 3. Section 4 describes flood-prone areas, Section 5 presents the methods of ML used for flood forecasting, Section 6 is discussion, and Section 7 is about the conclusion and future results.

2 Methods

A Scientometric analysis of bibliometric data [46,47] on flood analysis technique and flood vulnerability in the Asian area was carried out in this work. The main motivation for creating a Scientometric review approach is because academics’ subjective interpretations of hydrological occurrences have been demonstrated to be prone to mistakes. When applied alone, Scientometric generates a more reasonable and less biased conclusion since it is unaffected by the viewpoint of any person [48,49]. This study compiles and synthesizes studies over the last two decades. This study uses maps and links between bibliometric data to quantify research progress, resulting in a quantitative evaluation.

On the present issue, several documents have been published, and it is critical to choose the most accurate database. Scopus and Web of Science [50] are the two most effective, comprehensive, and impartial databases for doing literature searches. Scopus [51] has a wider bibliometric coverage and more current data than Web of Science [21]. The bibliometric data for the present study on the usage of waste material in concrete were compiled using Scopus. In August 2021, bibliometric data were searched in the Scopus database. The searched keywords and the number of articles returned were reported to get relevant articles from the Scopus database. Researchers in a variety of domains have used similar strategies in the past [52]. Figure 1 depicts the Scientometric analysis procedure as well as the different filters/limits used at various stages [53].

Figure 1 
               Scientometric analysis.
Figure 1

Scientometric analysis.

2.1 Publications per year

Each searched keyword’s yearly publishing trend has been presented. The term “Floods in Asia” yielded the majority of documents (3,374). Between 2004 and 2009, there were 1,132 total publications (sum of all keyword results), which might be considered a peak era. Following that, from 2010 to 2019, there was a significant increase in the number of publications (total: 1,744), but a steady reduction in comparison to the preceding 6 years, and this era may be characterized as a pick-up and pace phase. It is amazing to observe how academics are increasingly emphasizing environmentally friendly study in their studies. It is crucial to note that while searching for various keywords, there is the possibility of finding duplicate articles, which are then added to the total number of publications, which is a restriction of our research. Figure 2 shows the number of publications per year.

Figure 2 
                  Number of publications per year.
Figure 2

Number of publications per year.

2.2 Journal publishing

Source mapping allows for the evaluation of system analysis and design visualization. These resources provide us with the access to information that is limited by certain restrictions. The research pattern may be used progressively in the analysis area after initializing the mapping of research sources. This research was carried out using the VOS viewer and Scopus bibliometric data. The “analysis type” was selected as “bibliographic coupling,” and the “analysis unit” was chosen as “sources.” The minimum number of documents required for a source was set at 20, and 13 of the 605 sources satisfied this requirement. Table 1 shows the top sources/journals that published at least 50 papers on waste material usage in concrete, as well as the number of citations and overall link strength. Flood analysis, journal of hydrology, and hydrological processes, geomorphology, natural hazards, journal of geological society, and geophysical research are the top six journals in terms of published documents, contributing 22, 20, 15, 15, 10, and 9%, respectively. The top three journals in terms of citation count were the journal of hydrology, geomorphology, and hydrological process research, with 5,575, 2,668, and 2,582 citations, respectively (Figure 3).

Table 1

Top journals for flood analysis

Source Documents Citations Total link strength
Journal of hydrology 64 5,575 36
Geomorphology 42 2,668 19
Hydrology processes 59 2,582 18
Quaternary international 20 752 13
Natural hazards 42 1,292 10
Journal of hydrologic engineering 21 1,010 6
Journal of geological society 30 338 6
Science of total environment 22 1,063 6
Journal of hydro-environment research 26 671 4
Water resources management 22 1,064 4
Figure 3 
                  Source mapping.
Figure 3

Source mapping.

2.3 Keywords mapping

Keywords are useful research material that identify and reflect the study domain’s basic topic. Table 2 shows the top 12 terms in the current study area that appear most often in research publications. Asia, flooding with floods, flooding, Asia, China, and Eurasia are the most regularly used terms in the related subject, accounting for the top five. The keywords network co-occurrence visualization and linkages are shown in Figure 4. The frequency of a term is represented by the size of the keyword node, while the location of the keyword is represented by its co-occurrence in published articles. The picture also shows that the aforementioned keywords have more nodes than the others, meaning that they are the most important terms in the current research topic. Various colors have been used to indicate keyword clusters in the figure, suggesting keyword co-occurrence in different published articles. The colors red, green, and blue show three groups of keywords. This discovery will be valuable to authors in the future when selecting keywords and obtaining relevant articles.

Table 2

Frequently occurred keywords

Keyword Occurrences Total link strength
Asia 1,345 8,672
Eurasia 1,221 8,115
Far east 669 4,727
Floods 466 3,565
China 517 3,448
Flooding 329 2,453
Rivers 261 2,319
South Asia 379 2,274
Flood 302 2,022
Flood control 225 1,845
Climate change 278 1,793
India 265 1,793
Figure 4 
                  Keywords mapping.
Figure 4

Keywords mapping.

2.4 Top countries

Some countries have contributed more in the past and continue to do so in the current research area than others. Table 3 shows the major contributing countries in terms of the number of publications and citations in the subject field. In terms of total papers, China, the United States, and India were the top three contributors, with 543, 398, and 285 documents, respectively. The United States, China, and the United Kingdom were the top three participating nations in terms of citation count, with 23,383, 31,302, and 14,133 citations, respectively. The impact of a country on the development of the current research field is measured by the number of documents, citations, and overall link strength. The overall connection strength shows how a region’s publications affect other locations involved in these study fields. China has the greatest overall link strength (837), followed by the United States (789) and India (420). As a result, the nations in the aforementioned areas were deemed to be the most influential in the subject of sustainable development. The nations’ relationship in terms of citations is seen in Figure 5. The size of the frame depicts the region’s involvement in the relevant research area. The graphical depiction of participating nations will aid future academics in developing scientific relationships, generating joint venture reports, and exchanging innovative strategies and methodologies.

Table 3

Highly cited countries

Country Documents Citations Total link strength
China 543 31,302 837
United States 398 23,383 789
India 285 10,883 420
United Kingdom 183 14,133 387
Japan 263 11,487 354
Australia 106 7,742 349
Philippines 40 3,323 259
Germany 132 7,056 233
Taiwan 106 5,037 193
Vietnam 61 2,749 186
Figure 5 
                  Top countries.
Figure 5

Top countries.

3 Case study of Asian countries

3.1 China

Floods are a commonly found hazard in China. Between 1950 and 2018, floods in China caused the death of 282,737 individuals, destroyed 6 billion acres of land, and economically cost $6,000 billion [54]. However, the external effects of storms were not addressed. Since 1950, the amount of flood-damaged land has increased, indicating a possible increase in flood damage, despite a decrease in flood-related death [55]. China is now one of the world’s largest most flood-prone nations, and its weather is anticipated to vary as much as the worldwide average this century [56]. In China, demographic vulnerability and possible damage from coastal flooding in the twenty-first century [56,57]. In contrast, using a modeled flood damage map, gridded land for development, and differentiated community datasets, spatiotemporal variations in urban land, and population in floodplains were explored, and fast increases in flood vulnerability were shown to be associated with urban growth [58]. Satellite-based nighttime light data, which provide a rare chance to actually monitor movement of people from space, have been extensively used as a proxy for human activities in the past few decades, thanks to the advent of numerous nighttime sensing devices [59]. At a given location, outburst floods have the ability to deliver substantially greater peak flows than climatic floods. Despite the fact that we catalogued 287 landslide dams, the majority of which had undergone outburst floods, numerical for just a handful of the floods was accessible [60]. Only 24 avalanche dam outbursts have peak flood flow values, 20 of which were explicitly documented and 4 via hydro-geological or uses the process data such as dammed reservoir layers, dam proportions, and flooding cross-section [61]. Flood exposure reduces from the eastern coastal regions to the middle and western regions in general. In Tianjin, Shanghai, Henan, Jiangsu, Shandong, and Beijing [62], the overall population vulnerable to floods is around 500 people per square kilometer. Shanghai has the most exposure community, with 2,556 people per square kilometer [63]. Major events of flood in China are shown in Table 4. Monsoon season of China is shown in Figure 6.

Table 4

Key events of flood prone areas in China

Location Cause Remarks Ref.
Wuhan Intense rainstorm The Sponge City concept is proposed as a replacement for conventional green technologies [54]
Huaihe River Natural unique future Developing flood complexes may generate risk dispersion, therefore we must address risk propagation effectively; different areas must exchange flood risk strategies and develop risk of flooding settlement and coverage methods [64]
province China has set out on a bold and determined mission to improve flood readiness by implementing various physical (“hard”) and non-structural (“soft”) solutions, such as flood retention and urban flood control, to reduce the impact of flashing and metropolitan floods [65]
province China has set off on a new path. The installation of rainfall reservoirs and the regular upkeep of streams and rivers and banks are considered crucial structural strategies. Non-structural precautions, such as emergency preparation, are also critical [57]
province Typhoon has already wreaked havoc on large rainwater basins and sewage infrastructure Integrating the flood simulation to real-time rainfall and tidal projections would allow for real-time flood risk calculation and, as a result, effective flood mitigation measures [29]
Guangzhou Rainfall It is also advised that flash flood data in flood-prone regions be gathered on a regular basis so that more appropriate policies and measures to minimize flood flows may be devised [54]
Figure 6 
                  Rainfall season of China [66].
Figure 6

Rainfall season of China [66].

3.2 India

The Uttarakhand floods of June 16–17, 2013, wreaked havoc on lives and properties. Heavy rains in the Kedarnath valley caused flash floods in the Mandakini and Saraswati Rivers [67]. In addition, owing to glacier/melting snow and glacier mountain ranges, the Mahatma Gandhi Sagar glacial lake outburst flood (GLOF) enhanced runoff towards Kedarnath and downstream displays the region’s strong and isolated rainfall from June 14 to June 19, 2013 [68].

This resulted in an occluded discontinuity and pulsed extension of monsoon across the Himalayas during the Uttarakhand flood [69]. In the high troposphere, the chilly gradient of the frontal WD (warmer in the lead, cooler in the tail) and the warmer, more humid monsoon flow in the lower troposphere caused this discontinuity [70]. Consequently, a thorough knowledge of these interactions was gained by high-resolution modeling and observational analyses. Floods occurred in Jammu and Kashmir and neighboring states as a result of depressions over Rajasthan recurving northward or northeastward, causing flash flooding [71]. Low pressure systems in the lower troposphere were coupled with a trough in the upper-level westerlies, which had an embedded jet stream 35, which resulted in a significant amount of moisture being absorbed [72]. The interplay between the low westward-moving monsoon and the eastward-moving deep trough in the mid-latitude westerlies 36 results in continuous heavy rainfall [73]. The state’s historical rainfall data indicates that the occurrence was unusual and may be classified as belonging to the “never before” group. The rainfall totals in Anantnag, Kukernag, and Quazigand topped prior records by 24, 48, and 72 h, respectively, while the rainfall totals at Katra beat previous records by 48 and 72 h [74].

The total rainfall reported in the Chennai district from November 1 to December 5, 2015 was 1416.8 mm, compared to the typical rainfall of 408.4 mm during the same period in 2014 [75]. In the Indian area, an anomalous mid tropospheric high located to the west of the region might cause anomalous northerly winds to blow to the north, preventing propagating storms from moving farther north and west [76]. Because of this, dry weather prevailed in the northwest Indian area while wet conditions prevailed in the southeast Indian peninsula; for example, an anomalous high pressure system over the Middle East around November resulted in higher rainfall across southern India [77].

While the rest of the world’s sea surface temperature has increased significantly over the last 35 years, temperatures in the northern and western Bay of Bengal have hardly changed at all. At this point, it is impossible to determine if global warming had a role in the incidence of excessive 1 day rainfall that caused extensive flooding in Chennai in December 2015 [78].

On December 1, 2015, heavy rainfall was caused by the creation of deep convective clouds that moved from the Bay of Bengal to Chennai city [79]. As a result of the obstruction of the natural drainage network, flood water remained stagnant in local depressions long after the water level in the Jhelum River had fallen. A number of studies conducted prior to the flood event have indicated that rapid urbanization, deforestation, and unrestrained land-use changes, such as encroachment in wetlands such as the littorals of the Dal and Anchar Rivers, Hokrasar Lake, and Narkara Lake, pose a significant threat to the water supply. Since 1972, the built-up area within Srinagar city limits has increased by approximately 29.20% (from 18.10– 84.50 km2), which is nearly three times the rate of population growth and observations clearly point to the encroachment of natural flood ways in the city [80]. These studies clearly stated that the depletion and degradation of wetlands as a result of excessive siltation, rapid urbanization, and encroachments have a negative impact on their ability to retain floodwaters, including flash flood waters during peak discharge, and that they require immediate restoration to function properly [77]. To effectively combat this type of natural hazard phenomenon, FS mapping is required. Based on these considerations, we investigated whether FS mapping may improve forecast accuracy in the Koiya River basin (Eastern India) [81]. Figure 7 shows the flood in eastern India.

Figure 7 
                  Flood in Eastern India: (a) bridge under water, (b) flooding in large area, (c) car and houses flooded with water, and (d) local boat is the main medium of transportation during flooding [81].
Figure 7

Flood in Eastern India: (a) bridge under water, (b) flooding in large area, (c) car and houses flooded with water, and (d) local boat is the main medium of transportation during flooding [81].

3.3 Nepal

The Himalayas are the source of the most of Nepal’s long-lasting rivers [82]. Stable rainfall (snow) and mountains play a critical role within Nepal’s key water resources, while rainfall water is immediately released into rivers in a relatively short time frame, resulting in flash floods [83]. In Nepal, the monsoon season (June–September) accounts for around 80% of total yearly precipitation, whereas winter snowfall accounts for about 3% of total annual heavy rainfall [84]. During the dry season of the year, the rainwater that melts contributes greatly to the mountain regions’ continual base flow. The GLOF, on the other hand, is one of the major worries. Most of the glacier lakes in Nepal Himalayas have been embanked by a sediment dam built during the modernity era [85]. These dams are often unconsolidated and inherently unstable. The catastrophic flood might cause issues not just for the infrastructure but also for the people living downstream. As a result, mitigating methods like regulated breaching, syphoning surplus lake water, and constructing a route under the moraine barrier are required to manage the GLOF. Nepal has around 6,000 rivers and rivulets flowing through it. Snow-fed rivers like the Narayani, Karnali, and Koshi are perennial among them [86]. These rivers travel across the Terai plains and originate in the Himalayas. During the monsoon season, from June to September, the flow in rivers increase much more, affecting the adjacent settlements. The following years saw large floods in Nepal: Tinao Basin (1978), Koshi River (1980), Tadi River Basin (1985), Sunkoshi Basin (1987), and the devastating floods triggered by a cloud burst in the Kulekhani region (1993), which killed over 1,336 people [87]. The most recent Koshi flood, which occurred in 2008, harmed around 200,000 people. Between April and May of this year, an interdisciplinary field research of past GLOFs in Nepal’s Kanchenjunga area was done. Since 1921, at least six large GLOFs have occurred in the area, according to oral history and field data [88]. A remote sensing investigation validated the existence of the six GLOFs indicated by informants, as well as two minor flood events that happened before 1962 but were not documented. According to a computer simulation of the Nangama GLOF, it was initiated by an ice/debris avalanche releasing 800,000 m3 of material, generating a rush wave that crossed the final moraine and unleashed 11.2 × 106 m3 ± 1.4 × 106 m3 of water (Figure 8). Several sources in Tapetok stated that the 1963 Olangchun Gola 1 flood was worst they had ever seen, almost affecting their homes 100 m well above river [89] (Figure 9).

Figure 8 
                  Nangama glacial lake and Chheche Pokhari 1980 GLOF [87].
Figure 8

Nangama glacial lake and Chheche Pokhari 1980 GLOF [87].

Figure 9 
                  Tapetok (1,380 m) on the Tamor. Flooding from the 1963 Olangchun Gola 1 GLOF almost reached the residences in the backdrop, or around 100 m above the river channel, according to eyewitnesses [87].
Figure 9

Tapetok (1,380 m) on the Tamor. Flooding from the 1963 Olangchun Gola 1 GLOF almost reached the residences in the backdrop, or around 100 m above the river channel, according to eyewitnesses [87].

3.4 Pakistan

When it comes to floods, topography has a significant impact. There are two major mountain ranges in Pakistan, the Hindu Kush and Karakoram mountains. Between 1,000 and 8,000 m above sea level, the snow-clad summits of the northern parts may be found. If you are looking for an example of the world’s highest peaks (above 8,000 m), go no farther than K-2, Gasherbrum II, the Broad Peak and the Gasherbrum [90]. There are almost 68 mountains in Pakistan that are above 7,000 m high. Floods caused by heavy rain and cyclones are the most common. In addition, tiny dams have been breached, resulting in very high floods. A large portion of the nation (59.3%) gets rainfall of less than 200 mm per year. However, the Himalayas get between 760 and 1,270 mm of annual rainfall, which accounts for over two-thirds of the average annual rainfall in the Indus River System. More than 594,700 km2 of land were inundated, affecting 166,075 communities, resulting in nearly $30 billion in direct damages and the deaths of 10,668 people over the course of the last 60 years [91]. During the rainy season, rain is one of the primary causes of flooding in Pakistan, which is often aided by river snowmelt. Snowmelt upstream of Tarbela Dam contributes to the rainy discharge in northern Pakistan. However, during the monsoon season, urban floods are widespread in Pakistan’s several cities, including Karachi, Islamabad, Lahore, and Hyderabad. Recent instances include the cyclones Yemyin and Phet that hit Pakistan in 2007 and 2010, respectively [75]. The 2010 floods caused unprecedented devastation and claimed the lives of about 1,985 people. Every province in Pakistan has a different kind of flooding. Consequently, it is a difficult challenge to solve, especially for those in charge of flood control. Many rivers have distinct catchment regions due to a variety of factors including geography, demographics, and socioeconomic situations. Climate change caused by human activity is cited by the Intergovernmental Panel on Climate Change as one of the causes driving up Asian monsoon rainfall levels. However, this condition may be difficult to meet until more scientific research is done. Flood embankments on the Indus River’s crest make the riverbed rise over the surrounding regions. As a result, the cheap regions remain wet for a longer length of time since the flow that exits the river does not rejoin the stream. Because Sindh’s tail links to the Arabian Sea, it is impossible to implement flood preventive actions in the province’s upper portion. From Guddu until a few kilometers short of the Arabian Sea, a double line of flood berms has been constructed on both banks of the river in the majority of the cracks. In Punjab, defensive marginal bunds have been constructed to maintain irrigation infrastructure and headworks, or to defend particular towns and communities. In the event that flood levels rise over the planned level, pre-determined breaching portions will be available [92]. In order to prevent erosion, spurs have been installed in high-risk regions. Most rivers in Balochistan have high bed slopes because of the region’s terrain. Besides the low-lying regions along the river banks, flash floods induce banks to crumble due to their force and velocity. There are embankment barriers or short spurs protecting agricultural land from the direct effect of flash floods [93]. Flood flow channels were built to disperse the surge of flood water. Irrigation water is also diverted from these sources. Most rivers in centrally governed regions have been plagued by bank erosion because of their high bed slopes. As a result, water bypasses have been built to spread the flood flow, which is also utilized for irrigation of agricultural community. The goal of this research is to determine the effect of the 2010–2011 flash floods on agricultural output in Sanghar, Sindh’s eastern district as shown in Figure 10. Agriculture is the major source of income for the over two million people that live there. Cotton, sugarcane, and wheat are the district’s principal cash crops. Sanghar was devastated by flash floods in 2010–2011 as a result of severe rains. These floods had a negative impact on the crops that were growing at the time. They did, on the other hand, improve the fertility of agricultural soils. Floods were quantified by mapping pre- and post-flood plant cover using satellite photos, precipitation data, and geographic information system (GIS) tools. From 2009 to 2013, supervised classification was used to derive vegetation area from Landsat photos [94]. The post-flood years show a large increase in plant cover, according to the temporal study. Furthermore, the research findings were corroborated by a comparison of pre- and post-flood agricultural production data obtained from the Pakistan Bureau of Statistics, which revealed an increase in crop output [95].

Figure 10 
                  Sanghar distract [95].
Figure 10

Sanghar distract [95].

3.5 Bangladesh

Bangladesh bears the repercussions of its placement in the Ganges–Brahmaputra–Meghna (GBM) river basin low-lying fluvial floodplain every year. Approximately 80% of Bangladesh’s territory is covered by flood plains, with up to 34% of the country’s land area submerged for 5–7 months each year [96]. Flooding is becoming more common in Bangladesh, according to research, and flooding is anticipated to become more common as a result of climate change. Flooding is a natural occurrence that occurs annually in Bangladesh. Bangladesh is susceptible nations to natural disasters due to its geography. Floods are one of the key obstacles to Bangladesh economic growth and planning; in other words, catastrophic floods, which occur regularly, are one of the country’s most critical handicaps [97]. Bangladesh is the second most flood-affected nation in the world, with a population of over a billion people. Flooding normally begins in the first week of June, lasts until October or November, and inundates nearly one-third of Bangladesh’s land area. This yearly flood phenomenon is typically beneficial to farmers. It is known as “Borsha,” and it assists farmers in cultivating their agricultural areas amid flood waters, as well as the “Aman” crops, which need flood water to develop correctly [98]. As a result, flooding is a helpful tool for watering and enriching agricultural regions. Even in years with regular rainfall, the monsoon populates 20–30% of the land each year. The regular series of floods in Bangladesh begins in April and May with severe flooding in the north and east highlands; in a flash flood, rivers rise fast and recede quickly, generally in a matter of days or hours. The enormous GBM River Basin receives most of the flood water. The monsoon has an impact on the whole GBM River. Heavy seasonal rainfall, which falls 80% of the time between June and October, and snow melt water from the Himalayas, find an outlet to the sea via the Bengal basin, which accounts for around 7.5% of the total river catchment of the main river systems. Flooding in Bangladesh has been caused by the building of barrages and protection works along the banks of the rivers, notably upstream (India, Nepal, and Bhutan). As a result of Bangladesh’s storm surge measures, such as the Brahmaputra right bank dam and Chalan beel dam barrier, floods have become more intense in areas that are not covered [99]. Precipitation of river-borne sediments is the fundamental process for delta formation. The projected embankments would prevent sedimentation on Bangladesh’s delta plain from aggravating riverbeds and causing the lands behind the embankments to be submerged by the increasing sea. Other issues that might arise as a result of the execution of such a megaproject include flash floods, significant river channel modifications, the loss of a large amount of land to the project, loss of land fertility, and possibly population displacement. Building such embankments would need ongoing maintenance for decades, which will be a difficult challenge for Bangladesh. Flood is one of Bangladesh’s most prevalent natural catastrophes. Bangladesh has been hit by various sorts of disasters practically every year in the past. Each flood has a severe impact on the country’s people, livelihoods, and properties. However, both the state and non-government organizations in Bangladesh have made a variety of steps to mitigate the negative effects of floods. According to this report, implementing a comprehensive flood management strategy and a coordinated strategy among the various flood control players can help Bangladesh reduce flood risk. The communities of Nowapara and Pashurbunia were chosen due to their proximity to the Bay of Bengal, socioeconomic instability (i.e., living below the poverty line), and susceptibility to cyclone catastrophes. These two groups are illustrative of the overall situation of coastal Bangladeshi populations. The Bangladesh Water Development Board owns the wall, which is situated between 20 and 500 m of the Rabnabad Channel and feeds both villages (Figure 11a and b). Majority of the houses are in close proximity to the canal and wall (Figure 11c and d).

Figure 11 
                  (a and b) The community’s embankment and (c and d) houses positioned close to the Rabnabad Channel [99].
Figure 11

(a and b) The community’s embankment and (c and d) houses positioned close to the Rabnabad Channel [99].

3.6 Sri Lanka

Examined the qualitative evaluation of flood risk in Sri Lanka western province. We employed an index that has only weighted variables for this investigation [100]. Risk, susceptibility, and vulnerability indexes are used to create this risk score. Thus, a risk, exposure, and relative risk maps have been created. Only one of the eight (0.9%) GN Divisions has a very high flood danger, while only four of the eight have a high flash flood. A flood risk map may be used to identify the GN Divisions at risk of flooding and determine the relevant disaster mitigation strategies before undertaking planned projects in the region. The resulting data may be used to influence choices about disaster preparation, early warning, and other measures that can be put in place to improve a vulnerable population’s adaptive ability and lower their catastrophe risk. The study’s findings also include recommendations regarding how much money should be set aside for disaster relief and recovery efforts once flood has occurred. Gumblel model was used for recovery process of Ratnapura Divisional Secretariat region. The major approach utilized in this research was a GIS, which included a digital terrain model and data from the previous 21 years of flood heights [101]. Low, medium, and high flood danger maps, as well as likelihood of inundation maps, were generated during the course of the research for 5, 10, 20, 30, 40, 50, and 100 years. The flood maps revealed that 64.3% of the study region is in the high-hazard zone. Ratnapura town, Ratnapura town west, Godigamuwa, Thiriwanaketiya, and Weralupe are among them. These flood maps are essential for flood disaster management, rescue and restoration programs, and more. In the Rathnapura area, flood risk reduction measures in vernacular dwellings were investigated. 15 case studies were used to gather information. Chronological analysis approaches were used to examine the case studies. To design flood risk reduction methods for the research region, five factors were established. Location and orientation, plan layout, substructure superstructure, and services are the criteria [102]. The lack of contemporary materials and professional expertise in the district’s case study region was discovered in this investigation. As a result, this research will be utilized to create materials and building procedures in flood-prone regions of Sri Lanka. The potential of a fifteenth century canal system in Sri Lanka’s Metro Colombo region to regulate floods was investigated. MIKE FLOOD modeled the canal system for 10, 25, and 50 year rainfall return periods to attain the desired flood levels. The flood levels, inundation distributions, and impacted populations were all taken into account while analyzing the effects of the rainfalls in question. In the research, two simulation scenarios based on river boundary conditions were run, and they were classed as favorable and least favorable. It was discovered that, under current circumstances, the canal system could only manage a 10 year rainfall flood event in the best-case scenario. As a result, the canal system’s long-term viability in the face of future catastrophic occurrences is doubtful. Four interventions were developed to reduce such floods, and their effects were assessed. The flood water levels were dropped locally when the countermeasures were implemented one at a time, and they were not up to the flood safety standards of the surrounding region. When all four countermeasures were implemented simultaneously, flood water levels were dramatically reduced below flood safety limits under a 50 year design rainfall under ideal conditions. When all four countermeasures were used in a combined manner, the flooded area was significantly reduced. In that situation, the flooding area was reduced by 46%, and the number of persons impacted was reduced by 49% [103].

4 Flood forecasting by using ML algorithms

4.1 DT algorithms

It is one of the contributors to predictive modeling, and it has a broad range of applications in flood simulation, including the ML technique of DT. DT makes use of a decision tree that extends from the branches to the goal values of the leaves. Classes are represented by leaves in classification trees, and features are represented by conjunctions of feature labels in DTs as shown in Figure 12. The final variables in a DT contain a discrete set of values, where leaves represent class labels and branches represent conjunctions of feature labels. An ensemble of trees is used to construct a regression tree when the target variable in a DT has continuous values and an ensemble of trees is used to construct the DT (RT) [104,105]. There are several parallels and distinctions between regression and classification trees. Due to the fact that DTs are considered fast algorithms, they have become particularly popular in ensemble forms for modeling and forecasting floods. The classification and regression trees are two types of trees (CART) [106,107]. The DT is a ML technique that may be used for classification and regression problems. It worked in a similar manner to SVM. The DT and the bagged decision are the same thing. The main difference is that the forecasting model does not use the whole set of data as input, as opposed to the previous method [108]. A variety of tree predictors are included in RF. A collection of response predictor values is generated for each individual tree, which is then connected with a set of independent values. Furthermore, an ensemble of these trees finds the most appropriate set of classes for a given situation [109]. The flood prediction modeling field, RF, has been proposed as a viable alternative to SVM, which in many cases provides superior performance [110]. It was determined that the performance of ANN, SVM, and RF in general applications to floods was the best, with RF delivering the greatest results [111]. In order to reduce the variance of the final variable, M5 divides the decision space into single characteristics and generates a DT from those single qualities. Additional decision-tree algorithms that are commonly used in flood prediction include reduced-error pruning trees, Naive Bayes trees, chi-squared automatic interaction detectors (CHAIDs), logistic model trees, alternating decision trees, and exhaustive CHAIDs, to name a few [112].

Figure 12 
                  Classification diagram of DT [113].
Figure 12

Classification diagram of DT [113].

4.2 ANN

ANN model is made up of input, hidden, and output layers and is built on the perceptron method, which is similar to human neurons. Every layer is made up of nodes, which are the fundamental computational units of a neural network [114]. Each node is linked to the others to use a feed forward mechanism that takes linkages into account while computing node simulation. A feed forward back propagation neural network with one input layer, one hidden layer, and one output layer is shown in Figure 13. As effective mathematical modeling systems with efficient parallel processing, ANNs are capable of simulating the behavior of a biological neural network by employing interconnected neuron units. ANNs are the most common learning algorithms among all ML techniques, and they are well-known for being adaptable and efficient at modeling complex flood processes with a high fault tolerance and precise approximation [115]. When compared to standard statistical models, the ANN technique was shown to be more accurate in terms of prediction accuracy [116]. ANNs, rather than relying on a catchment’s physical qualities, gain significance from past data. As a result, ANNs are regarded as trustworthy data-driven methods for developing black-box models of complicated and nonlinear rainfall and flood connections [117]. Though ANNs have several benefits, they also have a number of disadvantages when used in flood modeling, including network construction, data management, and physical interpretation of the studied system. When employing ANNs, the poor precision, the need to repeat parameter adjustment, and the delayed reaction time to gradient-based learning processes are all significant disadvantages to be aware of [118]. Modeled flash floods, using ANN and ANFIS, used a dataset compiled from 14 distinct streamflow gauge sites to get the desired results. The assessment criteria were the root mean square error and the R 2 coefficient. When compared to ANN, the findings indicated that adaptive neuro-fuzzy inference system (ANFIS) displayed a much greater capacity to predict real-time flash floods [119]. A large number of ANNs were designed and the results were compared. In order to teach the researchers, they picked water level data from various stations between 1970 and 1985, and the data from 1986 to 1987 were utilized for verification. The ANNs performed well, even in cases when the dataset was not full, and they were a feasible option for making correct predictions. ANNs introduced the prospect of lowering analytical expenses by decreasing the amount of time spent on data analysis that was previously required [120].

Figure 13 
                  General diagram of ANN [121].
Figure 13

General diagram of ANN [121].

4.3 Ensemble prediction systems

Ensemble learning basic idea is to reduce the probability of inference mistakes caused by a single classification model. Although the various classification models employed in ensemble learning have similar training outcomes and levels of accuracy, they also have distinct generalization capabilities, or inferential skills about diverse samples. The outcomes of these separate classification models are eventually integrated to provide the final classification performance, reducing the likelihood of misclassification dramatically. Furthermore, in ensemble learning, integrating the multiple inference outputs of many classifiers may not always lead to a good classification than employing the best particular classifier in the ensemble. Ensemble learning, on the other hand, has a high possibility of lowering the risk of selecting an especially terrible choice and improving overall classification prediction reliability [122]. Breiman introduced the bagging (bootstrap aggregating) ML ensemble technique in 1994. The bagging procedure divides the primary training dataset into numerous training data subsets (bootstrapped datasets), each of which is expected to build a classifier independently. To acquire the ultimate classification performance, the forecast results obtained by different classifiers are then combined via casting as shown in Figure 14. With a solid base in flood modeling, a variety of ML modeling alternatives are offered. As a result, there is a growing trend to move away from a single prediction model and toward an ensemble of models tailored to a certain purpose, cost, and database. ML ensembles are made up of a limited number of different models that provide greater flexibility than the alternatives. In flood prediction, ensemble ML algorithms have a lengthy history. Ensemble prediction methods have become popular in recent years (EPSs) [123]. The benefit of EPS is that it manages and evaluates ensemble techniques in a rapid and appropriate model. As a result, the functionality of EPS, particularly for flood modeling, may be enhanced [124]. EPSs may leverage numerous quick or statistical methods as classifier ensembles, such as ANNs, MLPs, DTs, rotation forest (RF) bootstrap, and boosting, enabling for greater accuracy and resilience in their classification of data. Based on the prediction rate employed in the event, the following ensembles prediction methods may be used to assess the likelihood of flooding. The methods for generating these EPS projections are quite simple. Some practical EPSs are built on a Monte Carlo structure of NWPs, with one realization based on a “central” assessment (the control prediction) and others depending on troubling the baseline circumstances (the perturbed forecasts). Based on the prediction site, the range of clusters ranges from 10 to 50 [125]. It is worth noting that tiny improvements in rainfall data are really not noticeable, which is terrible for hydrology [124].

Figure 14 
                  Flow chart of Bagging (Bootstrap aggregation) [122].
Figure 14

Flow chart of Bagging (Bootstrap aggregation) [122].

4.4 SVM

Statistical process of learning has been used to develop and classify the SV as a nonlinear search method [126]. Subsequently, the SVM was developed as a kind of SV that was intended to lower the predicted error of learning algorithms by minimizing over-fitting. This method is an iterative machine learning that relies on the statistical learning theory and the structural risk reduction rule [111]. The ideal hyperplane performs a policy function in binary integer SVM for classification among two classes related to particular data. There are two approaches to achieving optimum original training categorization. To obtain a complete separation among training sample classes, hard boundary maximization might be used as shown in Figures 15 and 16. The hyperplane conditional probability is used to determine the peak value. It aids in increasing the length between both the hyperplane and the closest training relevant data. After determining the hyperplane, a different dataset may be fed into the SVM classifier. Depending on the direction of the input in relation to the test set, class is given +1 or 1 [2] as shown in Figure 16, in the event of a classification method with many classes. It is often used in flood modeling. SVM’s training process creates algorithms that generate additional non-probabilistic linear programming classifications that, via reverse conflict resolution, reduce the empirical classification error, and maximize the visual gap [127]. SVM is a ML algorithm that predicts a number in the future based on previous data [128]. The SVM has been expanded as a regression technique, termed as SVR, during the last two decades. SVM is still very much in inception in hydrological models, despite its popularity in many other domains. There have been many contradicting outcomes in its use so far. Scientific research shows that SVMs have similar over-fitting and under fit difficulties, although the excessively problem is more detrimental than the under-fitting issue, which has never been well tackled by the scientific community [129]. This is a highly good technique of learning about an SVM model’s function and flaws by seeing how it reacts to varying amounts of rainfall. For now, we do not know what this crucial response characteristic means for SVM’s evolution in hydrology, but future study will surely increase our understanding of this problem and allow models developed to make better use of this data [130].

Figure 15 
                  Binary classification of SVM [2].
Figure 15

Binary classification of SVM [2].

Figure 16 
                  Multi-classification of SVM.
Figure 16

Multi-classification of SVM.

4.5 WNN

Use the wavelet transform (WT) to extract information from multiple data sources by looking at the local fluctuations in time-series data. WT, in reality, has a major impact on simulation results [131]. The dependable decomposition of an original time series by means of a transform helps to enhance the value of the evidence. DWT, which decays the actual information into zones, improves flood forecast lead times by increasing the accuracy of predictions. When developing a model, better information may be extracted using DWT’s decomposition of the basic dataset into distinct resolution levels [132]. DWTs are commonly employed in flooding estimate time because of their advantageous qualities. Rainfall–runoff DWTs were frequently used in flood simulation. Using two large-scale climatic data like SST and SLP as variables, a WNN hybrid model can estimate maximum monthly discharge of the Madarsoo watershed in northern Iran [133]. The achievement of the prediction of highest monthly release of three different hydrometry terminals of the drainage basin was measured using error metrics such as root-mean-square error [134], mean absolute error, and similarity measures such as coefficient of correlation (R), and Nash–Sutcliffe coefficient [135]. To forecast flood discharges in the period from March to August, the WNN hybrid ML model greatly exceeded the solo ANN model and MLR model in all situations [136]. To enhance environmental monitoring equipment, mechanized weather station networks capable of collecting minimum temperature and rainfall data have been installed almost globally since the turn of the century. Thus, there are now many temperature-dependent records available from many places, with few gaps and lasting over a decade [137]. As a result of recent research trying to combine ANN-based hydrology to wavelet analysis, the purpose of this study is to develop and validate various hybrid WNN models to forecast future monthly rainfall in Andalusia (Southern Spain) using only brief thermo-precipitation valid and reliable data sources [126,137]. The ability to predict river flow with high accuracy is critical in lowering the danger of flash flooding. It has become increasingly obvious that data-driven and hybrid strategies are being used to address the nonlinear and changeable aspects of hydraulic systems. As a result, this research introduces a unique hybrid WNN technique for river flow forecasting that includes image enhancement. In order to do this, the wavelet approach is used to evaluate the data that have been acquired as shown in Figure 17.

Figure 17 
                  Wavelet model for reducing flood risk [138].
Figure 17

Wavelet model for reducing flood risk [138].


The fuzzy logic is a descriptive modeling system that employs a soft computing method that is based on natural language to get its results. Fuzzy logic is a reduced mathematical formula that relies on adding expert information into a fuzzy inference system (FIS) to make decisions in uncertain situations. Additionally, an FIS simulates human learning by using an approximation function that is less complicated than the original function, which has considerable promise for nonlinear modeling of severe hydrological processes, notably floods. For example, researchers looked at river level predictions utilizing a GIS, as well as rainfall–runoff models for water level. Neuro-fuzzy is a more sophisticated kind of fuzzy-rule-based modeling that combines the BPNN with the commonly used least-square error approach to produce a hybrid version. The Takagi–Sugeno (T–S) fuzzy modeling approach, which was developed via the use of neuro-fuzzy clustering, is also frequently used in the RFFA industry. ANFIS is a more sophisticated type of neuro-fuzzy that is based on the T–S FIS, which was initially defined in the 1970s. ANFIS is widely regarded as one of the most trustworthy estimators for complicated systems in use today. ANFIS technology, which combines ANNs and fuzzy logic, delivers more learning power. Specifically, this hybrid ML technique relates to a collection of sophisticated fuzzy rules that are ideal for modeling nonlinear flood dynamics. An ANFIS operates by using neural learning algorithms to detect and tune the variables and structure of an FIS. This is how it works. With the use of ANNs, the ANFIS hopes to identify any missing fuzzy sets in the database. ANFIS has become quite prominent in flood modeling because of its quick and simple application, precise learning, and excellent generalization capabilities, among other factors. While BPNNs are now commonly employed in this field, the MLP, a more sophisticated approximation of ANNs, has lately grown in favor as a replacement for them.

4.7 Multilayer perceptron

It is a kind of FFNN that uses supervised learning of BP for training a network of linked nodes of various layers, and it is one of the most often used. The MLP is characterized by its flexibility, nonlinear operation and a significant number of layer combinations. The approach was extensively utilized in flood forecasting and other sophisticated hydrogeological simulations as a result of these properties. MLP models were shown to be more efficient than ANN models in a study of ANN classes being used for flood simulation, as well as having more generalization ability. In spite of this, the MLP is often regarded as more difficult to optimize. Back-percolation training techniques are used to determine the transmission mistake in hidden network nodes on an individual level, allowing for a more sophisticated modeling framework. It is interesting to note that the MLP has acquired levels that are high within hydrologists than any other variety of ANNs (e.g., FFNN, BPNN, and FNN) in recent years. Furthermore, because of the large number of case studies that used the conventional form of MLP, it deviated from the usual form of ANNs. Furthermore, writers of works in the field of flood prediction that makes use of the MLP designate to their methods as MLP models when referring to their models. This was taken into consideration when we determined to create a distinct area for the MLP.

5 Discussion

The stability of these models and the speed at which they can be trained to analyze hydrological data make ML techniques for flood prediction quite effective. These information sources include elements like precipitation, soil moisture, water levels, river inflow, runoff water, streamflow, river flood, frequency of floods, flash floods, peak flow, groundwater level, storm surge, and rainfall stage. Moreover, it is crucial to keep in mind that there can be several flood types, each of which can result from a different purpose, such as increased soil moisture or lengthy stream flow, making it difficult to create reliable flood predictions over the lengthy period [139].

Because of their precision, high fault-tolerant, and powerful parallel computing in dealing with complex flood functions, ANNs are the most often utilized ML approach, particularly when datasets are incomplete [140,141]. However, generalization remains a problem with ANN. ANFIS, MLP, and SVM outperformed ANNs in this setting [142]. However, WTs have been observed to be effective for decompositions of original time series, boosting the capabilities of most ML algorithms by giving insight into datasets at different resolution levels as appropriate data pre-processing. WNNs, for example, often give more consistent outcomes than regular ANNs [141,143]. Most deconstructed ML algorithms (e.g., WNN) were observed to be more accurate, precise, and performant than those trained using un-decomposed time series. Despite the success of WNNs, the estimates for long lead times were inadequate. Novel hybrids such as WARM, a combination of WNN and an autoregressive model, and wavelet multi-resolution analysis were proposed to improve the reliability of longer lead time forecasts up to one year. In other cases, predictive performance was considerably enhanced through breakdown to generate better inputs [144].

This study proposed novel integrative FS prediction models based on multi-time resampling approaches, RS, and BT algorithms, which were combined with ML models such as the GAM, boosted regression tree (BTR), and MARS. The RS and BT algorithms provided ten rounds of data resampling for model learning and testing. The mean of ten runs of predictions is then used to generate FSM. This technique was used in Ardabil Province, which is located on the Caspian Sea’s coastline borders and has experienced devastating floods. To assess the predictive accuracy of the presented models, the AUC of the ROC, TSS, and COR were used [44].

Flash floods are becoming more well recognized as a common natural danger around the world. Iran has been one of the most severely damaged areas by the big floods. While temporal flash-flood prediction models are primarily designed for warning systems, models for identifying hazardous areas can significantly contribute to disaster risk reduction and adaption and mitigation policy making. Former studies in flash-flood danger mapping have increased the desire for the development of more realistic models. As a result, the current study proposes cutting-edge ensemble models of boosted GLMBoost and RF, as well as BayesGLM methodologies for better performance modeling. Moreover, SA is utilized as a pre-processing method to remove superfluous variables from the modeling process [45].

Algorithms for ML have undergone extensive testing in recent years, leading researchers to the conclusion that the strategy is very effective at detecting floods. For the ML algorithms that have been put to the test thus far, accuracy levels of up to 90% have been reported. Algorithms have primarily been studied for binary classifications, where the only choice is to categorize flooded vs unflooded areas [145].

Creating a dependable system that can help with instant communication regarding flooded areas and assist in boosting public safety, rescue, and security procedures is necessary for disaster recovery. The use of ML techniques can improve already-existing systems and perhaps even create new, better emergency preparedness systems [146].

When addressing the post-disaster problem, it is discovered that the adoption of ML-based solutions is uncommon. This necessitates the automation of AI to enhance the post-disaster process flow. Future studies are also promising in the application of AI-enabled big data for flood risk assessment [126].

6 Conclusion and future recommendations

The approach of scientometric assessment is used to identify the most closely linked research subjects, the pattern in paper publication by authors, the co-occurrence of key phrases, and the most active countries in the flood field. Although still in its infancy, ML modeling for flood prediction is already making significant strides forward. This work shows an insight of ML algorithms that have been utilized in flood forecasting, as well as a categorization strategy for analyzing the current research in this field. The conclusion is as follows:

  • Hydrological, geomorphology, hydrology processes, quaternary international, natural hazards, and hydrologic engineering accounted for 64, 42, and 59% of total publications, correspondingly, according to a Scientometric analysis of the data from the database search. Between 2004 and 2009, there was a small rise in the quantity of flood-related publications. Furthermore, data collected between 2000 and 2003 show a considerable drop in the number of publications. Among the most frequently used terms are Asia, floods, China, and far east. In addition, publications about floods were most often provided by China, the United States, and India. With 2,254 citations, Ismail A. M. remained the most often referenced source.

  • In India, high growth and uncontrolled intrusion on groundwater flow paths are destined to choke surface run-off, resulting in overflow and floods. Based on the findings of this research, high-priority zones may be identified for rapid and considerable progress in improving the understanding of severe weather and climate, as well as developing strategies to cope with extreme occurrences in China. The history of modern GLOFs in the Kanchenjunga nature preserve in eastern Nepal was reconstructed using a mix of oral evidence, remote sensing, and numerical flood modeling. A detailed flood management strategy and a coordinated effort among flood control players would help Bangladesh reduce flood risk. In Sri Lanka, flood inundation maps showed more regions flooded nearer to the river discharge point than in ideal hydrological conditions.

  • The ANN model only takes one factor, and is proven to be useful for generating flood-related forecasts. SVM is good at transforming non-separable categories into separate panel by using a particular function called kernel trick to transform low-dimensional input vector into elevated input space. As a result, it can process extremely complicated data and samples obtained depending on labels. SVM is better for smaller datasets and assigns labels directly because it is not a way of estimating. Both for classification and prediction, DDTs, also called as supervised learning methods, are used. It produces a model that predicts the target variable by applying ML techniques based on the information derived from data attributes. Furthermore, the possibility for improved time-series data, the WNN has proven to be effective in accurate flood modeling. Following are the future suggestions:

  • For future endeavors, it is highly suggested that a study on spatial flood forecasting utilizing ML algorithms be conducted.

  • To improve our power to manage and identify future weather condition changes, we will continue to build and maintain high-quality climate surveillance systems.

  • It is strongly recommended to conduct this research on spatial flood forecasting using ML algorithm.

  • The latest advances in ML techniques for spatial flood assessment have completely transformed this specific arena of flood forecasting, which need more exploration.

  • Research on establishing new models in various situations utilizing a mix of GIS and data mining techniques should proceed.

  • In order to effectively identify flood-prone locations, ML technologies are being integrated with physically based hydrological models.

  • Further sections in the ML area could focus on unsupervised machine learning methods reinforcement learning, and deep learning models.

  • In evaluating the chance of future river flood episodes, the DT and SVM ML methods provide adequate accuracy.

  • To improve the model resilience, more research into ensemble ML and deep learning combined with turbulence models is needed.

  • Future research should examine methods for estimating the period of reconstruction and rehabilitation following floods.

  • It may be able to forecast risk maps for subsequent events by taking into account local anthropogenic activities and the effects of climate change.

  • Utilizing soil maps, useful information that is critical in the development of flooding can be evaluated.

  • Additional research in developing new models in a variety of settings using a combination of Geospatial and data analysis approaches should continue.

  • Recent advancements in ML algorithms for temporal flood assessment have totally revolutionized this specific domain of flood prediction, which requires further investigation.


The careful review and constructive suggestions by the anonymous reviewers are gratefully acknowledged.

  1. Author contributions: Peiying Li: conceptualization, methodology, resources, project administration, and writing – reviewing and editing. Yanjie Zhao: conceptualization, data curation, investigation, validation, and writing – original draft. Muhammad Sufian: software, methodology, investigation, and writing – reviewing and editing. Ahmed Farouk Deifalla: resources, visualization, funding acquisition, writing – reviewing and editing, and supervision.

  2. Conflict of interest: The authors declare no conflict of interest.


[1] Danso-Amoako E, Scholz M, Kalimeris N, Yang Q, Shao J. Predicting dam failure risk for sustainable flood retention basins: A generic case study for the wider Greater Manchester area. Comput Environ Urban Syst. 2012;36(5):423–33.Search in Google Scholar

[2] Muzzammel R, Raza A. A support vector machine learning-based protection technique for MT-HVDC systems. Energies. 2020;13(24):6668.Search in Google Scholar

[3] Korup O, Clague JJ. Natural hazards, extreme events, and mountain topography. Quat Sci Rev. 2009;28(11–12):977–90.Search in Google Scholar

[4] Borah DK. Hydrologic procedures of storm event watershed models: A comprehensive review and comparison. Hydrol Processes. 2011;25(22):3472–89.Search in Google Scholar

[5] Fernández-Pato J, Caviedes-Voullième D, García-Navarro P. Rainfall/runoff simulation with 2D full shallow water equations: Sensitivity analysis and calibration of infiltration parameters. J Hydrol. 2016;536:496–513.Search in Google Scholar

[6] Liang X, Lettenmaier DP, Wood EF, Burges SJ. A simple hydrologically based model of land surface water and energy fluxes for general circulation models. J Geophys Research: Atmospheres. 1994;99(D7):14415–28.Search in Google Scholar

[7] Yue Z, Zhou W, Li T. Impact of the Indian Ocean dipole on evolution of the subsequent ENSO: Relative roles of dynamic and thermodynamic processes. J Clim. 2021;34(9):3591–607.Search in Google Scholar

[8] Adamowski J, Fung Chan H, Prasher SO, Ozga‐Zielinski B, Sliusarieva A. Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Water Resour Res. 2012;48(1):1–14.Search in Google Scholar

[9] Valipour M, Banihabib ME, Behbahani SMR. Parameters estimate of autoregressive moving average and autoregressive integrated moving average models and compare their ability for inflow forecasting. J Math Stat. 2012;8(3):330–8.Search in Google Scholar

[10] Aziz K, Rahman A, Fang G, Shrestha S. Application of artificial neural networks in regional flood frequency analysis: A case study for Australia. Stoch Environ Res risk Assess. 2014;28(3):541–54.Search in Google Scholar

[11] Haddad K, Rahman A. Regional flood frequency analysis in eastern Australia: Bayesian GLS regression-based methods within fixed region and ROI framework–Quantile Regression vs Parameter regression technique. J Hydrol. 2012;430:142–61.Search in Google Scholar

[12] Kroll CN, Vogel RM. Probability distribution of low streamflow series in the United States. J Hydrologic Eng. 2002;7(2):137–46.Search in Google Scholar

[13] Kerkhoven E, Gan TY. A modified ISBA surface scheme for modeling the hydrology of Athabasca River Basin with GCM-scale data. Adv water Resour. 2006;29(6):808–26.Search in Google Scholar

[14] Mosavi A, Rabczuk T, Varkonyi-Koczy AR, editors. Reviewing the novel machine learning tools for materials design. International Conference on Global Research and Education. Cham: Springer Nature; 2017.Search in Google Scholar

[15] Liu Y, Zhang K, Li Z, Liu Z, Wang J, Huang P. A hybrid runoff generation modelling framework based on spatial combination of three runoff generation schemes for semi-humid and semi-arid watersheds. J Hydrol. 2020;590:125440.Search in Google Scholar

[16] Wang G, Zhao B, Wu B, Wang M, Liu W, Zhou H, et al. Research on the macro-mesoscopic response mechanism of multisphere approximated heteromorphic tailing particles. Lithosphere. 2022;2022(Special 10):1–12.Search in Google Scholar

[17] Wang G, Zhao B, Wu B, Zhang C, Liu W. Intelligent prediction of slope stability based on visual exploratory data analysis of 77 in situ cases. Int J Min Sci Technol. 2022;33:47–59.Search in Google Scholar

[18] Dandagala S, Reddy MS, Murthy DS, Nagaraj G. Artificial Neural Networks Applications in Groundwater Hydrology-A Review . Artif Intell Syst Mach Learn. 2017;9(9):182–7.Search in Google Scholar

[19] Suykens JA, Vandewalle J. Least squares support vector machine classifiers. Neural Process Lett. 1999;9(3):293–300.Search in Google Scholar

[20] Gizaw MS, Gan TY. Regional flood frequency analysis using support vector regression under historical and future climate. J Hydrol. 2016;538:387–98.Search in Google Scholar

[21] Ebid AM, Deifalla A. Prediction of shear strength of FRP reinforced beams with and without stirrups using (GP) technique. Ain Shams Eng J. 2021;12(3):2493–510.Search in Google Scholar

[22] Abedini M, Ghasemian B, Shirzadi A, Shahabi H, Chapi K, Pham BT, et al. A novel hybrid approach of Bayesian logistic regression and its ensembles for landslide susceptibility assessment. Geocarto Int. 2019;34(13):1427–57.Search in Google Scholar

[23] Khosravi K, Shahabi H, Pham BT, Adamowski J, Shirzadi A, Pradhan B, et al. A comparative assessment of flood susceptibility modeling using multi-criteria decision-making analysis and machine learning methods. J Hydrol. 2019;573:311–23.Search in Google Scholar

[24] Zhu X, Xu Z, Liu Z, Liu M, Yin Z, Yin L, et al. Impact of dam construction on precipitation: A regional perspective. Mar Freshw Res. 2022. 10.1071/MF22135.Search in Google Scholar

[25] Wang Y-J, Huang J-K, Wang J-X. Household and community assets and farmers’ adaptation to extreme weather event: The case of drought in China. J Integr Agriculture. 2014;13(4):687–97.Search in Google Scholar

[26] Chen X-L, Liu C-G, Wang M-M, Zhou Q. Causes of unusual distribution of coseismic landslides triggered by the Mw 6.1 2014 Ludian, Yunnan, China earthquake. J Asian Earth Sci. 2018;159:17–23.Search in Google Scholar

[27] Shrestha MS, Takara K. Impacts of floods in South. Asia J South Asia Disaster Study. 2008;1(1):85–106.Search in Google Scholar

[28] Ding G, Li X, Li X, Zhang B, Jiang B, Li D, et al. A time-trend ecological study for identifying flood-sensitive infectious diseases in Guangxi, China from 2005 to 2012. Environ Res. 2019;176:108577.Search in Google Scholar

[29] Griffiths JA, Zhu F, Chan FKS, Higgitt DL. Modelling the impact of sea-level rise on urban flood probability in SE China. Geosci Front. 2019;10(2):363–72.Search in Google Scholar

[30] Xu Z, Li J. Short‐term inflow forecasting using an artificial neural network model. Hydrol Processes. 2002;16(12):2423–39.Search in Google Scholar

[31] Goswami BN, Venugopal V, Sengupta D, Madhusoodanan M, Xavier PK. Increasing trend of extreme rain events over India in a warming environment. Science. 2006;314(5804):1442–5.Search in Google Scholar

[32] Roxy MK, Ritika K, Terray P, Murtugudde R, Ashok K, Goswami B. Drying of Indian subcontinent by rapid Indian Ocean warming and a weakening land-sea thermal gradient. Nat Commun. 2015;6(1):1–10.Search in Google Scholar

[33] Gupta AK, Nair SS. Urban floods in Bangalore and Chennai: Risk management challenges and lessons for sustainable urban ecology. Curr Sci. 2011;1638–45.Search in Google Scholar

[34] Brichieri‐Colombi S, Bradnock RW. Geopolitics, water and development in South Asia: Cooperative development in the Ganges–Brahmaputra delta. Geographical J. 2003;169(1):43–64.Search in Google Scholar

[35] Huda MS, Ali SH. Environmental peacebuilding in South Asia: Establishing consensus on hydroelectric projects in the Ganges-Brahmaputra-Meghna (GBM) Basin. Geoforum. 2018;96:160–71.Search in Google Scholar

[36] Dhar O, Nandargi S. Hydrometeorological aspects of floods in India. Nat Hazards. 2003;28(1):1–33.Search in Google Scholar

[37] Choubin B, Hosseini FS, Rahmati O, Youshanloei MM. A step toward considering the return period in flood spatial modeling. Nat Hazards. 2023;115:431–60.Search in Google Scholar

[38] Azareh A, Rafiei Sardooi E, Choubin B, Barkhori S, Shahdadi A, Adamowski J, et al. Incorporating multi-criteria decision-making and fuzzy-value functions for flood susceptibility assessment. Geocarto Int. 2021;36(20):2345–65.Search in Google Scholar

[39] Hosseini FS, Sigaroodi SK, Salajegheh A, Moghaddamnia A, Choubin B. Towards a flood vulnerability assessment of watershed using integration of decision-making trial and evaluation laboratory, analytical network process, and fuzzy theories. Environ Sci Pollut Res. 2021;28(44):62487–98.Search in Google Scholar

[40] Taromideh F, Fazloula R, Choubin B, Emadi A, Berndtsson R. Urban Flood-Risk Assessment: Integration of Decision-Making and Machine Learning. Sustainability. 2022;14(8):4483.Search in Google Scholar

[41] Mosavi A, Golshan M, Janizadeh S, Choubin B, Melesse AM, Dineva AA. Ensemble models of GLM, FDA, MARS, and RF for flood and erosion susceptibility mapping: A priority assessment of sub-basins. Geocarto Int. 2022;37(9):2541–60.Search in Google Scholar

[42] Choubin B, Moradi E, Golshan M, Adamowski J, Sajedi-Hosseini F, Mosavi A. An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Sci Total Environ. 2019;651:2087–96.Search in Google Scholar

[43] Rafiei-Sardooi E, Azareh A, Choubin B, Mosavi AH, Clague JJ. Evaluating urban flood risk using hybrid method of TOPSIS and machine learning. Int J Disaster Risk Reduct. 2021;66:102614.Search in Google Scholar

[44] Dodangeh E, Choubin B, Eigdir AN, Nabipour N, Panahi M, Shamshirband S, et al. Integrated machine learning methods with resampling algorithms for flood susceptibility prediction. Sci Total Environ. 2020;705:135983.Search in Google Scholar

[45] Hosseini FS, Choubin B, Mosavi A, Nabipour N, Shamshirband S, Darabi H, et al. Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method. Sci Total Environ. 2020;711:135161.Search in Google Scholar

[46] Xiao X, Skitmore M, Li H, Xia B. Mapping knowledge in the economic areas of green building using scientometric analysis. Energies. 2019;12(15):3011.Search in Google Scholar

[47] Mryglod O, Holovatch Y, Kenna R, editors. Data mining in scientometrics: Usage analysis for academic publications. 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP). IEEE; 2018.Search in Google Scholar

[48] Darko A, Chan AP, Huo X, Owusu-Manu D-G. A scientometric analysis and visualization of global green building research. Build Environ. 2019;149:501–11.Search in Google Scholar

[49] Huang S, Wang H, Ahmad W, Ahmad A, Ivanovich Vatin N, Mohamed AM, et al. Plastic waste management strategies and their environmental aspects: A scientometric analysis and comprehensive review. Int J Environ Res Public Health. 2022;19(8):4556.Search in Google Scholar

[50] Aghaei Chadegani A, Salehi H, Yunus M, Farhadi H, Fooladi M, Farhadi M, et al. A comparison between two main academic literature collections: Web of science and Scopus databases. Asian Soc Sci. 2013;9(5):18–26.Search in Google Scholar

[51] Bergman EML. Finding citations to social work literature: The relative benefits of using Web of Science, Scopus, or Google Scholar. J academic Librariansh. 2012;38(6):370–9.Search in Google Scholar

[52] Saka AB, Chan DW. A scientometric review and metasynthesis of building information modelling (BIM) research in Africa. Buildings. 2019;9(4):85.Search in Google Scholar

[53] Markoulli MP, Lee CI, Byington E, Felps WA. Mapping human resource management: Reviewing the field and charting future directions. Hum Resour Manag Rev. 2017;27(3):367–96.Search in Google Scholar

[54] Huang H, Chen X, Zhu Z, Xie Y, Liu L, Wang X, et al. The changing pattern of urban flooding in Guangzhou, China. Sci Total Environ. 2018;622:394–401.Search in Google Scholar

[55] Sun P, Wen Q, Zhang Q, Singh VP, Sun Y, Li J. Nonstationarity-based evaluation of flood frequency and flood risk in the Huai River basin, China. J Hydrol. 2018;567:393–404.Search in Google Scholar

[56] Wang Y-J, Gao C, Zhai J-Q, Li X-C, Hartmann H. Spatio-temporal changes of exposure and vulnerability to floods in China. Adv Clim Change Res. 2014;5(4):197–205.Search in Google Scholar

[57] Zhang Y, Wang Y, Chen Y, Liang F, Liu H. Assessment of future flash flood inundations in coastal regions under climate change scenarios—A case study of Hadahe River basin in northeastern China. Sci Total Environ. 2019;693:133550.Search in Google Scholar

[58] Zhang Y, Zhao Y, Liu B, Wang Z, Zhang S. Rill and gully erosion on unpaved roads under heavy rainfall in agricultural watersheds on China’s Loess Plateau. Agric Ecosyst Environ. 2019;284:106580.Search in Google Scholar

[59] Xiao-jun W, Jian-yun Z, Shahid S, ElMahdi A, Rui-min H, Zhen-xin B, et al. Water resources management strategy for adaptation to droughts in China. Mitig Adapt Strateg Glob change. 2012;17(8):923–37.Search in Google Scholar

[60] Zhang J, Zhou C, Xu K, Watanabe M. Flood disaster monitoring and evaluation in China. Glob Environ Change Part B: Environ Hazards. 2002;4(2):33–43.Search in Google Scholar

[61] Wan GH. Peasant flood in China: Internal migration and its policy determinants. Third World Q. 1995;16(2):173–96.Search in Google Scholar

[62] Yin J, Ye M, Yin Z, Xu S. A review of advances in urban flood risk analysis over China. Stoch Environ Res Risk Assess. 2015;29(3):1063–70.Search in Google Scholar

[63] Alderman K, Turner LR, Tong S. Floods and human health: A systematic review. Environ Int. 2012;47:37–47.Search in Google Scholar

[64] Kai W, Deyi C, Zhaohui Y. Flood control and management for the transitional Huaihe River in China. Procedia Eng. 2016;154:703–9.Search in Google Scholar

[65] Wu H-L, Cheng W-C, Shen S-L, Lin M-Y, Arulrajah A. Variation of hydro-environment during past four decades with underground sponge city planning to control flash floods in Wuhan, China: An overview. Undergr Space. 2020;5(2):184–98.Search in Google Scholar

[66] Lyu H-M, Xu Y-S, Cheng W-C, Arulrajah A. Flooding hazards across southern China and prospective sustainability measures. Sustainability. 2018;10(5):1682.Search in Google Scholar

[67] Sen Roy S, Balling Jr RC. Trends in extreme daily precipitation indices in India. Int J Climatology: A J R Meteorological Soc. 2004;24(4):457–66.Search in Google Scholar

[68] Rakhecha P, Soman M. Trends in the annual extreme rainfall events of 1 to 3 days duration over India. Theor Appl Climatol. 1994;48(4):227–37.Search in Google Scholar

[69] Ramaswami C. Meteorological aspects of severe floods in India 1923–1979. Meteoroll Monograph; 1987.Search in Google Scholar

[70] Dhar O, Nandargi S. The zones of severe rainstorm activity over India. Int J Climatol. 1993;13(3):301–11.Search in Google Scholar

[71] Jenamani RK, Bhan S, Kalsi S. Observational/forecasting aspects of the meteorological event that caused a record highest rainfall in Mumbai. Curr Sci. 2006;90(10):1344–62.Search in Google Scholar

[72] Shyamala B, Bhadram C. Impact of mesoscale–synoptic scale interactions on the Mumbai historical rain event during 26–27 July 2005. Curr Sci. 2006;91(12):1649–54.Search in Google Scholar

[73] Mooley D. The role of western disturbances in the production of weather over India during different seasons. Indian J Meteor Geophys. 1957;8:253–60.Search in Google Scholar

[74] Sikka DR. Synoptic and meso-scale weather disturbances over South Asia during the Southwest Summer monsoon season. The global monsoon system: Research and Forecast. Singapore: World Scientific; 2011. p. 183–204.Search in Google Scholar

[75] Houze R, Rasmussen K, Medina S, Brodzik S, Romatschke U. Anomalous atmospheric events leading to the summer 2010 floods in Pakistan. Bull Am Meteorological Soc. 2011;92(3):291–8.Search in Google Scholar

[76] Ghosh S, Veeraraghavan K. Severe floods in Jammu & Kashmir in August. Mausam. 1975;26(2):203–7.Search in Google Scholar

[77] Rajeevan M, Unnikrishnan C, Bhate J, Niranjan Kumar K, Sreekala P. Northeast monsoon over India: Variability and prediction. Meteorol Appl. 2012;19(2):226–36.Search in Google Scholar

[78] Karmegam D, Mappillairaju B. Spatio-temporal distribution of negative emotions on Twitter during floods in Chennai, India, in 2015: A post hoc analysis. Int J health geographics. 2020;19:1–13.Search in Google Scholar

[79] Bhuvana N, Aram IA. Facebook and Whatsapp as disaster management tools during the Chennai (India) floods of 2015. Int J disaster risk Reduct. 2019;39:101135.Search in Google Scholar

[80] Alam A, Bhat MS, Farooq H, Ahmad B, Ahmad S, Sheikh AH. Flood risk assessment of Srinagar city in Jammu and Kashmir, India. Int J Disaster Resil Built Environ. 2018;9(2):114–29.Search in Google Scholar

[81] Saha A, Pal SC, Arabameri A, Blaschke T, Panahi S, Chowdhuri I, et al. Flood susceptibility assessment using novel ensemble of hyperpipes and support vector regression algorithms. Water. 2021;13(2):241.Search in Google Scholar

[82] Gautam D. Assessment of social vulnerability to natural hazards in Nepal. Nat Hazards Earth Syst Sci. 2017;17(12):2313–20.Search in Google Scholar

[83] Sherpa SF, Shrestha M, Eakin H, Boone CG. Cryospheric hazards and risk perceptions in the Sagarmatha (Mt. Everest) national park and buffer zone, Nepal. Nat Hazards. 2019;96(2):607–26.Search in Google Scholar

[84] Watanabe T, Byers AC, Somos-Valenzuela MA, McKinney DC. The need for community involvement in glacial lake field research: The case of Imja glacial lake, Khumbu, Nepal Himalaya. Climate change, glacier response, and vegetation dynamics in the Himalaya. Cham: Springer; 2016. p. 235–50.Search in Google Scholar

[85] Watanabe T. Geoecological studies in the Kangchenjunga conservation area, eastern Nepal Himalaya. Glob Environ Research-English Ed. 2006;10(1):87.Search in Google Scholar

[86] Ishikawa M, Watanabe T, Nakamura N. Genetic differences of rock glaciers and the discontinuous mountain permafrost zone in Kanchanjunga Himal, Eastern Nepal. Permafr Periglac Process. 2001;12(3):243–53.Search in Google Scholar

[87] Byers AC, Chand MB, Lala J, Shrestha M, Byers EA, Watanabe T. Reconstructing the history of glacial lake outburst floods (GLOF) in the Kanchenjunga conservation area, East Nepal: An interdisciplinary approach. Sustainability. 2020;12(13):5407.Search in Google Scholar

[88] Byers AC. An assessment of contemporary glacier fluctuations in Nepal’s Khumbu Himal using repeat photography. Himal J Sci. 2007;4(6):21–6.Search in Google Scholar

[89] Chand MB, Watanabe T. Development of supraglacial ponds in the Everest Region, Nepal, between 1989 and 2018. Remote Sens. 2019;11(9):1058.Search in Google Scholar

[90] Shah SMH, Mustaffa Z, Teo FY, Imam MAH, Yusof KW, Al-Qadami EHH. A review of the flood hazard and risk management in the South Asian Region, particularly Pakistan. Sci Afr. 2020;10:e00651.Search in Google Scholar

[91] Looney R. Economic impacts of the floods in Pakistan. Contemp South Asia. 2012;20(2):225–41.Search in Google Scholar

[92] Aslam N, Kamal A. Stress, anxiety, depression, and posttraumatic stress disorder among general population affected by floods in Pakistan. Pak J Med Res. 2016;55(1):29.Search in Google Scholar

[93] Iqbal A, Hassan SA. ENSO and IOD analysis on the occurrence of floods in Pakistan. Nat Hazards. 2018;91(3):879–90.Search in Google Scholar

[94] Laghari ZA, Soomro AM, Tunio SA, Lashari K, Baloach FG, Baig NM, et al. Malnutrition among children under five years in district Sanghar, Sindh, Pakistan. Gomal J Med Sci. 2015;13(1):1–4.Search in Google Scholar

[95] Talpur Z, Naseer T, Memon AR, Zaidi A. Impact of floods on vegetation cover in the Sanghar District of Sindh, Pakistan. Environ Sci Proc. 2020;7(1):5.Search in Google Scholar

[96] Kabir MH, Hossen MN. Impacts of flood and its possible solution in Bangladesh. Disaster Adv. 2019;12(10):48–57.Search in Google Scholar

[97] Wahiduzzaman M. Major floods and tropical cyclones over Bangladesh: Clustering from ENSO timescales. Atmosphere. 2021;12(6):692.Search in Google Scholar

[98] Haque CE, Azad MA, Choudhury MU. Discourse of flood management approaches and policies in Bangladesh: Mapping the changes, drivers, and actors. Water. 2019;11(12):2654.Search in Google Scholar

[99] Ahmed B, Kelman I, Fehr HK, Saha M. Community resilience to cyclone disasters in coastal Bangladesh. Sustainability. 2016;8(8):805.Search in Google Scholar

[100] De Alwis D, Noy I. The cost of being under the weather: Droughts, floods, and health-care costs in Sri Lanka. Asian Dev Rev. 2019;36(2):185–214.Search in Google Scholar

[101] Siriwardana CS, Jayasiri G, Hettiarachchi S. Investigation of efficiency and effectiveness of the existing disaster management frameworks in Sri Lanka. Procedia Eng. 2018;212:1091–8.Search in Google Scholar

[102] Zubair L, Ralapanawe V, Tennakoon U, Yahiya Z, Perera R. Natural disaster risks in Sri Lanka: Mapping hazards and risk hotspots. Natural disaster hotspots case studies. United Kingdom: World Bank; 2006. p. 109.Search in Google Scholar

[103] Moufar MMM, Perera EDP. Floods and countermeasures impact assessment for the metro colombo canal system, Sri Lanka. Hydrology. 2018;5(1):11.Search in Google Scholar

[104] De’ath G, Fabricius KE. Classification and regression trees: A powerful yet simple technique for ecological data analysis. Ecology. 2000;81(11):3178–92.Search in Google Scholar

[105] Parvez I, Shen J, Hassan I, Zhang N. Generation of hydro energy by using data mining algorithm for cascaded hydropower plant. Energies. 2021;14(2):298.Search in Google Scholar

[106] Choubin B, Zehtabian G, Azareh A, Rafiei-Sardooi E, Sajedi-Hosseini F, Kişi Ö. Precipitation forecasting using classification and regression trees (CART) model: A comparative study of different approaches. Environ earth Sci. 2018;77(8):1–13.Search in Google Scholar

[107] Choubin B, Darabi H, Rahmati O, Sajedi-Hosseini F, Kløve B. River suspended sediment modelling using the CART model: A comparative study of machine learning techniques. Sci Total Environ. 2018;615:272–81.Search in Google Scholar

[108] Wang X, Gao Y, Lin J, Rangwala H, Mittu R, editors. A machine learning approach to false alarm detection for critical arrhythmia alarms. 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA). IEEE; 2015.Search in Google Scholar

[109] Yu P-S, Yang T-C, Chen S-Y, Kuo C-M, Tseng H-W. Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting. J Hydrol. 2017;552:92–104.Search in Google Scholar

[110] Tehrany MS, Pradhan B, Jebur MN. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. J Hydrol. 2014;512:332–43.Search in Google Scholar

[111] Bui DT, Tuan TA, Klempe H, Pradhan B, Revhaug I. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides. 2016;13(2):361–78.Search in Google Scholar

[112] Etemad-Shahidi A, Mahjoobi J. Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Eng. 2009;36(15–16):1175–81.Search in Google Scholar

[113] Olivier J, Aldrich C. Use of decision trees for the development of decision support systems for the control of grinding circuits. Minerals. 2021;11(6):595.Search in Google Scholar

[114] Khan MA, Aslam F, Javed MF, Alabduljabbar H, Deifalla AF. New prediction models for the compressive strength and dry-thermal conductivity of bio-composites using novel machine learning algorithms. J Clean Prod. 2022;350:131364.Search in Google Scholar

[115] Carcano EC, Bartolini P, Muselli M, Piroddi L. Jordan recurrent neural network versus IHACRES in modelling daily streamflows. J Hydrol. 2008;362(3–4):291–307.Search in Google Scholar

[116] Wu C, Chau K-W. Data-driven models for monthly streamflow time series prediction. Eng Appl Artif Intell. 2010;23(8):1350–67.Search in Google Scholar

[117] Sulaiman J, Wahab SH. Heavy rainfall forecasting model using artificial neural network for flood prone area. IT convergence and security 2017. Singapore: Springer; 2018. p. 68–76.Search in Google Scholar

[118] Deo RC, Şahin M. Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydrometeorological parameters and climate indices in eastern Australia. Atmos Res. 2015;161:65–81.Search in Google Scholar

[119] Jimeno-Sáez P, Senent-Aparicio J, Pérez-Sánchez J, Pulido-Velazquez D, Cecilia JM. Estimation of instantaneous peak flow using machine-learning models and empirical formula in peninsular Spain. Water. 2017;9(5):347.Search in Google Scholar

[120] Elsafi SH. Artificial neural networks (ANNs) for flood forecasting at Dongola station in the River Nile. Sudan Alex Eng J. 2014;53(3):655–62.Search in Google Scholar

[121] Song Y, Wang J. Optimization of relief well design using artificial neural network during geological CO2 storage in pohang basin, South Korea. Appl Sci. 2021;11(15):6996.Search in Google Scholar

[122] Wu L-Y, Weng S-S. Ensemble Learning Models for Food Safety Risk Prediction. Sustainability. 2021;13(21):12291.Search in Google Scholar

[123] Sajedi-Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, et al. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Sci Total Environ. 2018;644:954–62.Search in Google Scholar

[124] Ouyang Q, Lu W, Xin X, Zhang Y, Cheng W, Yu T. Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction. Water Resour Manage. 2016;30(7):2311–25.Search in Google Scholar

[125] Wang W-C, Chau K-W, Xu D-M, Chen X-Y. Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition. Water Resour Manage. 2015;29(8):2655–75.Search in Google Scholar

[126] Li S, Ma K, Jin Z, Zhu Y, editors. A new flood forecasting model based on SVM and boosting learning algorithms. 2016 IEEE Congress on evolutionary computation (CEC). IEEE; 2016.Search in Google Scholar

[127] Sachindra D, Huang F, Barton A, Perera B. Least square support vector and multi‐linear regression for statistically downscaling general circulation model outputs to catchment streamflows. Int J Climatol. 2013;33(5):1087–106.Search in Google Scholar

[128] Jajarmizadeh M, Lafdani EK, Harun S, Ahmadi A. Application of SVM and SWAT models for monthly streamflow prediction, a case study in South of Iran. KSCE J Civ Eng. 2015;19(1):345–57.Search in Google Scholar

[129] Bao Y, Xiong T, Hu Z. Multi-step-ahead time series prediction using multiple-output support vector regression. Neurocomputing. 2014;129:482–93.Search in Google Scholar

[130] Bray M, Han D. Identification of support vector machines for runoff modelling. J Hydroinformatics. 2004;6(4):265–80.Search in Google Scholar

[131] Moore KJ, Kurt M, Eriten M, McFarland DM, Bergman LA, Vakakis AF. Wavelet-bounded empirical mode decomposition for measured time series analysis. Mech Syst Signal Process. 2018;99:14–29.Search in Google Scholar

[132] Shoaib M, Shamseldin AY, Melville BW. Comparative study of different wavelet based neural network models for rainfall–runoff modeling. J Hydrol. 2014;515:47–58.Search in Google Scholar

[133] Dubossarsky E, Friedman JH, Ormerod JT, Wand MP. Wavelet-based gradient boosting. Stat Comput. 2016;26(1–2):93–105.Search in Google Scholar

[134] Partal T. Wavelet regression and wavelet neural network models for forecasting monthly streamflow. J Water Clim Change. 2017;8(1):48–61.Search in Google Scholar

[135] Kumar S, Tiwari MK, Chatterjee C, Mishra A. Reservoir inflow forecasting using ensemble models based on neural networks, wavelet analysis and bootstrap method. Water Resour Manage. 2015;29(13):4863–83.Search in Google Scholar

[136] Seo Y, Kim S, Kisi O, Singh VP. Daily water level forecasting using wavelet decomposition and artificial intelligence techniques. J Hydrol. 2015;520:224–43.Search in Google Scholar

[137] Sudhishri S, Kumar A, Singh J. Comparative evaluation of neural network and regression based models to simulate runoff and sediment yield in an outer Himalayan watershed. J Agric Sci Technol. 2016;18(3):681–94.Search in Google Scholar

[138] Malekpour Heydari S, Aris TNM, Yaakob R, Hamdan H. Data-Driven Forecasting and Modeling of Runoff Flow to Reduce Flood Risk Using a Novel Hybrid Wavelet-Neural Network Based on Feature Extraction. Sustainability. 2021;13(20):11537.Search in Google Scholar

[139] Munawar HS, Hammad AW, Waller ST. A review on flood management technologies related to image processing and machine learning. Autom Constr. 2021;132:103916.Search in Google Scholar

[140] Ahmad M, Al Mehedi MA, Yazdan MMS, Kumar R. Development of Machine Learning Flood Model Using Artificial Neural Network (ANN) at Var River. Liquids. 2022;2(3):147–60.Search in Google Scholar

[141] Al Rifat SA, Liu W. Predicting future urban growth scenarios and potential urban flood exposure using Artificial Neural Network-Markov Chain model in Miami Metropolitan Area. Land Use Policy. 2022;114:105994.Search in Google Scholar

[142] Rivas Casado M, Irvine T, Johnson S, Palma M, Leinster P. The use of unmanned aerial vehicles to estimate direct tangible losses to residential properties from flood events: A case study of cockermouth following the desmond storm. Remote Sens. 2018;10(10):1548.Search in Google Scholar

[143] Dahri N, Yousfi R, Bouamrane A, Abida H, Pham QB, Derdous O. Comparison of analytic network process and artificial neural network models for flash flood susceptibility assessment. J Afr Earth Sci. 2022;193:104576.Search in Google Scholar

[144] Lohani AK, Goel NK, Bhatia K. Improving real time flood forecasting using fuzzy inference system. J Hydrol. 2014;509:25–41.Search in Google Scholar

[145] Lohani A, Kumar R, Singh R. Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. J Hydrol. 2012;442:23–35.Search in Google Scholar

[146] Liu C, Li Y. GIS-based dynamic modelling and analysis of flash floods considering land-use planning. Int J Geographical Inf Sci. 2017;31(3):481–98.Search in Google Scholar

Received: 2022-10-26
Revised: 2023-02-23
Accepted: 2023-03-18
Published Online: 2023-05-24

© 2023 the author(s), published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Downloaded on 8.6.2023 from
Scroll to top button