•Flood susceptibility modeling was done using hybrid machine learning approaches.•OneR method was used for feature selection.•Models performance was evaluated using standard statistical measures ...including AUC-ROC.•Developed models achieved a high flood susceptibility prediction accuracy.•RSSPART was the best machine learning model.
Recently, floods are occurring more frequently every year around the world due to increased anthropogenic activities and climate change. There is a need to develop accurate models for flood susceptibility prediction and mapping, which can be helpful in developing more efficient flood management plans. In this study, the Partial Decision Tree (PART) classifier and the AdaBoost, Bagging, Dagging, and Random Subspace ensembles learning techniques were combined to develop novel GIS-based ensemble computational models (ABPART, BPART, DPART and RSSPART) for flood susceptibility mapping in the Quang Binh Province, Vietnam. In total, 351 flood locations were used in the model study. This data was divided into a 70:30 ratio for model training (70% ≅ 255 locations) and (30% ≅ 96 locations) for model validation. Ten flood influencing factors, namely elevation, slope, curvature, flow direction, flow accumulation, river density, distance from river, rainfall, land-use, and geology, were used for the development of models. The OneR feature selection method was used to select and prioritize important factors for the spatial modeling. The results revealed that land-use, geology, and slope are the most important conditioning factors in the occurrence of floods in the study area. Standard statistical methods, including the ROC curve (AUC), were used for the performance evaluation of models. Results indicated that the performance of all models was good (AUC > 0.9) and RSSPART (AUC = 0.959) outperformed the others. Thus, the RSSPART model can be used for accurately predicting and mapping flood susceptibility.
In this study, a new approach of machine learning (ML) models integrated with the analytic hierarchy process (AHP) method was proposed to develop a holistic flood risk assessment map. Flood ...susceptibility maps were created using ML techniques. AHP was utilized to combine flood vulnerability and exposure criteria. We selected Quang Binh province of Vietnam as a case study and collected available data, including 696 flooding locations of historical flooding events in 2007, 2010, 2016, and 2020; and flood influencing factors of elevation, slope, curvature, flow direction, flow accumulation, distance from river, river density, land cover, geology, and rainfall. These data were used to construct training and testing datasets. The susceptibility models were validated and compared using statistical techniques. An integrated flood risk assessment framework was proposed to incorporate flood hazard (flood susceptibility), flood exposure (distance from river, land use, population density, and rainfall), and flood vulnerability (poverty rate, number of freshwater stations, road density, number of schools, and healthcare facilities). Model validation suggested that deep learning has the best performance of AUC = 0.984 compared with other ensemble models of MultiBoostAB Ensemble (0.958), Random SubSpace Ensemble (0.962), and credal decision tree (AUC = 0.918). The final flood risk map shows 5075 ha (0.63%) in extremely high risk, 47,955 ha (5.95%) in high‐risk, 40,460 ha (5.02%) in medium risk, 431,908 ha (53.55%) in low risk areas, and 281,127 ha (34.86%) in very low risk. The present study highlights that the integration of ML models and AHP is a promising framework for mapping flood risks in flood‐prone areas.
Purpose
In October 2020, Vietnam was repeatedly hit by large storms, including Linfa, Nangka, Saudel and Molave, causing heavy rains and whirlwinds in the Central provinces of Vietnam. The heavy rain ...led to severe flooding in many localities. The water levels on major rivers broke records of historical flood events in 1950, 1979, 1999, 2007, 2010 and 2016. In response, this paper aims to quantify the impacts of 2020 flooding to support flood risk management activities and the relief agencies that can use the analysis.
Design/methodology/approach
This study demonstrates an approach to quickly map flood impacts on population, schools, health-care facilities, agriculture, transportation and business facilities and assess flood risks using available data and spatial analysis techniques.
Findings
The results show that all districts of Quang Binh were affected by the event, in which 1,014 residential areas, 70 schools, 13 health-care facilities, 32,558 ha of agriculture lands, 402 km road length, 29 km railway, 35 bridges on roads and 239 business facilities were exposed within flooded areas.
Research limitations/implications
This study is limited to direct or tangible impacts, including flooded residential areas, schools, health-care facilities, agriculture land categories, road networks and business facilities. Indirect or intangible impacts such as health, flood pollution and business disruption should be considered in further studies.
Practical implications
These detailed impact maps can support decision-makers and local authorities in implementing recovery activities, allocating relief and devoting human resources and developing flood risk management action plans and land-use planning in the future.
Social implications
This study investigates the context of flood impacts on population, schools, health-care facilities, agriculture, transportation and business facilities. Based on this research, decision-makers can better understand how to support affected communities and target the most at risk people with interventions.
Originality/value
This paper presents a framework to quantify the impacts of the 2020 extreme flood event using available data and spatial analysis techniques in support of flood risk management activities.
Vietnam’s central coastal region is the most vulnerable and always at flood risk, severely affecting people’s livelihoods and socio-economic development. In particular, Quang Binh province is often ...affected by floods and storms over the year. However, it still lacks studies on flood hazard estimation and prediction tools in this area. This study aims to develop a flooding susceptibility assessment tool using various machine learning (ML) techniques namely alternating decision tree (AD Tree), logistic model tree (LM Tree), reduced-error pruning tree (REP Tree), J48 decision tree (J48) and Naïve Bayes tree (NB Tree); historical flood marks; and available data of topography, hydrology, geology, and environment considering Quang Binh province as a study area. We used flood mark locations of major flooding events in the years 2007, 2010, and 2016; and ten flood conditioning factors to construct and validate the ML models. Various validation methods, including area under the ROC curve (AUC), were used to validate and compare the models. The result of the models’ validation suggests that all models have good performance: AD Tree (AUC = 0.968), LM Tree (AUC = 0.967), REP Tree (AUC = 0.897), J48 (AUC = 0.953), and NB Tree (AUC = 0.986). Out of these, NB Tree managed to achieve the best performance in terms of flood prediction with an accuracy higher than 92 %. The final flood susceptibility map highlights 6,265 km
2
(78.8 % area) with a very low flooding hazard, 391 km
2
(4.9 % area) with a low flooding hazard, 224 km
2
(2.8 % area) with a moderate flooding hazard, 243 km
2
(3.1 %) with a high flooding hazard, and 829 km
2
(10.4 % area) with very high flooding hazard. The final flooding susceptibility assessment map could add a valuable source for flood risk reduction and management activities of Quang Binh province.
Flash floods and landslides are dangerous natural hazards in hilly areas. They often occur extensively and potentially cause widespread destruction to agriculture, infrastructure, roads, houses, and ...human beings. This research aimed to analyze the hazard susceptibility on a mountainous roadway using advanced Machine Learning (ML) models. We conducted field surveys to collect data on flash flood and landslide locations in 2017, 2018, and 2019 on a particular roadway in Vietnam, National Highway 6, consisting of 88 flash flood sites and 235 landslide sites. The state-of-art ML models were utilized for the predictive modeling, including AdaBoost-RBF, Bagging-RBF, MultiBoostAB-RBF, and Random Sub-spaceRBF, with Radial Basis Function (RBF) serving as the primary classifier. The AdaBoost-RBF model outperformed all others in predicting landslide and flash flood vulnerability. The resulting map showed that 44.89% or 14,183 ha is in very high susceptibility zones, 15.55% or 4914 ha is in high susceptibility zones, 10.37% or 3.275 ha is in moderate susceptibility zones, 13.69% or 4324 ha is in low susceptibility zones, and 15.50% or 4899 ha is in very low susceptibility zones. A detailed map of the areas where landslides and flash floods are most likely to occur on the roadway might provide local authorities with crucial information for disaster management.
Display omitted
•Modeling landslide and flash flood susceptibility for a mountainous roadway.•Advanced machine learning algorithms were developed for susceptibility modeling.•Hazard assessment maps may aid disaster risk mitigation and management.
Flood damage is often severe and directly affects housing, transport infrastructure, industrial, service, commercial, and land use. A flood risk assessment based on vulnerability indicators can ...provide valuable information to support decision-making and operational strategies to reduce disaster damage. The main objective of this study is to propose a framework for assessing flood risk based on flood hazard factor and its relationship with flood vulnerability indicators. We applied an integrated machine learning (ML) and analytic hierarchy process (AHP) framework for a case study of Quang Binh province, Vietnam. Several state-of-the-art ML models of AdaBoost, logistic regression, and AdaBoost-Logistic were applied to build a flood hazard map. AHP was employed to integrate vulnerability criteria for the assessment. We used 671 flooding locations of historical flooding events in 2007, 2010, 2016, and 2020 in Quang Binh province; and 14 flood conditioning factors relating to geo-environment to generate and verify the flood susceptibility models. Statistical indexes were applied to verify the used models. The validated result showed that the AdaBoost-Logistic ensemble model has the best performance of AUC = 0.996. The flood hazard map was combined with flood vulnerability maps to generate a valuable flood risk assessment map for Quang Binh province. The result of this study shows that 330,579 ha (40.99%) is in very low-risk zones, 349,511 ha (43.33%) in low-risk zones, 50,628 ha (6.28%) in medium risk zones, 48,688 ha (6.04%) in high-risk zones, and 27,121 ha (3.36%) in extremely high-risk zones. This proposed methodology and flood risk map result can be beneficial for selecting priority measures for flood risk reduction and management.
Flash flood is one of the most common natural hazards affecting many mountainous areas. Previous studies explored flash flood susceptibility models; however, there is still a lack of case studies in ...the transport sector. This paper aimed to develop advanced hybrid machine learning (ML) algorithms for flash flood susceptibility modeling and mapping using data from the road network National Highway 6 in Hoa Binh province, Vietnam. A single ML model of reduced error pruning trees (REPT) and four hybrid ML models of Decorate-REPT, AdaBoostM1-REPT, Bagging-REPT, and MultiBoostAB-REPT were applied to develop flash flood susceptibility maps. Field surveys were conducted about the flash flood locations on the 115-km route length of the National Highway 6 in 2017, 2018, and 2019 flood events. This study used 88 flash flood locations and 14 flood conditioning factors to construct and validate the proposed models. Statistical metrics, including sensitivity, specificity, accuracy, root mean square error, and area under the receiver operating characteristic curve, were applied to evaluate the models’ performance and accuracy. The DCREPT model showed the best performance (AUC = 0.988) among the training models and had the highest prediction accuracy (AUC = 0.991) among the testing models. We found that 12,572 ha (Decorate-REPT), 9564 ha (AdaBoostM1-REPT), 11,954 ha (Bagging-REPT), 14,432 ha (MultiBoostAB-REPT), and 17,660 ha (REPT) of the 3-km buffer area of the highway are in the high- and very high-flash-flood-susceptibility areas. The proposed methodology could be potentially generalized to other transportation routes in mountainous areas to generate flash flood susceptibility prediction maps.
Landslide is a severe geohazard in many mountainous areas of Vietnam during the rainy season. They directly threaten human lives and properties every year. Landslide susceptibility maps are useful ...tools for risk mitigation, land-use planning, and early warning systems for local areas. It is necessary to update these maps continuously because of the complexity of landslide events. This fact requires further extending the approach techniques with practical implications. Therefore, this study aimed to develop landslide susceptibility prediction maps based on advanced machine learning (ML) techniques. Five state-of-the-art hybrid ML models were developed: bagging MLP, dagging MLP, decorate MLP, rotation forest MLP, and random subspace MLP with multilayer perceptron (MLP) as a base classifier. Sixteen causative factors were collected to build landslide susceptibility maps based on the relationship between historical landslide locations and specific local geo-environmental conditions. The model performance was verified using various statistical indexes. Based on the area under ROC curve (AUC) analysis results of the testing dataset, the rotation forest MLP model has the greatest predictive accuracy of AUC = 0.818. It is followed by the decorate MLP and bagging MLP (AUC = 0.804), the random subspace MLP model (AUC = 0.796), the dagging MLP (AUC = 0.789), and the single MLP (AUC = 0.698). The results of this study can be applied effectively to other mountainous regions to mitigate the risk of landslides.
PDF