A Novel Estimation of the Composite Hazard of Landslides and Flash Floods Utilizing an Artificial Intelligence Approach

Abstract

Landslides and flash floods are significant natural hazards with substantial risks to human settlements and the environment, and understanding their interconnection is vital. This research investigates the hazards of landslides and floods in two adopted basins in the Yamaguchi and Shimane prefectures, Japan. This study utilized ten environmental variables alongside categories representing landslide-prone, non-landslide, flooded, and non-flooded areas. Employing a machine-learning approach, namely, a LASSO regression model, we generated Landslide Hazard Maps (LHM), Flood Hazard Maps (FHM), and a Composite Hazard Map (CHM). The LHM identified flood-prone low-lying areas in the northwest and southeast, while central and northwest regions exhibited higher landslide susceptibility. Both LHM and FHM were classified into five hazard levels. Landslide hazards predominantly covered high- to moderate-risk areas, since the high-risk areas constituted 38.8% of the study region. Conversely, flood hazards were mostly low to moderate, with high- and very high-risk areas at 10.49% of the entire study area. The integration of LHM and FHM into CHM emphasized high-risk regions, underscoring the importance of tailored mitigation strategies. The accuracy of the model was assessed by employing the Receiver Operating Characteristic (ROC) curve method, and the Area Under the Curve (AUC) values were determined. The LHM and FHM exhibited an exceptional AUC of 99.36% and 99.06%, respectively, signifying the robust efficacy of the model. The novelty in this study is the generation of an integrated representation of both landslide and flood hazards. Finally, the produced hazard maps are essential for policymaking to address vulnerabilities to landslides and floods.

Integrating Geographic Information Systems and Hydrometric Analysis for Assessing and Mitigating Building Vulnerability to Flash Flood Risks

“…The runoff propagation and runoff velocity were spatially mapped for a time step of 6 hr, as shown in Figure 11a-f. After about 18 hr from the outset of the storm, the flow inundated most of the study area. It is logically observed that when comparing the region's elevation map with the estimated floodplain map, the concentration of the flow is anticipated to accrue in the lower-lying region where the likelihood of flood hazard is projected to be considerably elevated, as deduced by previous studies [29,45]. The region has an area of about 35 hectares containing 938 buildings.…”

Development of the SiAlong Platform to Improve Digital Literacy on Landslide Disasters among Generation Z in Semarang City

“…Many of these studies leverage GIS technology or other mapping platforms. Various previous research efforts have concentrated on the use of GIS and remote sensing technologies combined with other innovative technologies for assessing and predicting landslide disasters [68][69][70][71][72][73] and designing early warning systems for landslide disasters [74][75][76].…”

“…Artificial intelligence has also been widely used in sensing and assessment processes, as demonstrated in studies by Karantanellis et al [77], Selamat et al [78], and Sun et al [79], and Wahba et al [72]. Additional research by Pennington et al [80] and Ofli et al [81] has developed tools for reporting landslide incidents globally and in near real-time using social media and artificial intelligence.…”