Multi-hazards (landslides, floods, and gully erosion) modeling and mapping using machine learning algorithms

Abstract

The current study aimed at producing a multi-hazard susceptibility map for the Hasher-Fayfa Basin. The basin is part of the Jazan region in southwestern Saudi Arabia and is characterized by mountainous terrain. Recently, this area has experienced many extreme natural processes, which become natural hazard events when they intersect with human activities (urban areas and infrastructures). In this work, the probabilities of the three main hazards; landslides, floods, and gully erosion are mapped using machine learning algorithms such as boosted regression tree (BRT), generalized linear model (GLM), Flexible discriminant analysis (FDA), random forest (RF), and multivariate discriminant analysis (MDA). Several factors from various sources, including, topographic, geologic, meteorological, hydrologic, and human activities, were incorporated to produce the final multi-hazard susceptibility model. The area under the curve (AUC) was used to determine the best predictive model for each type of natural hazard. AUC values between 80 and 90% indicated that the model was very good, and values above 90% indicated that the model had excellent predictive capability. Based on the accuracy evaluation, the FDA model was found to be the most accurate landslides prediction with an AUC value of (92.7%, excellent performance). The RF model was found to be the most accurate in predicting floods and erosion with AUC values of (97.2% - excellent and 83.3% - very good performance, respectively). Finally, a map of multi-hazard susceptibility was created by coupling of the mentioned three hazards. The results showed that 33.5% of the total area is safe (no-hazard), while 66.5% is characterized by at least a single hazard and a combination of two or three hazards. Machine learning approaches are useful tools as a basis for management and mitigation processes, based on multi-hazard modeling.