Landslide susceptibility assessment using the certainty factor and deep neural network

Abstract

Areas with vulnerable ecological environments often breed many geological disasters, especially landslides, which pose a severe threat to the safety of people’s lives and property in these areas. To aid in landslide prevention and mitigation, an approach combining the coefficient of determination method (CF) and a deep neural network (DNN) were proposed in this study for landslide susceptibility evaluation. The deep neural network can excavate the deep features of samples and improve the accuracy of the susceptibility model. In addition, the logistic regression model (LRM) and support vector machine (SVM) were selected to create landslide susceptibility maps for comparison, which also involved the coefficient of determination method (CF). Based on landslide remote sensing interpretation and field investigations, a spatial database of mudstone landslides in the Xining area was established. Eight different conditional factors, including the elevation, slope, slope aspect, undulation, curvature, watershed, distance from a fault, and distance from a road, in the study area were selected as the evaluation factors to evaluate the susceptibility. The results revealed that four factors (i.e., the ground elevation, curvature, distance from a fault, and distance from a road) had relatively significant influences on the landslide susceptibility in the study area. Finally, the confusion matrix was used to evaluate the accuracy of the results obtained using the three methods, and the optimal result was selected to evaluate the landslide susceptibility in the study area. It was found that the combined CF-DNN method was more suitable for evaluating the landslide susceptibility in this area. Landslide susceptibility zoning was conducted to divide the study area into four sensitivity levels: low (32.65%), medium (35.12%), high (22.44%), and extremely high (9.79%) susceptibility. The high-risk areas were primarily distributed in the high-elevation areas along the eastern edge of the Huangshui Basin.

GIS-based modeling of landslide susceptibility zonation by integrating the frequency ratio and objective–subjective weighting approach: a case study in a tropical monsoon climate region

“…In statistical analysis, numerous methods were applied to landslide susceptibility, mostly by frequency ratio (FR) (Nicu and Asăndulesei, 2018), Weight of Evidence (WoE) (Razavizadeh et al, 2017), Shannon entropy (SE) (Roodposhti et al, 2016), and logistic regression (LR) (Budimir et al, 2015). The technological era of artificial intelligence has witnessed a variety of machine learning-based methods, such as the traditional algorithms support vector machine (SVM), random forest (RF), and recent innovations in deep learning models (Zhang et al, 2022;Ma et al, 2023). On the other hand, semi-qualitative approaches, such as the analytic hierarchy process (AHP) (Kayastha et al, 2013), fuzzy logic (Bui et al, 2015), and weighted linear combination (WLC) (Li et al, 2022), were also recognized for their significant applications in landslide probability zonation (Tyagi et al, 2022).…”

GIS-based landslide and rockfall susceptibility zoning in Chepelarska River Basin (Western Rhodope Mountains, Bulgaria)

“…In the literature, LSZ has adopted two approaches: 1) a qualitative approach based on expert knowledge and 2) a quantitative approach that is based on statistical algorithms, deterministic, frequency analysis or using the certainty factor and deep neural network (e.g. Carrara et al, 1991;Van Westen, 1993;Van Westen et al, 1997;Lee, Sambath, 2006;Pradhan, 2010;Yalcin et al, 2011;Bourenane et al, 2015;Steger et al, 2016;Oh et al, 2017;Dobrev et al, 2023;Ma et al, 2023). The first approach is strongly influenced by the knowledge of the experts.…”