A GIS-Based Landslide Susceptibility Mapping and Variable Importance Analysis Using Artificial Intelligent Training-Based Methods

Abstract

Landslides often cause significant casualties and economic losses, and therefore landslide susceptibility mapping (LSM) has become increasingly urgent and important. The potential of deep learning (DL) like convolutional neural networks (CNN) based on landslide causative factors has not been fully explored yet. The main target of this study is the investigation of a GIS-based LSM in Zanjan, Iran and to explore the most important causative factor of landslides in the case study area. Different machine learning (ML) methods have been employed and compared to select the best results in the case study area. The CNN is compared with four ML algorithms, including random forest (RF), artificial neural network (ANN), support vector machine (SVM), and logistic regression (LR). To do so, sixteen landslide causative factors have been extracted and their related spatial layers have been prepared. Then, the algorithms were trained with related landslide and non-landslide points. The results illustrate that the five ML algorithms performed suitably (precision = 82.43–85.6%, AUC = 0.934–0.967). The RF algorithm achieves the best result, while the CNN, SVM, the ANN, and the LR have the best results after RF, respectively, in this case study. Moreover, variable importance analysis results indicate that slope and topographic curvature contribute more to the prediction. The results would be beneficial to planning strategies for landslide risk management.

Landslide Susceptibility Mapping of Landslides with Artificial Neural Networks: Multi-Approach Analysis of Backpropagation Algorithm Applying the Neuralnet Package in Cuenca, Ecuador

“…The use of hidden layers increases the model flexibility, though one hidden layer is usually sufficient to model continuous functions [84], considering that an excessive number of hidden neurons would cause overfitting problems; therefore, it is preferable to use the least number of hidden neurons for an adequate performance of the network [85]. Based on the above and considering that trial and error methods are used to determine the number of neurons in the hidden layer [86], the implementation of ANN in this research was based on an experimental procedure, elaborating several tests with different numbers of hidden neurons, which allowed obtaining a better performance of the network in terms of runtime, validation parameter values, and avoiding problems of non-convergence of the ANN, by configuring a hidden layer with three neurons. By increasing the number of hidden neurons or the number of neurons within this layer, problems such as an excessive runtime or lack of convergence were encountered.…”

On the use of explainable AI for susceptibility modeling: examining the spatial pattern of SHAP values

“…The most traditional way to understand how a machine-learning models work is to list the variable importance ranking (e.g., Band et al, 2020;Hosseini et al, 2020;Zhao et al, 2022b). Here, we also produce the same graphics in Figure 5 but use SHAP values to sort each predictor according to the impact it may have over the final susceptibility.…”

Improving the accuracy of forest aboveground biomass using Landsat 8 OLI images by quantile regression neural network for Pinus densata forests in southwestern China

“…The stepwise linear regression model (LSR) can select variables closely related to the response variables by significance testing, solving the problem of collinearity among explanatory variables (Zhu et al, 2017). However, when the models with insignificant influence on dependent variables are ignored, there would be a lower prediction accuracy when the forest AGB and the independent variables do not have a simple linear relationship (Yadav et al, 2021;Zhao et al, 2022).…”

“…Many non-parametric models have been explored for forest AGB estimation, such as random forest (RF) (Yadav et al, 2021), k-nearest neighbors (kNN) (Wan et al, 2021;Andras et al, 2022;Beaudoin et al, 2022), support vector machine (SVM) (Mountrakis et al, 2010;Christoffer et al, 2013), and maximum entropy (MaxEnt) (Wang et al, 2022;Zhao et al, 2022). Although the nonparametric models can provide an excellent fitting effect, it is still hard to improve the precision influence caused by overestimation and underestimation.…”