Factors Affecting Landslide Susceptibility Mapping: Assessing the Influence of Different Machine Learning Approaches, Sampling Strategies and Data Splitting

Abstract

Data driven methods are widely used for the development of Landslide Susceptibility Mapping (LSM). The results of these methods are sensitive to different factors, such as the quality of input data, choice of algorithm, sampling strategies, and data splitting ratios. In this study, five different Machine Learning (ML) algorithms are used for LSM for the Wayanad district in Kerala, India, using two different sampling strategies and nine different train to test ratios in cross validation. The results show that Random Forest (RF), K Nearest Neighbors (KNN), and Support Vector Machine (SVM) algorithms provide better results than Naïve Bayes (NB) and Logistic Regression (LR) for the study area. NB and LR algorithms are less sensitive to the sampling strategy and data splitting, while the performance of the other three algorithms is considerably influenced by the sampling strategy. From the results, both the choice of algorithm and sampling strategy are critical in obtaining the best suited landslide susceptibility map for a region. The accuracies of KNN, RF, and SVM algorithms have increased by 10.51%, 10.02%, and 4.98% with the use of polygon landslide inventory data, while for NB and LR algorithms, the performance was slightly reduced with the use of polygon data. Thus, the sampling strategy and data splitting ratio are less consequential with NB and algorithms, while more data points provide better results for KNN, RF, and SVM algorithms.