A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping

This study introduces four heterogeneous ensemble-learning techniques, that is, stacking, blending, simple averaging, and weighted averaging, to predict landslide susceptibility in Yanshan County, China. These techniques combine several state-of-the-art classifiers of convolutional neural network, recurrent neural network, support vector machine, and logistic regression in specific ways to produce reliable results and avoid problems with the model selection. The study consists of three main steps. The first step establishes a spatial database consisting of 16 landslide conditioning factors and 380 historical landslide locations. The second step randomly selects training (70% of the total) and test (30%) datasets out of grid cells corresponding to landslide and non-slide locations in the study area. The final step constructs the proposed heterogeneous ensemble-learning methods for landslide susceptibility mapping. The proposed ensemble-learning methods show higher prediction accuracy than the individual classifiers mentioned above based on statistical measures. The blending ensemble-learning method achieves the highest overall accuracy of 80.70% compared to the other ensemble-learning methods.

Automated summary

This study introduces four heterogeneous ensemble-learning techniques to predict landslide susceptibility, combining state-of-the-art classifiers in specific ways for reliable results and avoiding model selection issues. The proposed ensemble-learning methods show higher prediction accuracy than individual classifiers, with the blending method achieving the highest overall accuracy of 80.70%.