Combining logistic regression-based hybrid optimized machine learning algorithms with sensitivity analysis to achieve robust landslide susceptibility mapping

Abstract

Landslides and other catastrophic environmental disasters pose a significant danger to environmental, infrastructure, and people's lives. This research aimed to construct four optimized ensemble machine learning algorithms for landslide susceptibility (LS) mapping, namely particle swarm optimization (PSO) based artificial neural network (ANN), random forest, M5P, and support vector machine. The logistic regression (LR) model was then applied to the four-ensemble machine learning model and generated a hybrid optimized machine learning model. The receiver operating characteristics (ROC) curve was then used to validate LS map. The best model of four LS models depending on ROC's area under curve (AUC) is PSO-ANN (AUC-0.958) model. Also, LR model-based hybrid ensemble machine learning model achieved better accuracy (AUC: 0.962) than PSO-ANN model. Various resources, viz. grassland, built-up, and scarce foliage, are declared as landslide risk zones. Finally, elevation, soil-texture, slope, rainfall, and road distance are considered the most sensitive parameters for landslide occurrences.