Torrential rainfall-induced landslide susceptibility assessment using machine learning and statistical methods of eastern Himalaya

Landslide susceptibility predictive capabilities are believed to be varied with numerous techniques such as stand-alone statistical, stand-alone machine learning (ML), and ensemble of statistical and ML. However, the landslide susceptibility (LS) model is constantly being modified with recent progress in statistics and in ML. We used logistic regression (LR), random forest (RF), boosted regression tree (BRT), BRT-LR, and BRT-RF model for model calibration and validation. Apart from that, we used RF to measure the relative importance of landslide causative factors (LCFs). Tests were conducted to the damaged landslide patches using a number of 16 LCFs (geomorphological, hydrological, geological, and environmental). We noticed that the predicted rates are exceptional for the BRT-RF model (AUC: 0.919), whereas models of LR (0.822), RF (0.876), BRT (0.857), and BRT-LR (0.902) produced higher variations in the data set accuracy. We therefore propose that the BRT-RF model be an effective method of increasing predictive precision level of LS. This research finding can be used in other fields for planning and management by stakeholders in order to minimize the impact of landslide.

Automated summary

Different techniques were used to predict landslide susceptibility, with the BRT-RF model showing exceptional predictive rates. The research findings have practical implications for planning and management to minimize landslide impacts.