Hybrid machine learning approach for landslide prediction, Uttarakhand, India

Abstract

Natural disasters always have a damaging effect on our way of life. Landslides cause serious damage to both human and natural resources around the world. In this paper, the prediction accuracy of five hybrid models for landslide occurrence in the Uttarkashi, Uttarakhand (India) was evaluated and compared. In this approach, the Rough Set theory coupled with five different models namely Bayesian Network (HBNRS), Backpropagation Neural Network (HBPNNRS), Bagging (HBRS), XGBoost (HXGBRS), and Random Forest (HRFRS) were taken into account. The database for the models development was prepared using fifteen conditioning factors that had 373 landslide and 181 non-landslide locations that were then randomly divided into training and testing locations with a ratio of 75%:25%. The appropriateness and predictability of these conditioning factors were assessed using the multi-collinearity test and the least absolute shrinkage and selection operator approach. The accuracy, sensitivity, specificity, precision, and F-Measures, and the area under the curve (AUC)-receiver operating characteristics curve, were used to evaluate and compare the performance of the individual and hybrid created models. The findings indicate that the constructed hybrid model HXGBRS (AUC = 0.937, Precision = 0.946, F1-score = 0.926 and Accuracy = 89.92%) is the most accurate model for predicting landslides when compared to other models (HBPNNRS, HBNRS, HBRS, and HRFRS). Importantly, when the fusion is performed with the rough set method, the prediction capability of each model is improved. Simultaneously, the HXGBRS model proposed shows superior stability and can effectively avoid overfitting. After the core modules were developed, the user-friendly platform was designed as an integrated GIS environment using dynamic maps for effective landslide prediction in large prone areas. Users can predict the probability of landslide occurrence for selected region by changing the values of a conditioning factors. The created approach could be beneficial for predicting the impact of landslides on slopes and tracking landslides along national routes.

SBAS-InSAR based validated landslide susceptibility mapping along the Karakoram Highway: a case study of Gilgit-Baltistan, Pakistan

“…Also, XGBoost is designed to train with multiple Processing cores, and it can identify and learn upon nonlinear data patterns, and regularized boosting is employed. Therefore the model can avoid the overfitting problem and enhances the prediction accuracy 15 , 96 .…”

Analyzing hydro-meteorological data from Yamuna river basin, western Himalaya: Using a Markov Chain and LSTM approach to forecast future disasters

“…Intense precipitation comes by the end of November, and higher altitude treks are impractical until late March when the snows melt. Most rain happens in the monsoon season (59-84 percent) between July to September in Uttarakhand (Kainthura and Sharma, 2022). Markov Chain approach also gives successful results during the monsoon period.…”

Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation

“…Climate change results in an increased probability of extreme weather events causing, among others, severe floods [1], landslides [2], and glacier collapses [3]. Such natural hazards can cause significant casualties, put critical infrastructures at risk of failure, and decrease the quality of human lives.…”