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 progre...

Full description

Saved in:
Bibliographic Details
Published inNatural hazards (Dordrecht) Vol. 107; no. 1; pp. 697 - 722
Main Authors Chowdhuri, Indrajit, Pal, Subodh Chandra, Chakrabortty, Rabin, Malik, Sadhan, Das, Biswajit, Roy, Paramita
Format Journal Article
LanguageEnglish
Published Dordrecht Springer Netherlands 01.05.2021
Springer Nature B.V
Subjects
Calibration
Civil Engineering
Earth and Environmental Science
Earth Sciences
Environmental Management
Geomorphology
Geophysics/Geodesy
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Hydrology
Landslides
Learning algorithms
Machine learning
Natural Hazards
Original Paper
Rain
Rainfall
Regression analysis
Statistical analysis
Statistical methods
Statistics
Logistic regression
Random forest
Landslide susceptibility
Ensemble methods
Boosted regression tree
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:0921-030X
1573-0840
DOI:10.1007/s11069-021-04601-3