Publication details

Landslide susceptibility mapping along the Thimphu-Phuentsholing highway using machine learning


DAHAL Manju Sara CHHETRI Asheer GHALLEY Hemant PASANG Sangey PATRA Moujhuri

Year of publication 2022
Type Chapter of a book
MU Faculty or unit

Faculty of Science

Description In the Himalayan region, landslides are considered one of the most common natural disasters. The study area for this study is a 2 km buffer along the Thimphu-Phuentsholing highway in Bhutan, which is a part of Asian Highway 48. In this study, machine learning was adopted which allows relatively precise predictions to be made by providing accurate and reliable data. Of the numerous methods available for machine learning, two methods, i.e., random forest (RF) and logistic regression (LR) have been selected for this paper. Slope, aspect, geology, land cover, precipitation, distance from the drainage, distance from the road, TPI, TRI, Elevation, and surface roughness were the parameters selected for the study area. The two methods are validated and compared using the ROC and (AUC). The RF method performed slightly better than the LR method with an AUC of 0.91 and LR of 0.86.

You are running an old browser version. We recommend updating your browser to its latest version.

More info