Landslide susceptibility assessment in the monsoon-dominated Sikkim Himalayan region using state-of-the-art models

Landslides are a common life-threatening natural event in the Sikkim Himalayan Region (SHR). The state-of-the-art decision tree (DT), random forest (RF) and deep learning neural network (DLNN) models were employed to assess landslide susceptibility mapping (LSM) in the monsoon-dominated SHR. The major findings of this research highlight that DLNN is the most effective tool for assessing LSM, proving to be more accurate than alternative methods. The LSM depicts that the southern part of the study area poses high landslide susceptibility than the other parts. The AUC‒ROC curve successfully validated the model, which is 89.90 % for DLNN, 87.20% for RF and 81.10% for DT. More participation of local communities, along with strict governmental policies, could be effective in mitigating landslides in the SHR. Adaptation of advanced RS and GIS, along with hybrid models (deep learning and soft computing), could be important tools to assess LSM more accurately.

Authors

Institutions

Publication Details

Journal
Geocarto International
Published
2026-11-14
DOI
https://doi.org/10.1080/10106049.2026.2682726
Primary Topic
Landslides and related hazards
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Landslide susceptibility assessment in the monsoon-dominated Sikkim Himalayan region using state-of-the-art models

Asish Saha, Chaitanya B. Pande, Aznarul Islam, Tanmoy Biswas et al.
Geocarto International
Landslides and related hazards
article

Landslide susceptibility assessment in the monsoon-dominated Sikkim Himalayan region using state-of-the-art models

Asish Saha, Chaitanya B. Pande, Aznarul Islam, Tanmoy Biswas, Subodh Chandra Pal, Edris Alam, Debasis Sengupta
article en

Abstract

Landslides are a common life-threatening natural event in the Sikkim Himalayan Region (SHR). The state-of-the-art decision tree (DT), random forest (RF) and deep learning neural network (DLNN) models were employed to assess landslide susceptibility mapping (LSM) in the monsoon-dominated SHR. The major findings of this research highlight that DLNN is the most effective tool for assessing LSM, proving to be more accurate than alternative methods. The LSM depicts that the southern part of the study area poses high landslide susceptibility than the other parts. The AUC‒ROC curve successfully validated the model, which is 89.90 % for DLNN, 87.20% for RF and 81.10% for DT. More participation of local communities, along with strict governmental policies, could be effective in mitigating landslides in the SHR. Adaptation of advanced RS and GIS, along with hybrid models (deep learning and soft computing), could be important tools to assess LSM more accurately.

Geocarto InternationalVol. 41(1)
University of Burdwan (IN), Aliah University (IN), Al-Ayen Iraqi University (IQ), Rabdan Academy (AE), Manipal University Jaipur (IN), University of Chittagong (BD)
Landslides and related hazards
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon