Details
| Original language | English |
|---|---|
| Article number | 100187 |
| Number of pages | 20 |
| Journal | Quaternary Science Advances |
| Volume | 14 |
| Early online date | 18 Apr 2024 |
| Publication status | E-pub ahead of print - 18 Apr 2024 |
Abstract
Landslides are a prevalent natural hazard in West Bengal, India, particularly in Darjeeling and Kurseong, resulting in substantial socio-economic and physical consequences. This study aims to develop a hybrid model, integrating a Genetic-based Random Forest (GA-RF) and a novel Self-Attention based Convolutional Neural Network and Long Short-term Memory (SA-CNN-LSTM), for accurate landslide susceptibility mapping (LSM) and generate landslide vulnerability-building map in these regions. To achieve this, we compiled a database with 1830 historical data points, incorporating a landslide inventory as the dependent variable and 32 geo-environmental parameters from Remote Sensing (RS) and Geographic Information Systems (GIS) layers as independent variables. These parameters include features like topography, climate, hydrology, soil properties, terrain distribution, radar features, and anthropogenic influences. Our hybrid model exhibited superior performance with an AUC of 0.92 and RMSE of 0.28, outperforming standalone SA-CNN-LSTM, GA-RF, RF, MLP, and TreeBagger models. Notably, slope, Global Human Modification (gHM), Combined Polarization Index (CPI), distances to streams and roads, and soil erosion emerged as key layers for LSM in the region. Our findings identified around 30% of the study area as having high to very high landslide susceptibility, 20% as moderate, and 50% as low to very low. The vulnerability-building map for 244,552 building footprints indicated varying landslide risk levels, with a significant proportion (27.74%) at high to very high risk. Our model highlighted high-risk zones along roads in the northeastern and southern areas. These insights can enhance landslide risk management in Darjeeling and Kurseong, guiding sustainable strategies for future damage qualification.
Keywords
- Convolutional neural network (CNN), Landslide susceptibility modeling (LSM), Natural hazard, Open Buildings, Random forest (RF)
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Geology
- Earth and Planetary Sciences(all)
- Earth-Surface Processes
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Quaternary Science Advances, Vol. 14, 100187, 06.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India
AU - Moghimi, Armin
AU - Singha, Chiranjit
AU - Fathi, Mahdiyeh
AU - Pirasteh, Saied
AU - Mohammadzadeh, Ali
AU - Varshosaz, Masood
AU - Huang, Jian
AU - Li, Huxiong
PY - 2024/4/18
Y1 - 2024/4/18
N2 - Landslides are a prevalent natural hazard in West Bengal, India, particularly in Darjeeling and Kurseong, resulting in substantial socio-economic and physical consequences. This study aims to develop a hybrid model, integrating a Genetic-based Random Forest (GA-RF) and a novel Self-Attention based Convolutional Neural Network and Long Short-term Memory (SA-CNN-LSTM), for accurate landslide susceptibility mapping (LSM) and generate landslide vulnerability-building map in these regions. To achieve this, we compiled a database with 1830 historical data points, incorporating a landslide inventory as the dependent variable and 32 geo-environmental parameters from Remote Sensing (RS) and Geographic Information Systems (GIS) layers as independent variables. These parameters include features like topography, climate, hydrology, soil properties, terrain distribution, radar features, and anthropogenic influences. Our hybrid model exhibited superior performance with an AUC of 0.92 and RMSE of 0.28, outperforming standalone SA-CNN-LSTM, GA-RF, RF, MLP, and TreeBagger models. Notably, slope, Global Human Modification (gHM), Combined Polarization Index (CPI), distances to streams and roads, and soil erosion emerged as key layers for LSM in the region. Our findings identified around 30% of the study area as having high to very high landslide susceptibility, 20% as moderate, and 50% as low to very low. The vulnerability-building map for 244,552 building footprints indicated varying landslide risk levels, with a significant proportion (27.74%) at high to very high risk. Our model highlighted high-risk zones along roads in the northeastern and southern areas. These insights can enhance landslide risk management in Darjeeling and Kurseong, guiding sustainable strategies for future damage qualification.
AB - Landslides are a prevalent natural hazard in West Bengal, India, particularly in Darjeeling and Kurseong, resulting in substantial socio-economic and physical consequences. This study aims to develop a hybrid model, integrating a Genetic-based Random Forest (GA-RF) and a novel Self-Attention based Convolutional Neural Network and Long Short-term Memory (SA-CNN-LSTM), for accurate landslide susceptibility mapping (LSM) and generate landslide vulnerability-building map in these regions. To achieve this, we compiled a database with 1830 historical data points, incorporating a landslide inventory as the dependent variable and 32 geo-environmental parameters from Remote Sensing (RS) and Geographic Information Systems (GIS) layers as independent variables. These parameters include features like topography, climate, hydrology, soil properties, terrain distribution, radar features, and anthropogenic influences. Our hybrid model exhibited superior performance with an AUC of 0.92 and RMSE of 0.28, outperforming standalone SA-CNN-LSTM, GA-RF, RF, MLP, and TreeBagger models. Notably, slope, Global Human Modification (gHM), Combined Polarization Index (CPI), distances to streams and roads, and soil erosion emerged as key layers for LSM in the region. Our findings identified around 30% of the study area as having high to very high landslide susceptibility, 20% as moderate, and 50% as low to very low. The vulnerability-building map for 244,552 building footprints indicated varying landslide risk levels, with a significant proportion (27.74%) at high to very high risk. Our model highlighted high-risk zones along roads in the northeastern and southern areas. These insights can enhance landslide risk management in Darjeeling and Kurseong, guiding sustainable strategies for future damage qualification.
KW - Convolutional neural network (CNN)
KW - Landslide susceptibility modeling (LSM)
KW - Natural hazard
KW - Open Buildings
KW - Random forest (RF)
UR - http://www.scopus.com/inward/record.url?scp=85190852052&partnerID=8YFLogxK
U2 - 10.1016/j.qsa.2024.100187
DO - 10.1016/j.qsa.2024.100187
M3 - Article
AN - SCOPUS:85190852052
VL - 14
JO - Quaternary Science Advances
JF - Quaternary Science Advances
M1 - 100187
ER -