Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Armin Moghimi
  • Chiranjit Singha
  • Mahdiyeh Fathi
  • Saied Pirasteh
  • Ali Mohammadzadeh
  • Masood Varshosaz
  • Jian Huang
  • Huxiong Li

Externe Organisationen

  • Visva-Bharati University
  • University of Tehran
  • Shaoxing University
  • K.N. Toosi University of Technology
  • Saveetha University (SIMATS)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer100187
Seitenumfang20
FachzeitschriftQuaternary Science Advances
Jahrgang14
Frühes Online-Datum18 Apr. 2024
PublikationsstatusVeröffentlicht - Juni 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.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India. / Moghimi, Armin; Singha, Chiranjit; Fathi, Mahdiyeh et al.
in: Quaternary Science Advances, Jahrgang 14, 100187, 06.2024.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Moghimi, A, Singha, C, Fathi, M, Pirasteh, S, Mohammadzadeh, A, Varshosaz, M, Huang, J & Li, H 2024, 'Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India', Quaternary Science Advances, Jg. 14, 100187. https://doi.org/10.1016/j.qsa.2024.100187
Moghimi, A., Singha, C., Fathi, M., Pirasteh, S., Mohammadzadeh, A., Varshosaz, M., Huang, J., & Li, H. (2024). Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India. Quaternary Science Advances, 14, Artikel 100187. https://doi.org/10.1016/j.qsa.2024.100187
Moghimi A, Singha C, Fathi M, Pirasteh S, Mohammadzadeh A, Varshosaz M et al. Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India. Quaternary Science Advances. 2024 Jun;14:100187. Epub 2024 Apr 18. doi: 10.1016/j.qsa.2024.100187
Download
@article{4757f4553cee4272bbf9ea3f8a41a633,
title = "Hybridizing genetic random forest and self-attention based CNN-LSTM algorithms for landslide susceptibility mapping in Darjiling and Kurseong, India",
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)",
author = "Armin Moghimi and Chiranjit Singha and Mahdiyeh Fathi and Saied Pirasteh and Ali Mohammadzadeh and Masood Varshosaz and Jian Huang and Huxiong Li",
year = "2024",
month = jun,
doi = "10.1016/j.qsa.2024.100187",
language = "English",
volume = "14",

}

Download

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 - 2024/6

Y1 - 2024/6

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 -