文献类型：期刊文献

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

作者：Moghimi, Armin[1];Singha, Chiranjit[2];Fathi, Mahdiyeh[3];Pirasteh, Saied[4,5];Mohammadzadeh, Ali[6];Varshosaz, Masood[4,6];Huang, Jian[4,7];Li, Huxiong[4]

机构：[1]Leibniz Univ Hannover, Ludwig Franzius Inst Hydraul Estuarine & Coastal E, Nienburger Str 4, D-30167 Hannover, Germany;[2]Visva Bharati Univ, Inst Agr, Dept Agr Engn, Birbhum 731236, W Bengal, India;[3]Univ Tehran, Coll Engn, Sch Surveying & Geospatial Engn, Tehran, Iran;[4]Shaoxing Univ, Inst Artificial Intelligence, 508 West Huancheng Rd, Shaoxing 312000, Zhejiang Provin, Peoples R China;[5]Saveetha Inst Med & Tech Sci, Saveetha Sch Engn, Dept Geotech & Geomat, Chennai, Tamilnadu, India;[6]KN Toosi Univ Technol, Geomat Engn Fac, Dept Photogrammetry & Remote Sensing, Tehran, Iran;[7]Shaoxing Univ, Principals Off, Shaoxing 312000, Peoples R China

年份：2024

卷号：14

外文期刊名：QUATERNARY SCIENCE ADVANCES

收录：ESCI(收录号：WOS:001291976700001)、Scopus(收录号：2-s2.0-85190852052)、WOS

语种：英文

外文关键词：Natural hazard; Landslide susceptibility modeling (LSM); Convolutional neural network (CNN); Random forest (RF); Open Buildings

外文摘要：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 geoenvironmental 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.