Comparative analysis of the TabNet algorithm and traditional machine learning algorithms for landslide susceptibility assessment in the Wanzhou Region of China

Natural Hazards, Journal Year: 2024, Volume and Issue: 120(8), P. 7627 - 7652

Published: March 15, 2024

Language: Английский

---

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

Quaternary Science Advances, Journal Year: 2024, Volume and Issue: 14, P. 100187 - 100187

Published: April 18, 2024

Landslides are a prevalent natural hazard in West Bengal, India, particularly Darjeeling and Kurseong, resulting substantial socio-economic physical consequences. This study aims to develop hybrid model, integrating Genetic-based Random Forest (GA-RF) novel Self-Attention based Convolutional Neural Network Long Short-term Memory (SA-CNN-LSTM), for accurate landslide susceptibility mapping (LSM) generate vulnerability-building map these regions. To achieve this, we compiled database with 1830 historical data points, incorporating inventory as the dependent variable 32 geo-environmental parameters from Remote Sensing (RS) Geographic Information Systems (GIS) layers independent variables. These include features like topography, climate, hydrology, soil properties, terrain distribution, radar features, anthropogenic influences. Our model exhibited superior performance an AUC of 0.92 RMSE 0.28, outperforming standalone SA-CNN-LSTM, GA-RF, RF, MLP, TreeBagger models. Notably, slope, Global Human Modification (gHM), Combined Polarization Index (CPI), distances streams roads, erosion emerged key LSM region. findings identified around 30% area having high very susceptibility, 20% moderate, 50% low low. The 244,552 building footprints indicated varying risk levels, significant proportion (27.74%) at risk. highlighted high-risk zones along roads northeastern southern areas. insights can enhance management guiding sustainable strategies future damage qualification.

Language: Английский

---

Spatiotemporal analysis, simulation, and early warning of landslides based on landslide sensitivity and multisource precipitation products in Southwestern China

Landslides, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Language: Английский

---

Interpretable machine learning models and decision-making mechanisms for landslide hazard assessment under different rainfall conditions

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126582 - 126582

Published: Jan. 1, 2025

Language: Английский

---

Early warning system for landslide of gentle Piedmont slope based on displacement velocity, factor of safety, and effective rainfall threshold

International Journal of Disaster Risk Reduction, Journal Year: 2025, Volume and Issue: unknown, P. 105232 - 105232

Published: Jan. 1, 2025

Language: Английский

---