Landslide Assessment Classification Using Deep Neural Networks Based on Climate and Geospatial Data

Sustainability, Journal Year: 2024, Volume and Issue: 16(16), P. 7063 - 7063

Published: Aug. 17, 2024

This study presents a method for classifying landslide triggers and sizes using climate geospatial data. The data were sourced from the Global Landslide Catalog (GLC), which identifies rainfall-triggered events globally, regardless of size, impact, or location. Compiled 2007 to 2018 at NASA Goddard Space Flight Center, GLC includes various mass movements triggered by rainfall other events. Climatic 10 years preceding each event, including variables such as amounts, humidity, pressure, temperature, integrated with dataset was then used classify deep neural networks (DNNs) optimized through genetic algorithm (GA)-driven hyperparameter tuning. DNN models achieved accuracies 0.67 0.82, respectively, in multiclass classification tasks. research demonstrates effectiveness GA enhance disaster risk management.

Language: Английский

Reactivation mechanism of a deep-seated landslide along fault zones in Baihetan reservoir area

Bulletin of Engineering Geology and the Environment, Journal Year: 2024, Volume and Issue: 83(12)

Published: Nov. 9, 2024

Language: Английский