What question did this study set out to answer?

The aim is to apply machine learning models to forecast landslide displacement influenced by rainfall and pore water pressure.

Data-driven Forecasting of Landslide Displacement Using Machine Learning and Real-time Monitoring

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates the capability of machine learning to improve landslide prediction in vulnerable areas, highlighting rainfall's impact.

The aim is to apply machine learning models to forecast landslide displacement influenced by rainfall and pore water pressure.
Analyzed hourly rainfall and pore water pressure data from a monitoring system between 2020 and 2024.
Employed Decision Tree, Random Forest, and Long Short-Term Memory models to assess landslide predictors.
Identified critical cumulative rainfall thresholds linked to landslide occurrences.
The Random Forest model achieved the highest predictive performance with an R² of 0.6406.
Cumulative rainfall thresholds were determined as crucial indicators for landslide events.
Results support enhanced early warning systems for landslide risk mitigation.

Tien et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark