Improving debris flow evacuation alerts in Taiwan using machine learning

TL;DR

This paper demonstrates that machine learning models, especially random forests, can significantly improve debris flow prediction accuracy in Taiwan, reducing false alarms and saving lives compared to existing rainfall threshold systems.

Contribution

The study introduces machine learning models for debris flow prediction in Taiwan, outperforming current systems and identifying key rainfall patterns associated with debris flows.

Findings

Random forest outperforms other models in debris flow prediction.

Machine learning reduces false alarms compared to existing thresholds.

Rainfall trajectories are strongly linked to debris flow occurrences.

Abstract

Taiwan has the highest susceptibility to and fatalities from debris flows worldwide. The existing debris flow warning system in Taiwan, which uses a time-weighted measure of rainfall, leads to alerts when the measure exceeds a predefined threshold. However, this system generates many false alarms and misses a substantial fraction of the actual debris flows. Towards improving this system, we implemented five machine learning models that input historical rainfall data and predict whether a debris flow will occur within a selected time. We found that a random forest model performed the best among the five models and outperformed the existing system in Taiwan. Furthermore, we identified the rainfall trajectories strongly related to debris flow occurrences and explored trade-offs between the risks of missing debris flows versus frequent false alerts. These results suggest the potential for machine learning models trained on hourly rainfall data alone to save lives while reducing false alerts.