In this episode, we talk with Ms. Jamila B. Abuda about her study on using machine learning to predict when landslides are likely to occur along a mountain highway in Benguet, Philippines. Being able to predict when landslides will happen is critical for early warning systems. The study tested five machine learning algorithms using only rainfall data and documented landslide events, and found that grouping landslide occurrences by rock type or lithology before training the models significantly improved prediction accuracy.

📚Reference: Abuda JB, Saturay RM Jr., Catane SG, Guevarra I. 2026. Lithologically-constrained, machine learning-based temporal landslide prediction models using rainfall time series for the Benguet First Engineering District, Philippines. Bulletin of Engineering Geology and the Environment. 85:156.

🤝Behind The Science Podcast is in partnership with the UP Resilience Institute.