UP develops AI model for tropical cyclone rainfall prediction

Climate experts from the University of the Philippines (UP) have developed an artificial intelligence model that uses past tropical cyclone tracks to predict rainfall.

The AI model, developed by Dr. Gerry Bagtasa and Cris Gino Mesias, utilizes machine learning techniques and can spot patterns more efficiently than previous models.

Unlike dynamic models that require significant computational resources, this AI model can run within minutes on a laptop.

A study published in the journal Meteorological Applications found the AI model's predictive skill for rainfall was comparable to, and better for extreme rainfall than, regularly used dynamic models.

The storm's distance and duration are the primary parameters influencing the AI model's rainfall predictions.

This development is considered crucial for disaster risk reduction efforts, providing a more efficient and robust tool for forecasting.