How AI is supporting Philippines disaster relief

A new initiative in the Philippines is using artificial intelligence to support disaster relief, and better allocate aid after natural disasters.

510 global, an initiative of the Netherlands Red Cross, uses open data such as wind speeds, rainfall in affected areas, and datasets from past disasters to build a “Priority Index” for typhoons in the Philippines.

The team was able to release their first “Priority Index” 24 hours after Typhoon Haima in October this year. This enabled faster distribution of supplies due to predictions of the worst-hit areas.

The typhoon killed at least eight people, and destroyed tens of thousands of homes, according to AFP. “Currently damage assessments and identification of the most vulnerable is a time consuming process, which can takes weeks to complete due to logistics, safety constraints, or workload”, the team wrote.

Data on the distribution of damaged houses was later provided by the Department of Social Welfare and Development (DSWD) and the National Disaster Risk Reduction and Management Council (NDRRMC) and proved the predictions correct.

“Our objective is to develop machine learning methodologies that can be applied to different countries, using local data, and with minor modifications reach a fast and sufficiently accurate damage prediction”, the team said.

The team acknowledges one blind spot: the model “has difficulty to predict really low and really high damage”. It hopes to “get more complete building damage data” and victim statistics to reduce biases in the model.

The system will also be used in Nepal in case of future earthquakes, and also in Africa, the Red Cross said.

Now read: Five Great Government AI Projects Image shows destruction caused by Typhoon Haiyan in the city of Tacloban, Philippines