A new study has found that machine learning techniques can be utilized to better identify food insecurity outbreaks across the world long before they occur. The timely disbursement of humanitarian aid can be crucial during a food crisis, making the gathering of information and response times extremely important, researchers argue.

The study, published in the journal Science Advances, used deep learning to extract relevant text from over 11 million news articles focused on food-insecure countries and published between 1980 and 2020.

By analyzing how journalists reported on food insecurity and its causes, researchers found that news indicators significantly improved the Integrated Phase Classification (IPC) predictions of food insecurity across 21 countries from 2009 to 2020.

This creates an early warning system that mines news coverage to predict incoming food crisis outbreaks more accurately than the traditional risk systems currently used across 37 food-insecure countries in Africa, Asia, and Latin America.

Samuel Fraiberger, a data scientist at the World Bank Group and co-author of the paper, highlights that traditional food security models rely on risk measures that are often delayed, outdated, or incomplete. This method could have a significant impact on how humanitarian aid is allocated to regions, helping to prevent looming food crises.

Speaking to Axios, Art delaCruz, CEO of Team Rubicon stated:

When a disaster strikes, and some of those things that people rely on is the connectors between water and food and where they are, it begins to create gaps in the ability to solve that food chain.

"Hope is a terrible game plan when it comes to disasters," delaCruz concluded.