As famine data dries up, can AI step in? (Devex)

A crowd of Rohingya refugees clamors for food during a distribution by a volunteer organization in Kutupalong camp in southern Bangladesh in 2017.

Credit: Tommy Trenchard / Panos Pictures

This was shared in Devex Newswire.

Researchers are developing AI tools to predict famine more accurately and affordably - especially in conflict zones and data-scarce areas - as traditional early warning systems face the financial strain of aid cuts, Devex reported. Yanyan Liu was interviewed for this article exploring how IFPRI's model could eventually assist humanitarians, policymakers, and development agencies once it is peer-reviewed and published, which could happen later this year.

"We are not trying to replace IPC or FEWS NET," said Yanyan Liu. "But we can say that our model, this method, is complementary," Liu said. "Our model can help fill in some gaps, some locations, in the conflict-affected setting, for example - where we cannot send people to go."

The article emphasized that conflict is one of the most important factors to consider when it comes to predicting hunger. Devex reported that the IFPRI team found that a 10% increase in conflict intensity corresponds with a 31% chance that people classified as "stressed" - or IPC Phase 2, according to IPC's five-stage framework for assessing the severity of hunger crises - get pushed into Phase 3 or worse, which marks the threshold for humanitarian crisis, and that Stage 5 is famine.

Using all of these inputs, the model uses machine learning to forecast the extent and severity of acute food insecurity up to a year in advance. Validated against published IPC estimates, it accurately identifies 94.1% of cases classified as IPC Phase 3 or worse, Liu said. In addition, 77.5% of cases the model predicted to experience severe food insecurity materialized within three to 12 months, the article stated.

Read the full article here.