In Somalia, AI is helping deliver food to hungry families

Artificial intelligence is helping the World Food Programme (WFP) deliver aid to Somalis facing a deepening hunger crisis, according to UN News. Data collected by WFP partners and analyzed through AI tools in the agency’s hunger-tracking platform, HungerMap Live, enable teams to position resources in specific areas before conditions deteriorate. Although WFP cannot reach all 6 million Somalis facing hunger, the technology helps prioritize aid where it is most needed. In Burhakaba District, about 180 kilometres northwest of Mogadishu, the tools guided assistance to dangerously malnourished children. The story illustrates how predictive analytics are reshaping humanitarian response in one of the world’s most severe hunger hotspots.

Somalia faces climate change-induced droughts followed by flash floods and a brutal conflict that has persisted for 35 years and killed hundreds of thousands. The Horn of Africa country also imports most of its food, exposing it to global price shocks such as the current conflict in the Middle East. In June, WFP and the UN’s Food and Agriculture Organization (FAO) added Somalia to their list of “hunger hotspots of highest concern” alongside northeast Nigeria. The list also includes Sudan, South Sudan, Yemen and Palestine.

“It is a very gruesome situation, and I’m very, very concerned about these next few weeks and months,” said Simon Renk, head of vulnerability, analysis and mapping for the WFP in Somalia.

Old technology, new lifesaving potential

HungerMap Live was first launched in January 2020 to monitor food security in more than 90 countries. The publicly accessible platform draws on data covering food insecurity, climate, economies, agriculture and inflation to display areas that are food insecure or trending that way. Its initial version used AI to estimate food insecurity in countries lacking sufficient data, but its ability to predict future crises was limited. It also did not track the nutritional quality of diets in the countries it covered. HungerMap Live 2.0, released by WFP in April, overhauled the user interface and introduced new predictive AI features.

In Burhakaba, WFP humanitarian workers identified the district’s urgent need through the AI tools, providing food assistance to 48,000 people and nutrition support to 3,000 women and children.

“Instead of waiting for that malnutrition of children to deteriorate and lead to displacement or even death, we knew it prior,” Renk told UN News.

The data cannot replace on-the-ground assessment, but it helps WFP decide which communities to help first and which type of aid—cash or specialized nutrition support—is most useful. WFP analyzes predictive data on rainfall deficits, flood risk, market prices, conflict and nutrition to forecast where hunger will strike next. This allows governments to take preventive action and WFP and partners to pre-position assistance.

Prioritizing aid in Somalia

In a country where 6 million people experience crisis levels of food insecurity, WFP is only able to reach one in 10 people in need. WFP’s office in Somalia requires an additional $192 million between now and January 2027 to reach everyone who needs food, Renk said. With resources stretched thin, AI-powered tools help the agency decide which communities to prioritize and shorten the time between early warning and lifesaving action. Renk stressed that using AI does not compensate for the fact that most Somalis who need help will not receive it. “It helps us to prioritise with stronger evidence,” he said. “But in itself, it doesn’t make the shortage of support acceptable.”