Food Security: New Tool Can Forecast Food Insecurity Up to 30 Days in Advance

Time trends of insufficient food consumption. Each panel displays daily time series of the percentage of people with insufficient food consumption in the first-level administrative units of Burkina Faso, Cameroon, Mali, Nigeria, Syria and Yemen. The six countries are highlighted in the map, and the orange shade indicates the areas that are considered by our analysis. The map was created by the authors using GeoPandas v0.9.079 and the shapefiles provided by OCHA under the CC BY-IGO license on HDX (https://data.humdata.org/).

A new tool that can be used to forecast the prevalence of individuals within a country that may have insufficient access to food — known as food insecurity — up to 30 days into the future is presented in a study published in Scientific Reports. The authors suggest that the tool could aid decision makers in countries at risk of food insecurity and help facilitate more timely responses.

Elisa Omodei and colleagues developed the tool using food consumption data from Burkina Faso, Cameroon, Mali, Nigeria, Syria and Yemen — all countries that have recently experienced acute food insecurity — between 2018 and 2022. The authors enhanced their tool with data on conflict-related fatalities, food prices, extreme weather events and the occurrence of Ramadan — as food consumption patterns within much of each country are altered during this month of the Islamic calendar — throughout this period. They then used their tool to estimate the prevalence of households at risk of insufficient access to food between October 2021 and February 2022.

The authors found that their tool was able to forecast the prevalence of food insecurity within Yemen and Syria with 99% accuracy one day into the future and with 72% and 47% accuracy, respectively, 30 days into the future. However, they found that for the remaining four countries, which had less available food consumption data than Syria and Yemen, the tool’s predictions were not as accurate. This highlights that the tool’s forecasts are more accurate when using food consumption data collected at regular intervals over long periods of time and across a broad range of geographic areas.

The authors suggest that their tool could complement existing techniques for modelling food insecurity by providing rapidly available forecasts using real-time data. Their tool’s predictions could be further improved by incorporating mobile phone data or automated text mining of news, they add.

No Comments Yet

Leave a Reply

Your email address will not be published.

©2024 Africa Security News Wire. Use Our Intel. All Rights Reserved. Washington, D.C.