Forecasting transitions in the state of food security with machine learning using transferable features

• DOI: 10.1016/j.scitotenv.2021.147366
• Publication Date: 2021-04-27T10:49:06Z
• Authors: Joris J.L. Wester...; Marc J.C. van den...; Gabriela Guimarãe...; Dennis L.J. van d...; Aklilu D. Teklesadik; Sjoerd M. Stuit
• Keywords: Aurora Universities Network; 2. Zero hunger; 0301 basic medicine; Environmental Engineering; Open data; 1. No poverty; Extreme gradient boosting; Food security; Energy Research; Pollution; Early warning systems; EUTOPIA Alliance; 03 medical and health sciences; 13. Climate action; Machine learning; IPC; SDG 13 - Climate Action; Environmental Chemistry; SDG 2 - Zero Hunger; Waste Management and Disposal; Knowmad Institut; Netherlands

Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.