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

Joris J L Westerveld; Marc J C van den Homberg; Gabriela Guimarães Nobre; Dennis L J van den Berg; Aklilu D Teklesadik; Sjoerd M Stuit

doi:10.1016/j.scitotenv.2021.147366

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

Sci Total Environ. 2021 Sep 10:786:147366. doi: 10.1016/j.scitotenv.2021.147366. Epub 2021 Apr 27.

Authors

Joris J L Westerveld¹, Marc J C van den Homberg², Gabriela Guimarães Nobre³, Dennis L J van den Berg², Aklilu D Teklesadik⁴, Sjoerd M Stuit⁵

Affiliations

¹ TNO Defense, Security and Safety, the Netherlands; Department of Experimental Psychology, Utrecht University, the Netherlands; 510, an initiative of the Netherlands Red Cross, the Netherlands. Electronic address: Joriswesterveld93@gmail.com.
² 510, an initiative of the Netherlands Red Cross, the Netherlands.
³ Institute for Environmental Studies (IVM), Vrije Universiteit Amsterdam, the Netherlands; World Food Programme, Research, Assessment and Monitoring Division, Italy.
⁴ 510, an initiative of the Netherlands Red Cross, the Netherlands; Vrije Universiteit Brussel, Belgium.
⁵ Department of Experimental Psychology, Utrecht University, the Netherlands.

PMID: 33971600
DOI: 10.1016/j.scitotenv.2021.147366

Abstract

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.

Keywords: Early warning systems; Extreme gradient boosting; Food security; IPC; Machine learning; Open data.