Current Awardee

Predicting International Food Security Crises: A Data-Driven Approach

Hope Michelson
Hope Michelson

College: Agricultural, Consumer and Environmental Sciences
Award year: 2019-2020
NCSA collaborators: Liudmila Mainzer, Aiman Soliman

In food crises, faster and more accurate evaluation and response can save lives and resources. Methods currently in use to predict such crises have limitations that delay and impede humanitarian response: they are not model-driven, and they do not engage the full scope of available data. Because government policy-makers and Non-Governmental Organizations often fail to recognize specific food insecure populations, scarce resources to mitigate hunger can arrive too late and in the wrong places. In many parts of the world, crises of this sort are on the rise, requiring improved methods to identify their scale and scope. Developing and deploying an effective early warning system is urgent, given the expectation that climate shocks disrupting agricultural production and market functioning will increase in frequency and severity in coming decades.

We propose to develop and test a new model-driven method for predicting food crises across the world. Dr. Michelson's previous work (Lentz, Michelson, Baylis and Zhou, 2018) demonstrates that we can improve prediction of food security crises by exploiting publicly-available high-frequency, spatially-resolved data. The proposed collaboration with NCSA's Data Analytics Group and the NCSA Genomics Group will take this research to the next level: developing new data sources for predicting and applying state of the art machine learning techniques to the prediction problem.