The Climate Hazards Center’s (CHC) workshop, “The Role of Machine Learning in Famine Early Warning”—held on October 15, 2019—gathered decision-makers, domain experts, applied analysts, and methodologists under the shared goal of identifying new quantitative methods and applications for advancing famine early warning. The meeting focused on methods and data that assist in predicting key food security determinants and outcomes, including food production, prices, and malnutrition. This workshop was highly successful in achieving its goal of gathering a diverse array of research applications and ideas to guide a productive discussion on the present and future role of machine learning in famine early warning. Furthermore, the workshop identified opportunities to use existing data sets in a machine learning framework to anticipate food insecurity.

 

 

The conference was primarily organized by CHC’s Frank Davenport, and included presentations by Shannon Wilson (USAID), Peter Thomas (Chemonics), Kathy Baylis (ACE, U of I), Doug Steigerwald (UCSB), Alan Murray (UCSB), Gary Eilerts (FEWS NET), Chris Funk (CHC & USGS), and Kelsey Jack (UCSB). 

 

The Climate Hazards Center extends its sincerest gratitude to all participants and attendees, with special thanks to the UCSB College of Letters and Sciences Conference Support and the UCSB Geography department for supporting this endeavor.