Geological Society of America

237 Challenges and Solutions for a Changing Climate: New Directions for GSA

Friday, 30 October 2020
10:00 AM - 2:00 PM
Auditorium

USING SATELLITES AND MACHINE LEARNING TO ENHANCE AND PROTECT FOOD SECURITY IN AFRICA

Paper number: 237-17
Program: Technical Sessions
Time: 12:25 PM – 12:30 PM

Authors

Catherine Nakalembe Presenting Author
University of Maryland Geographical Sciences, College Park, MD
Inbal Becker-Reshef
University of Maryland, College Park, MD
Hannah Kerner
University of Maryland, College Park, MD
Ritvik Sahajpal
University of Maryland, College Park, MD
Sergii Skakun
University of Maryland, College Park, MD

Abstract

When combined with data collected on the ground at farms, satellite Earth Observations (EO) data show what types of food crops are growing where and how they are doing as the growing season progresses. By comparing data from satellite images with reported crop yields from previous years, analysts can estimate how much food will likely be produced in a season. Combining satellite and ground data with climate information and weather forecasts enables us to forecast food production and get early warnings of potential crop failure from drought, floods, disease, and even pest infestations like the current 1 in 70-year locust invasion. This early warning gives organizations who respond to food insecurity more time to prepare and even mitigate shortages and famine altogether. Open data, machine learning, cloud computing and big data analytics are revolutionizing EO capabilities filling critical gaps in data even in the smallholder context. This presentation will summarize what satellite EO with machine learning offers today to support decisions that impact on smallholder farmers in sub-saharan Africa who face even more challenges and risk to agricultural productivity with climate change.

Geological Society of America Abstracts with Programs. Vol. 52, No. 6

doi: 10.1130/abs/2020AM-357128

© Copyright 2020 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.