RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
Temple, D. S., Polly, J. S., Hegarty-Craver, M., Rineer, J. I., Lapidus, D., Austin, K., Woodward, K. P., & Beach, R. H. (2019). The view from above: Satellites inform decision-making for food security. RTI Press. RTI Press Research Brief No. RB-0021-1908 https://doi.org/10.3768/rtipress.2019.rb.0021.1908
Images acquired by sensors placed on satellites provide valuable information on crop acreage, health, and yields.
Recent progress in artificial intelligence and high-performance computing makes it possible to obtain agricultural information at low cost and in near-to-real time.
Unmanned aerial vehicles lessen the burden for ground-truth data collection required for satellite image classification.
Continuous public and commercial support for improvements in the satellite infrastructure and in the development of robust models for information extraction will pay dividends for food security and sustainability.
Abstract
Despite notable progress in reducing global poverty and hunger in recent decades, about one out of nine people in the world suffers from hunger and malnutrition. Stakeholders charged with making decisions pertaining to agricultural production, development priorities, and policies at a region-to-country scale require quantitative and up-to-date information on the types of crops being cultivated, the acreage under cultivation, and crop yields. However, many low- and middle-income countries lack the infrastructure and resources for frequent and extensive agricultural field surveys to obtain this information. Technology supports a change of paradigm. Traditional methods of obtaining agricultural information through field surveys are increasingly being augmented by images of the Earth acquired through sensors placed on satellites. The continued improvement in the resolution of satellite images, the establishment of open-access infrastructure for processing of the images, and the recent revolutionary progress in artificial intelligence make it feasible to obtain the information at low cost and in near-to-real time. In this brief, we discuss the use of satellite images to provide information about agricultural production in low-income countries, and we comment on research challenges and opportunities. We highlight the near-term potential of the methodology in the context of Rwanda, a country in sub-Saharan Africa whose government has recognized early the value of information technology in its strategic planning for food security and sustainability.