Feb. 13 (UPI) -- Researchers at Stanford University have developed a new method for accurately measuring crop yields using satellite images. Scientists hope their new strategy will help researchers track agricultural productivity in developing countries where farming data is limited.
"Improving agricultural productivity is going to be one of the main ways to reduce hunger and improve livelihoods in poor parts of the world," Marshall Burke, an assistant professor of earth and environmental sciences at Stanford, said in a news release. "But to improve agricultural productivity, we first have to measure it, and unfortunately this isn't done on most farms around the world."
Until recently, the resolution of satellite images wasn't sufficient for the kind of analysis proposed by Burke and his colleagues. Now, satellites the size of a toaster can take and send high-resolution photographs of Earth's surface.
"You can get lots of them up there, all capturing very small parts of the land surface at very high resolution," said David Lobell, an associate professor of earth sciences. "Any one satellite doesn't give you very much information, but the constellation of them actually means that you're covering most of the world at very high resolution and at very low cost. That's something we never really had even a few years ago."
Researchers tested their crop yield prediction strategy in Western Kenya where small farms are plentiful. They combined on-the-ground field work, meeting and interviewing local farmers, with a model designed to interpret satellite images. The model uses local weather conditions and an understanding of how crops develop to predict yields based on satellite images.
Scientists used their field work to verify the accuracy of their new model, described in the journal PNAS.
"Just combining the imagery with computer-based crop models allows us to make surprisingly accurate predictions, just based on the imagery alone, of actual productivity on the field," Burke concluded.
Turkey and Lobell are now working on scaling up their predictive model to measure yields in other parts of Africa.