Researchers from Stanford University recently developed a deep learning-based system that can predict soybean production from satellite imagery.
“Accurate prediction of crop yields in developing countries in advance of harvest time is central to preventing famine, improving food security, and sustainable development of agriculture,” the researchers stated in their paper. “Existing techniques are expensive and difficult to scale as they require locally collected survey data. Approaches utilizing remotely sensed data, such as satellite imagery, potentially provide a cheap, equally effective alternative.”
What makes this system unique is that the neural network predicted crop yield in Argentina and Brazil but was only trained on data from the United States, which is readily more available, the researchers said.
“Our work shows promising results in predicting soybean crop yields in Argentina using deep learning techniques. We also achieve satisfactory results with a transfer learning approach to predict Brazil soybean harvests with a smaller amount of data,” the researchers stated. “The ability to improve predictive performance in regions with limited data by using transfer learning is exciting because these regions especially stand to benefit from a cheap, reliable crop prediction tool,” the team explained.
The researchers say they will expand the application of this approach to new regions in the developing world.
The research was recently published in the ACM Digital Library.