Today, farmers are inundated with seed choices for annual planting. They must choose from hundreds of varieties that have been optimized by seed companies to succeed in specific conditions. For example, one seed might be very good for early planting but not as high-yielding if rain delays planting. Others offer improved resistance to pests or require less water to grow.
Researchers at Washington University in St. Louis are using machine learning to help farmers make informed planting decisions. The computational models allow farmers to receive the top five recommendations for seeds in a given season based on average yields, weather conditions, and soil on their farms.
Dr. Dong and Dr. Sundaramoorthi built the web program called SimSoy to help farmers utilize complex data and algorithms in an easy-to-use tool. It was created with soybeans as a test crop but the technology can be used on any farm across a wide variety of crops.
The team leveraged big data from seed companies. This provided tens of thousands of data points, which was multiplied by the 182 seed varieties, and the 1,000 simulations of weather predictions at each target site.
Using machine-learning simulations, researchers developed usable models that could be integrated into a web-based application. The team boiled down the tool to a 27-question form that includes location, soybean varieties, irrigation, soil types, acreage, and yields.
This computational model tailors recommendations to help farmers thrive by removing the guesswork during the planting season and improving crop yields based on variable planting conditions.
“We are intrigued by the opportunity to help farmers around the world, who often have limited access to, and the knowledge of, processing the big data. This way, we can make the best use of what agricultural science offers.”
– Lingxiu Dong