Washington University at St. Louis Deciphering Decisions: Using digital tools to help farmers plant the right seeds

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 

Retaking The Field Volume 4 “Retaking the Field: Science Breakthroughs for Thriving Farms and a Healthier Nation” is a collaborative report from 20 FedByScience universities and the SoAR Foundation. The report highlights research projects in the five Science Breakthroughs areas identified as the most important fields to advance in agriculture by the year 2030: genomics, microbiomes, sensors, data and informatics, and transdisciplinary research. View The Issue
Retaking the Field Volume 4: Science Breakthroughs for Thriving Farms and a Healthier Nation Click to download report

More Stories from the community

Boosting Bees: Improving bee health to benefit farmers

Because pollinators are critical for the production of most berry crops, Dr. Isaacs and his transdisciplinary team investigate pollinator ecology and management, economic value, and benefits for agriculture. The group includes researchers experienced in honeybee management, wild bee ecology, and pest management.

Read More
Helping Hearts: Discovering the Impacts of Flavonoids and Interpersonal Gut Variations to Improve Cardiovascular Health

The American Heart Association notes a recent study that showed millions of people worldwide could prevent early deaths and disability from heart disease by eating more fruits and vegetables. Some health benefits associated with this diet are derived from pigments present in plants called flavonoids. Dr. Federico Rey and his team studies how flavanoids can improve human health.

Read More
Raising Resilient Pigs

Through cutting-edge genome editing, scientists are working to help the swine (pig) industry produce healthier, more resilient animals. Genome editors are enzymes that allow scientists to cut the DNA strands in cells at a specific position and introduce very precise genetic changes. With funding from USDA, scientists at Iowa State University and Kansas State University have discovered a genetic marker in pigs that is associated with resistance to porcine reproductive and respiratory syndrome (PRRS).

Read More