Harvesting Data Helps Farms Grow Yields
Matt Schweigert owns 7,000 acres of corn and soybean fields in Cuba City, Wisconsin. His 25 tractors, combines, and other farm machinery are fitted with the latest in agricultural technology: sensors that track GPS location and measure the number of seeds planted, the volume of fertilizer sprayed, and the quantities of harvested ears and beans.
But to use the data, his employees typically glance at displays in the cabs (to spot problems such as poorly spaced seed planting); or they pull out thumb drives from onboard computers to analyze everything later.
In 2013 Schweigert began testing a rubberized, cylindrical gadget made by a Chicago startup called 640Labs. He plugs it into his equipment data ports, and the device automatically transmits data wirelessly to a cloud-based analytics platform.
The platform compares yields in different fields within one farm, how the outputs compared to those from other farms, and what actions—such as the date of planting or fertilizer application levels—might be responsible for the difference. “The vast majority of data literally dies in the field,” says Corbett Kull, cofounder of 640Labs. “The farmer is busy enough trying to manage his farm and drive the tractor, and what we are trying to do is make it easier.”
For farmers, sophisticated weather prediction and data analysis can show what seed to plant on which day, which days to add fertilizer and herbicide, and when to harvest, says David LeZaks, a scientist at the University of Wisconsin, Madison, who researches sustainable agriculture.
“We know pretty quick if a field got overapplied or underapplied with herbicide,” says Schweigert of the 640Labs technology. “Maybe we come back and see if we have adequate weed control. It works the same way for fertilizer. Now we are catching more stuff.”
Last month the agriculture giant Monsanto acquired 640Labs as part of an ongoing effort to invest in agricultural data science. In 2013 Monsanto acquired Climate Corp., a company that has amassed a decade of data on precipitation and soil conditions for 29 million farm fields in the United States. Climate Corp. uses the data to calculate localized weather predictions, and sells insurance against weather-related crop losses. A year before, Monsanto bought Precision Planting, a company that sells very precise planting and related data-recording technology.
“The climate is changing and the challenges are increasing,” says Robert Fraley, chief technology officer of Monsanto. “I believe it is possible we can improve yields on the land we farm today so dramatically [that by] the time 2050 rolls around, we will be able to farm less land.”
Keep Reading
Most Popular
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist
An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work.
The Biggest Questions: What is death?
New neuroscience is challenging our understanding of the dying process—bringing opportunities for the living.
How to fix the internet
If we want online discourse to improve, we need to move beyond the big platforms.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.