For decades, scientists have known that there are ways to measure plant health through the use of multispectral photography. The idea that a plant can tell you something in a picture before you can see it with your eyes was borne out with the launch of the first land-focused satellite system — Landsat 1 — back in 1972. The concept is known as remote sensing, and it gained a lot of early attention.

Mark Johnson wants to beat the United States Department of Agriculture at its own game: predicting yields of America’s crops. The USDA puts boots on the ground, deploying hundreds of workers to survey thousands of farms a month ahead of the October corn harvest, America’s biggest crop. Johnson’s startup, Descartes Labs, has just 20 employees, and they never leave the office in Los Alamos, New Mexico. Instead, Descartes relies on 4 petabytes of satellite imaging data and a machine learning algorithm to figure out how healthy the corn crop is from space.

DE Bondurant Grain Co’s silos have for decades stored wheat, corn and milo grown by farmers in western Kansas. But the recent winter wheat harvest brought something different. “I’m putting wheat on the ground now for the first time in my life,” says Gary Gantz, president of the company his great-grandfather founded in 1888. “I was ready for a large crop, but I wasn’t ready for one of this proportion.”