Farming used to be about luck. And until the invention of nitrogen-based fertilizers, which allowed the average farmer to get nearly twice as much food out of the ground, bad luck could spell disaster, maybe even death. Those dark days seem to be behind us. But the explosive reproductive power of humans means our population could reach 11 billion people within the next century. And as cities continue to carve away at available farmland, that means we’ll need to feed essentially twice the people on half the land. We need to get better at farming, right now.
“Improving agricultural productivity is going to be one of the main ways to reduce hunger and improve livelihoods in poor parts of the world,” says Marshall Burke, an assistant professor of Earth system science at Stanford’s School of Earth, Energy & Environmental Sciences. “But to improve agricultural productivity, we first have to measure it, and unfortunately this isn’t done on most farms around the world.”
Stanford researchers, in a 2017 project, took advantage of the rise in low-cost, high-resolution satellite imagery — pulled from networks of small, cheap spacecraft called CubeSats — to predict the yield of small, backyard-sized plots of corn in western Kenya. The region had been widely studied in the past, so Burke and his co-author David Lobell were able to compare their predictions to what scientists already knew about these small farms.
“Just combining the imagery with computer-based crop models allows us to make surprisingly accurate predictions, based on the imagery alone, of actual productivity on the field,” Burke said.
Watching crops grow won’t necessarily allow farmers to improve the amount of food they get out of the ground, however. It takes small-scale experimentation that doesn’t require a farmer to risk her crop. So MIT has developed an open-source “Food Computer” that “creates a controlled environment using robotic control systems and actuated climate,” according to a recent paper by Caleb Harper, principal research scientist for the Open Agriculture Initiative at MIT’s Media Lab. Not only will this system allow farmers to experiment on a small scale, it can also allow networks of urban farmers — growing vertical plots of food inside buildings, for instance — to refine the perfect recipe for raising crops in their particular city.
Meanwhile, technology is making existing farms that much more productive. Chilean researchers managed to raise blueberries using just 30% of the typical amount of water thanks to wireless sensors that helped them optimize irrigation. Japanese farms regularly use drones to image fields, detect pest outbreaks, and spray crops. And even classic companies like farm-machinery manufacturer John Deere are building networked tractors that can follow precise instructions about seed spacing, fertilizer depth, and the amount of produce to harvest at any one time.
In other industries, technological innovations just improve on already highly efficient systems. But as farming is tasked with feeding so many more mouths — literally keeping the human race alive — it will have to be as coordinated and productive as possible.
Photo thanks to NASA on Unsplash