The AI farm experiment

Article Posted on May 3, 2018

By: Alison Snyder, Axios

Major companies are bringing together new machine learning algorithms, better and cheaper sensors, and increased computing power in hopes of addressing growing global demand for food and agriculture's diminishing labor force.

The big picture: Alphabet's X and John Deere, startups and universities are looking to AI-based agriculture to address these problems. But farming presents hard problems for AI that, if solved, could ultimately help it be deployed in more structured places (think: homes).

Show less

What's happening now

"We are at the stage where maybe Henry Ford was in the early 19th century with farm automation. There will be a lot of incremental advances that will snowball into massive changes."

— University of Illinois' Girish Chowdhary

Machine learning is used to analyze data collected from farmers' fields, satellites and drones and inform decisions about planting and fertilizing, to spot disease, and to try to predict crop yields.

  • For example, growers using The Climate Corporation's Climate FieldView tool (to decide the rate, density and location for planting corn) saw a 5-bushel-per-acre lift in 2017 compared to farmers who wrote their own planting plans, says Steven Ward, the company's director of geospatial sciences.

On the ground: AI-enabled equipment is on the market and under development.

  • John Deere combines come with an option that uses machine learning to coordinate their spouts with grain-collecting carts to minimize spillage. Another model uses it to assess the quality of grain going into the bin— though still with human oversight.
  • Fruits and vegetables are more difficult and labor-intensive crops to harvest. Harvest CROO Robotics is working on a strawberry picker that recognizes and picks ripe fruit — with limited success. "We really take for granted how good humans are at performing fine manipulation tasks. Our bodies provide us with a rich set of data about our environment, and our brains synergistically fuse this sight, touch, smell, and sound with prior experience in a way we're still struggling to understand," Carnegie Mellon University's Tim Mueller-Sim says.
  • Chowdhary developed and is testing a robot that can move through rows of plants and use computer vision to measure their height and stem width.
  • If precise, that information could be used by breeders to speed and standardize the process of screening thousands of plants in search of genetic combinations that give rise to desirable traits….

Click here to view original article