Google is launching pilot programs in the states of Telangana and Maharashtra to test the precision of its artificial intelligence-driven innovation AnthroKrishi.

It is backed by an artificial intelligence model capable of detecting field boundaries and water boundaries to enable eco-friendly farming practices and boost crop yields. It's not just about bringing these solutions to the whole country, but also to Asia and beyond.

AnthroKrishi employs artificial intelligence to analyze satellite images to trace the boundaries of individual farms and keep tabs on crops, yields, and farming activities.

The capability provides a wealth of information to support more efficient farming, from banks offering loans based on anticipated yields to governments enhancing support programs.

Manish Gupta, Head, Google Research APAC says, “We've done pilots with the state of Telangana where they have given us feedback of where there are some mistakes, (here's where) there is some over segmentation or under segmentation that's been done, but for the most part, it validated that the models were fairly accurate.”

Gupta says that the search giant has also been undertaking a pilot project in Maharashtra with IIT Bombay, where it is collaborating with the Department of Land Records to see if usage-based patterns provide adequate information about the ownership of farms.

“There is a lot of ground truth data in India, but it tends to be very noisy, which is one of the foremost challenges when it comes to this project. There were a lot of errors when the team looked at the data from some state government’s annual survey,” says Gupta.

Gupta says, “Once each farm has been identified, the next thing to be done is to identify what are the crops which are being grown as well as monitor various farming related activities like sowing of seeds, harvesting and so on.”