Plants can speak using electricity, so this startup built an AI model to decipher their language

Electric Plant is using sensors and an AI model to interpret electrical signals inside plants, aiming to give growers a clearer view of what their crops and trees need. The approach could help farmers adjust care in real time, and the startup says it may improve yields while reducing water use.

The company, founded by Justin Mast and neuroscientist Lee von Kraus, has spent three years collecting data for its model, Bombadil, which can interpret signals from about 125 plant species. Its sensors cost tens of dollars, attach to living tissue with stainless steel screws and send readings wirelessly to a cloud service; the company says only a few are needed per acre. Electric Plant has raised an $11.2 million seed round and claims the system could cut water use by 20% or more, though it has not named its initial customers.