Electric Plant’s AI Model Aims to Decode Plants’ Electrical Signals

Electric Plant has built an AI-powered translator meant to help humans interpret the subtle electricity moving through plant stems. Its model, called Bombadil, is designed to relay details about a plant’s needs to growers.

The company was founded by Justin Mast and Lee von Kraus after Mast encountered research involving a houseplant wired to a motorized stand that moved toward light based on electrical signals.

Electric Plant’s sensors attach to plants with stainless steel screws that reach the cambium, the living layer just under bark, to detect microvolt changes inside the plant. Data moves from the sensors to a base station over a low-power wireless network.

Bombadil interprets the data in the cloud and sends results back to customers. Growers could then use the information to adjust watering or fertilizer schedules, according to the TechCrunch report.

The company says Bombadil can interpret electrical signals across about 125 plant species, including ferns, redwoods, tomatoes, and dahlias. Mast told TechCrunch the model was trained using existing tools such as soil probes, handheld spectroscopes, and satellite imagery.

Electric Plant says its sensors cost “tens of dollars,” while existing tools generally cost thousands. Mast also claims the system can boost yields while reducing water use by 20% or more.

Electric Plant raised an $11.2 million seed round led by Onto Ventures and Climactic, with participation from Ponderosa, Endeavor Catalyst, Ludlow, Michigan Rise, The Fund, Schox VC, and Dug Song. The company plans to use the funding to bring its sensors and Bombadil to market.

Mast did not disclose Electric Plant’s initial customers. TechCrunch notes that agriculture and forestry are easy areas to imagine for the technology’s applications.