Electric Plant raises $11.2M to decode plant signals with AI model Bombadil

The company was founded by Justin Mast and Lee von Kraus, a neuroscientist who has worked with DARPA. For the past three years, Electric Plant has been collecting data to build Bombadil, a large language model designed to interpret subtle electrical signals coursing through a plant’s stem and relay details about the plant’s needs to growers. Mast is co-founder and CEO.

Mast said his interest began years ago when he read scientific literature about a houseplant wired to a motorized stand. When the plant wanted more light, electrical signals flowed through its living tissues; a control board sensed the current and moved the plant closer to the light. “I’m like, what the heck?” Mast told TechCrunch. “That was the entry to the rabbit hole for me.”

The founders believe the model could one day lead to a tool that lets people “speak” to plants. “We’re listening more than we’re speaking, but listening’s the first step,” Mast said.

Electric Plant says growers lack full visibility into what plants require even in controlled greenhouses. Farmers, growers and foresters have traditionally relied on tools that react to plants’ demands for water, nutrients or light. Soil probes, handheld spectroscopes and satellite imagery work well enough but leave much to be desired, Mast said.

“That technology is sophisticated, but its ability to get at the inside of the plant isn’t very sophisticated,” he said. “Most of that stuff still lags quite a bit behind the real-time needs of the plant.”

Electric Plant used those devices to train Bombadil, which can interpret electrical signals in about 125 species, according to TechCrunch. “We know the model will surpass a lot of that equipment,” Mast said.

The startup’s sensors are also significantly cheaper than existing tools, which generally cost thousands of dollars. “This is tens of dollars,” Mast said. The sensors are about the size of a regular iPhone folded lengthwise and are attached to a plant using stainless steel screws. The screws must penetrate the cambium, the layer of living tissue just under the bark, to connect to microvolt changes occurring within the plant. Data from the sensors is sent to a base station via a low-power wireless network.

Electric Plant only needs a couple of sensors per acre for accurate results, Mast said. Bombadil interprets the data in the cloud, and results are sent back to the customer, who can use them to adjust watering or fertilizer schedules. Mast claims the system can boost yields while reducing water use by 20% or more.

Mast would not disclose Electric Plant’s initial customers. The company sees applications in agriculture and forestry. Bombadil’s first hundred-plus species range from ferns, redwoods and tomatoes to dahlias, Mast said.

“This is the most diverse model ever created on biological electrical signals,” he said. “No one’s ever done anything equivalent to this in the animal world.”