Plants send electrical signals through living tissue, and startup Electric Plant is developing sensors and an AI model to interpret them. The company says the information could give growers a closer view of plant needs and help guide decisions about water and fertilizer.
A discovery that sparked a company
Electric Plant co-founder and CEO Justin Mast began exploring plant signals after reading about a houseplant connected to a motorized stand. When the plant sought more light, electrical activity in its tissues was detected by a control board, which moved the plant toward the light source.
Mast partnered with neuroscientist Lee von Kraus, who has worked with DARPA, to start the company. Over the past three years, Electric Plant has gathered data for Bombadil, its model for interpreting electrical signals traveling through plant stems.
The founders envision a future in which people can communicate with plants. For now, the idea is less about sending instructions and more about understanding what plants are signaling. As Mast put it, “We’re listening more than we’re speaking, but listening’s the first step.”
How the sensors gather information
Electric Plant’s sensors are roughly the size of a regular iPhone folded lengthwise. Stainless steel screws attach each sensor to a plant and penetrate the cambium, the living tissue just beneath the bark, allowing it to detect tiny changes measured in microvolts.
The collected data travels to a base station over a low-power wireless network. Bombadil processes it in the cloud, then sends results back to customers, who could use them to adjust watering or fertilizer schedules.
Mast says the company needs only a couple of sensors per acre to produce accurate results. That could make the system practical for monitoring larger growing areas, although the source does not identify Electric Plant’s initial customers.
Building a model across plant species
Bombadil can interpret electrical signals in about 125 different species, according to Mast. The range includes ferns, redwoods, tomatoes and dahlias, spanning very different plant forms.
To train the model, Electric Plant first used information from existing tools, including soil probes, handheld spectroscopes and satellite imagery. Those methods can help growers assess conditions, but Mast argues they offer limited insight into what is happening inside a plant in real time.
He says Bombadil will eventually outperform much of that equipment. The company also says its sensors cost tens of dollars, compared with existing tools that generally cost thousands. Those are claims from the company; the article does not provide independent performance comparisons.
Potential benefits and open questions
More direct information about plant needs could help growers make more targeted decisions. Mast claims the system can increase yields while reducing water use by 20% or more. The article does not provide trial details or explain how those results vary across crops or growing conditions.
Electric Plant recently raised a $11.2 million seed round led by Onto Ventures and Climactic. Ponderosa, Endeavor Catalyst, Ludlow, Michigan Rise, The Fund, Schox VC, and Dug Song also participated.
The company’s technology is aimed at agriculture and forestry, though Mast did not disclose its initial customers. Its next challenge is turning a broad model of plant electrical activity into reliable guidance that growers can use in day-to-day decisions.