Agriculture wasn’t originally part of Valeria Kogan’s life plan.
The founder and CEO of Fermata, a company using artificial intelligence to help farmers monitor plant health and prevent crop losses sustainably, Kogan’s background in mathematics and biotech led her to apply her expertise to agriculture after seeing the inefficiencies in manual plant scouting.
With a doctorate in bioinformatics, she began as a researcher and later led AI teams at biotech startups across Europe and the U.S. Before Fermata, she co-founded Smartomica, an AI-powered platform assisting oncologists in diagnosing cancer patients. Driven by her passion for using tech to solve critical problems, Kogan moved from cancer labs to farmlands to create Fermata’s Croptimus — a tool she believes can make crop care more efficient, sustainable and profitable for growers worldwide.
While working on solutions for human health, Kogan said someone working in a tomato greenhouse asked about AI and how it could relate to agriculture.
“I was curious, so I decided to go see them, and I was fascinated with commercial food production. When they shared with me the challenges they saw, it became clear that the task technically is very similar to what I had been doing in the medical space,” Kogan said. “So, for Fermata, I started with the idea of taking the technologies already out there [in the industry] and bringing them to help monitor the health of plants. That was five years ago — and here we are.”
Fermata’s proprietary platform, Croptimus, provides greenhouse and field growers with a continuous, 24/7 view of their crops through AI-enhanced monitoring using a simple off-the-shelf camera. By detecting pests and diseases earlier than human scouts, Croptimus reduces the need for costly and environmentally harmful pesticides while boosting yields sustainably, the company says. As agriculture faces a shortage of skilled labor, this round-the-clock AI solution offers consistent, tireless monitoring that learns and adapts over time to each unique crop and environment to deliver accurate, real-time insights, Kogan says.
Basically, Kogan says, the company is solving the problem of plant health.
“Right now, up to 30% of crops are lost due to pests and diseases,” she said. “This is a major source of food waste on the planet, and a substantial source of CO2 emissions as well.”
Manual scouting is the norm, Kogan says, where people walk through greenhouses or fields and look at every single leaf of every plant to identify if something goes wrong.
“Of course, being humans, we’re not built for these sorts of tasks, so Croptimus helps with this task,” she said.
Greenhouse growers purchase security cameras, install them in the greenhouses — about four per acre — Kogan says, then the cameras zoom into every plant and the AI processes the data.
“There are thousands of images that we collect, and it helps identify whether there are any pests, diseases, viruses, nutrient issues ... we have a list of more than 25 things that we are identifying like basic pests, spider mites, thrips diseases, mildew or other fungi or bacterial diseases,” she said. “And if there is something within these classes, then we present that to the grower, and that’s what the growers learns from our app.”
There are three major value proposition points, Kogan says. First is the reduction of labor that a grower needs for the scouting process.
“Our case studies show that up to 50% were able to reduce the amount of human involvement in scouting,” Kogan said.
“The second is the reduction of crop inputs — especially with biological protection being so expensive, and the price is growing,” she added. “It’s really important to know what happened and to localize the problem in time, and then you can save a lot on the crop protection.
“Last but not least is crop losses,” Kogan continued. “We make sure that they don’t get out of hand and there are no significant outbreaks.”
The technology itself is crop agnostic, but Kogan said the company needed to start with something, so it began with greenhouse vegetables.
Kogan says one success story is a grower named Yonathan, who was skeptical and wanted to test the technology.
“We started working with Yonathan and providing him data, she said. “In addition, he also had regular human scouts visit — an external company that comes to him once a week and goes through all the plants and provides him with the report. He was really happy with them, and he didn’t want us.”
Kogan says her company would put the reports together once a week — Croptimus versus the scouts’ reports — and compared them for two months.
“They were absolutely identical,” she said.
Yonathan was still skeptical and wondered why he was continuing with the AI monitoring, but one day Croptimus detected a fungal disease, Kogan says.
“Because he was skeptical, he was sure his team would find it as well, so he didn’t share the data with his team,” she said. “But they didn’t, and the next week they didn’t, or the week after. It took them three weeks to detect the fungal disease. This convinced him of the benefits, and he went from a skeptic to a believer.”
While the company is based in Tel Aviv, the technology is available worldwide, and Kogan recently spent time in Canada meeting with the Greenhouse Growers Association.
Looking toward the future, Kogan thinks two things will happen in the next five to 10 years.
“First is that we’ll add other items on top of pest and disease detection,” she said. “We’re already looking at pests, which means distinguishing them from other insects in the greenhouse. Since we’re tracking insects already, we’ll start tracking the population of pollinators or other beneficial insects. We see several other tasks that can be automated through automation vision too.
“The other direction, with how AI is developing now, using multiple sources of data can help give a more precise answer,” she added. “So, sometimes you can say it’s either this disease or that disease, but if you know what the climate is, it’s like a definitive answer. That’s why we also want to add, later on, the other sources of data to make sure that all our predictions are more accurate because our AI is not just an image, it’s a look at the bigger issue.”
