Fermata’s CEO shares how the company is using artificial intelligence to improve agriculture

• Valeria Kogan is the CEO of Fermata, a software development company specialized in agriculture.
• Her team is developing AI tools to reduce crop losses that cause food waste and greenhouse gas emissions.
• This article is part of “Build IT,” a series on digital technology trends that are disrupting industries.

This essay, as stated, is based on a conversation with Valeria Kogan, founder and CEO of Fermata. The company develops software for plant and crop monitoring. The following has been edited for length and clarity.

When we think of food waste, we usually think of the scale of not finishing lunch. In reality, agricultural waste is a much bigger problem. An estimated 20% to 40% of crops are lost to pests and diseases, affecting our food systems and the planet; Greenhouse gas emissions from food that is never eaten represents 6% of total emissions.

I didn’t know any of this about five years ago. I was working in bioinformatics, developing an AI-based platform that helps oncologists diagnose cancer, and I knew so little about agriculture that I couldn’t even keep a houseplant alive.

But someone who ran a commercial greenhouse reached out to discuss how AI could solve those crop loss challenges. I quickly saw the opportunity to translate my work in human health care into plant health care and Fermata was born.

Using artificial intelligence and computer vision where humans fail

Today, many farmers try to detect pests and diseases early by sending field workers daily to look at every leaf on every plant for early signs of trouble. But people get tired, distracted, and overlook the small changes that suggest a problem.

It reminded me of the specialists who review x-rays all day and miss early signs of cancer. We use AI image analysis to solve this problem and felt that the same solution could be applied here.

We originally thought about building a robot to move across the fields, but realized we didn’t have the expertise to do that – and that there was a simpler solution.

We developed the Croptimus platform, which uses standard security cameras in greenhouses and fields to photograph each plant several times a day.

Our artificial intelligence processes these images to detect any anomalies. If it does, let the farmers know through our app and suggest what they think is the problem. Using data science, we can also provide an overview of what is happening in a facility overall, whether problems are increasing or decreasing, and whether treatments are working.

With this technology, farmers need less labor and can identify problems earlier than they would with humans, which means they can apply less pesticide. This saves a lot of money and helps produce more sustainable and healthy food.

We do things manually while building the dataset

One of the biggest challenges we had to overcome was establishing the ground truth to build a reliable dataset to train our models on. Every agronomist or crop scientist has his own opinion and will make mistakes. We had to not only compile a decent dataset from scratch, but also build machine learning models that could adapt to mistakes.

I did a few things to help. First, we built a research lab, where we grow plants, infest them with different things, and record them on video. We have also hired an in-house team of agronomists to help us label these images.

In addition, we released our product to the public before it was automated, making identifications manually and encouraging in-app farmers to give us feedback. This helps us understand the problem better and gives us a more robust data set. Even as we move to relying on AI for identification, this feedback loop helps us continually improve our models.

Building relationships to find future possibilities for technology

It’s so important that any technologist trying to solve a problem in an industry new to them—especially more conservative fields like agriculture—stay humble and develop real relationships with the people they hope to help. If I came in as an outsider from the tech industry and told these farmers who have been doing this for decades that I could teach them how to operate and be more efficient, it wouldn’t work.

Instead, I work on building relationships and trust in the industry. I approach it from the perspective of wanting to learn from my customers and understand how my technological knowledge can help them.

Ultimately, this helped me see even more potential in what we do. I learned that there is so much visual data in agriculture, from understanding whether bees are pollinating to how employees treat plants. Fermata’s vision is to build a new layer of visual data in the agricultural industry, helping all stakeholders—from farmers to people who sell fertilizers to pesticide companies—be more efficient.