Editor’s Note: This post about Ceres Imaging was originally published on the now-defunct All Turtles blog in June 2018. You can read other articles I’ve written for that site here.
In the United States, much of the food is produced by 75 percent of the country’s farms, but this group grosses only $50,000 a year. The big question is how can these farmers improve the quality of their crops and maximize their profits and the answer rests in better understanding the land and soil. To ensure a successful harvest, farmers need to consider a host of factors like soil quality, temperature, and potential diseases. You might not think this is something artificial intelligence could help solve, but it’s a challenge Ceres Imaging wants to solve.
The company specializes in providing farmers aerial images of their land, using sensors to gather data on how healthy it is by examining wavelengths. Equipping contracted airplanes with its proprietary cameras (Ceres did try with drones but found it wasn’t able to sustain the weight of its cameras), it’s able to survey crops and provide farmers with a better understanding of where problem areas lie on their property, detect stress points, and anything else that might not immediately be recognizable initially by the naked eye.
“We’re more than putting a camera on a plane, but about data collection and how you deliver that to farmers,” Ceres chief executive and founder Ashwin Madgavkar tells me in an interview. “Our original thesis is around wavelengths and what types of data can be processed in order to create a repeatable process to generate returns to farmers.”
Farming With Better Data
For five years, he’s been building Ceres, the brainchild of his experiences not only as an electrical engineer, but also as a consultant helping energy companies explore clean tech, his time in South America working in agriculture, studying sustainability, and observing his Stanford professors use “novel techniques” like NASA sensors to gather data. “Working in South America gave me first-hand experience on the challenges farmers face. Existing imagery technology wouldn’t necessarily work,” he explains.
Farmers enroll in Ceres through a subscription service, uploading maps of their property, or any other area that they’d want to survey, such as neighbors or even competitors. It’s feasible to monitor other areas if farmers are willing to pay for it, to gauge whether issues come from neighboring crops or for other competitive reasons. A Ceres spokesperson tells me that others might use it to assess properties ahead of making buying decisions and since planes are flying at a high enough altitude, there’s no issue around privacy rights.
The company’s algorithm determines flight schedules, which farms will be scanned, and the flight plan to take. Madgavkar shares that four years of ground maps from across different universities and Ceres’ data have been used to train the AI. It has an algorithmic model similar to that of Uber, matching rented planes and fields together—Ceres does not own any planes.
“If we do a flight above a field and based on the models we’ve built, we can detect stress points or a lack thereof. Those stress points are often points of emerging diseases that we can see before the naked eye can. With a vineyard or orchard, we can detect water content and a linear line, which often is a broken drip line,” he says. “When you’re managing a field, you have hundreds of thousands of plants. It’s easy to see problems with one plant, but hard to know for the rest. The result is that people miss the bigger issues.
Ceres primarily works with large farms, described as professional enterprises, agriculture businesses, and retailers. Madgavkar wouldn’t disclose specifics but said that the company works with “hundreds of individual farms, covering hundreds of thousands of different acres” and its customers are mostly in the U.S., but it is operating in Australia. Initially, Ceres is working with vineyards and orchards, specialty crops that have a higher margin but make up a smaller percentage of total farms in the market.
AgTech Getting Competitive
If Ceres’ performance thus far is any indication, there’s an opportunity for solving agriculture problems using AI and machine learning. The company announced on Thursday that it’s raised $25 million in new capital through a round led by Insight Venture Partners, bringing its total fundraising effort to $31 million. Madgavkar tells me that the new investment will let Ceres expand into new crops, namely corn, soy, and wheat, which make up 75 percent of global farmland, and also expand its operations both domestically and internationally. Eventually, he hopes to fly over non-farm land to be able to warn farm customers of potential dangers nearby.
He’s not alone in thinking technology has an opportunity to improve the agriculture industry. More than $800 million has been raised by AI and robot startups targeting this space from 2012 to 2017, according to CB Insights, with focuses on making planting crops more efficient, satellite imagery by drone, predictive analytics, and more. Focused on imagery, Ceres isn’t in a class of its own, contrary to what Madgavkar tells me—he believes the competition is the “status quo” and “90 percent of farmers don’t use imagery.”
The truth though is Ceres is likely competing against a combination of satellite imagery startups like Descartes Lab, FarmShots, OmniEarth, and Orbital Insight; and in-field monitoring companies like Agri Eye, DJI Innovations, Gamaya, and others. But armed with new capital, Ceres’ differentiator might be the ability to combine all of these technologies into a single solution farmers might prefer and understand without breaking the bank.
“Farmers are quite high-tech when it comes to biological and chemical models they use, but they haven’t embraced technology,” Madgavkar shares. “Everyone has a smartphone and is keen to be mobile. We make it easy to digest the data if you’re mobile, but also make it easy to check on the web.”