Sustainable agriculture has an unlikely ally: satellites

the race to remove COtwo of our atmosphere is on. In an effort to reduce carbon on a significant scale, people look to the ground. The top meter of the world’s soil contains more than three times the amount of carbon currently in our atmosphere, and if we treat our land better, it could absorb even more.

This is good news for farmers. Companies and individuals desperate to offset their emissions by purchasing carbon credits are willing to pay farmers to use sustainable farming practices and capture carbon in their fields. The problem? The process of checking whether a field has absorbed additional carbon is not easy: physical samples must be collected regularly from across the field and sent to a laboratory for processing.

Enter Perennial, a Boulder, Colorado-based startup that claims to have the answer. While studying at Brown University, Chief Innovation Officer David Schurman met CEO Jack Roswell and President Oleksiy “Alex” Zhuk, passionate engineers from family farms in Michigan and Ukraine, respectively. When they got to Brown, they were surprised to find that “technologists had essentially forgotten agriculture as a whole,” says Zhuk. Today, its ambition is to produce “the infrastructure that supports the entire vertical of the soil carbon market,” says Roswell. “No technology solves a problem unless it does it at scale and in a cost-effective way,” says Roswell. “We are actively monitoring every field for carbon removal and net emissions, in the US and beyond.”

Jim Kellner, a professor at Brown University and Perennial’s chief scientist, explains that the company’s technology is based on multispectral satellite imagery. This means measuring light reflected from Earth in narrow bands across a wide range of the electromagnetic spectrum, capturing information that is invisible to the human eye. Kellner says that analyzing the spectrum of reflected light allows accurate identification of soil carbon, even using satellite imagery with a spatial resolution of just 10 meters. By comparing the amount of reflected light at different wavelengths, “you can learn to identify materials, even without the image,” he says.

The satellite images are fed into a machine learning algorithm, along with environmental data about the field in question, such as elevation and climate, to produce a measurement of soil carbon content. To accurately train the algorithm, the team collected thousands of soil samples, digging holes in fields across the US to calibrate their models for different weather conditions and crop types. By training their model on these representative physical measurements, the team allowed the algorithm to remotely quantify carbon in the soil. The company sees this as a critical step in unlocking the soil carbon market. “If you solve the problem of quantifying carbon but it depends on sending someone out into the field with a stake or a shovel, you’re not going to reach a global scale,” says Zhuk.

That’s all very well, but are farmers really willing to adopt sustainable farming practices and change the way they grow food? Zhuk believes the answer is yes. Against the backdrop of severe soil erosion around the world and rising farm chemical prices, he hopes Perennial will give farmers the financial boost they need to move away from environmentally damaging practices. and restore their lands. “Our approach produces a standard measure anywhere in the world: a farmer in Ethiopia who puts a ton of carbon in the soil will be recognized and paid the same as one in Iowa, across borders and inconsistent verification standards,” he says.

Right now, the company is working on training its algorithms in new countries and continents, as well as tackling new types of terrain, such as pastures and grasslands, in addition to crop fields. Zhuk’s goal? “Moving agriculture from just an industry that feeds us to an industry that makes a major contribution to offsetting our emissions and reversing climate change.”

Leave a Reply

Your email address will not be published. Required fields are marked *