AI Model Advances Scientific Discovery With Soil Carbon Research

Jul 28, 2026

A new computer model from Cornell University researchers is one of the first artificial intelligence tools to advance scientific discovery in agriculture and biogeochemistry and is 50 times more efficient than its predecessors.

In a paper published in the journal Geoscientific Model Development, the researchers demonstrated the AI on processes behind the important issue of soil organic carbon, as the Earth’s soils hold roughly three-quarters of the world’s terrestrial carbon and more carbon than the atmosphere and all the world’s plants combined.

Scientists have been exploring ways to use AI for research purposes, but most common AI tools, such as ChatGPT, mainly repurpose existing information. Researchers have also used AI to extract patterns from data. But the new model, called the Biogeochemistry-Informed Neural Network (BINN) goes a step further by predicting biological processes that are not yet well understood and suggesting factors that control them.

“BINN is very easy to use and can be democratized among the scientific community in various disciplines,” said Yiqi Luo, the senior author of the study. “This is one of the first tools of this type that can promote scientific research with AI.”

Soil scientists know the mechanisms by which soils acquire organic carbon – plants extract and sequester carbon from carbon dioxide to grow, and when those plants die, organic matter from stems, leaves and roots decompose into smaller and smaller bits to become part of the earth. But what is not well known are the speed of these processes and how many such processes are required to break down the litter.

“We use AI and data to tell us quantitatively how fast and how many of these kinds of processes are required,” said Haodi Xu, a doctoral student in Luo’s lab, and co-first author of the study.

Click here to see more...

Video: From Students to Solutions | On The Brink: Season 2, Episode 14

Ask Canada’s most decorated soybean breeder his favourite part of the job and he doesn’t name a single variety. He names the students.

Istvan Rajcan is a professor of soybean breeding and genetics in the Department of Plant Agriculture at the University of Guelph, where he has run the soybean breeding program for 28 and a half years. In that time he has developed 87 soybean cultivars, published 140 refereed papers and trained 51 graduate students. In 2025 he received the Public Sector Impact Award from the National Association for Plant Breeding.

He is also worried. In this episode he says Canada is at a crossroads, pointing to recent government cuts to plant breeding programs and to the facilities that support them. His prescription is structural. "Plant breeding funding formula has to be a long-term one," he says.

The formula he is defending is the public-private matching arrangement his program runs on. Private seed companies fund the work, provincial or federal money matches it, and the combined pool stretches each dollar further than either source could alone. At the National Association for Plant Breeding annual meeting in June, he says American public breeders were often surprised at how well that collaboration works in Canada.

He also describes how the people entering plant breeding have changed. His early graduate students came mostly from farms. More recently they include, in his words, "city kids who just became excited about genetics."

Topics covered:

Why public-private plant breeding funding in Canada needs a long-term

commitment rather than a larger one

How matching private seed company investment with provincial and federal

dollars multiplies research capacity

How the graduate student pipeline into plant breeding has shifted from

farm kids to city kids