BELTSVILLE, Md. – A new study by the USDA’s Agricultural Research Service (ARS) and Iowa State University shows the potential for using generative (relating to or capable of production or reproduction) artificial intelligence (AI) to help reduce cattle methane gas emissions.

The study said these gas emissions account for about 33 percent of U.S. agriculture, and 3 percent of total U.S. greenhouse gas emissions.

Simon Liu, ARS administrator, said developing solutions to address methane emissions from animal agriculture is a critical priority.

“Our scientists continue to use innovative and data-driven strategies to help cattle producers achieve emission reduction goals that will safeguard the environment and promote a more sustainable future for agriculture,” he said.

The study said one of these innovative solutions starts in the cow’s stomach, where microorganisms contribute to enteric fermentation and cause cows to belch methane as part of normal digestion processes.

The study added that the team of scientists found a group of compound molecules capable of inhibiting methane production in the largest of the cow’s four stomach compartments, the rumen (the cow’s first stomach), which can be tested to help mitigate methane emissions.

Researchers said one molecule, bromoform, which is naturally found in seaweed, has been identified by the scientific community to demonstrate properties that can result in reducing cattle enteric (relating to, or affecting the intestines) methane production by 80-98 percent when fed to cattle.

Unfortunately, the study said, bromoform is known to be a carcinogen, limiting its potential use in cattle for food safety reasons. Therefore, scientists continue to search for molecules with similar potential to inhibit enteric methane. However, this type of research presents challenges of being especially time-consuming and expensive.

The study said researchers combined generative AI with large computational models to jump start the quest for bromoform-like molecules that can do the same job without toxicity.

“We are using advanced molecular simulations and AI to identify novel methane inhibitors based on the properties of previously investigated inhibitors (like bromoform), but that are safe, scalable, and have a large potential to inhibit methane emissions,” said Matthew Beck, a research animal scientist working with ARS at the time the study was completed, and is now with Texas A&M University Department of Animal Science.

“Iowa State University is leading the computer simulation and AI work, while the USDA-ARS is taking the lead in identifying compounds and truth testing them using a combination of in-vitro (laboratory) and in-vivo (live cattle) studies,” he said.

The study said AI, along with these models, was used to predict the behavior of molecules, and to identify those that can be further tested in a laboratory.

Researchers said AI can play a significant role in understanding how known molecules interact with both proteins and the microbial community of the rumen, and thereby discover novel molecules and potentially key interactions within the rumen microbiome (microbial communities living within, and on, animals).

Jacek Koziel, RS research leader, said this type of predictive modeling can be particularly helpful for animal nutritionists.

“There are other promising strategies currently available to mitigate enteric methane emissions, but the available solutions are relatively limited,” he said.

Researchers said the study was also conducted to show an estimate of potential costs and foreseeable pitfalls of this research. This estimate can be used to guide decision-making on investments for this type of research to be done entirely in a laboratory.

Andrew P. Griffith, University of Tennessee professor of agricultural and resource economics, said, “It appears this team is using AI to speed up the process of finding a solution such that they do not have to laboratory test every single molecule. The assumption of speeding up the process would stem from the thought that the degree of error in the AI model they are working with is fairly low.

“However, the AI system may overlook some molecules that may actually do the job if it is not calibrated correctly, or does not have the correct information to work from,” he added. “Thus, there is some potential it slows down the process due to overlooking molecules that may be a good candidate to reduce methane output.”

When asked how economically feasible generative AI would be for cattle producers, he said, “The good thing about this study is that it is not something where cattlemen are expected to use AI, but rather use something that may be found in the future with the help of AI technology.

“More broadly speaking, research and development are always expensive, and the use of the technologies in production agriculture rarely makes sense until the cost of the technology can be significantly reduced from these early-stage costs. Thus, I fully expect AI to benefit cattle producers moving forward, and it will likely contribute to profitability as technology costs decrease.”