AI Model Maps Hidden Animal Feeding Operations to Tackle Water Pollution

Scientists have built an AI-powered model to locate hidden animal feeding operations, a crucial step in curbing water pollution and improving environmental management. With 87% accuracy, this breakthrough offers a powerful tool for policymakers and farmers alike.

Research: Machine learning-based identification of animal feeding operations in the United States on a parcel-scale. Image Credit: Valdis Skudre / Shutterstock

Understanding where farm animals are raised is crucial for managing their environmental impacts and developing technological solutions, but data gaps often make it challenging to get the full picture.

Becca Muenich, a biological and agricultural engineering researcher, set out to fill the gap by developing a new technique for mapping animal feeding operations.

Without proper control strategies, the waste generated by these operations can pose significant ecological harm, Muenich said, such as surface water contamination with excess phosphorus and nitrogen. Animal feeding operations are defined as facilities that feed animals for at least 45 days per year in a confined area that does not grow grass or forage. For Muenich, a water quality engineer who focuses on how water moves through landscapes and how it can pollute areas by picking up and moving toxic materials, this issue piqued her interest.

"We can't really address something if we don't know where the problem is," said Muenich, an associate professor with the College of Engineering at the University of Arkansas and researcher for the Arkansas Agricultural Experiment Station, the research arm of the University of Arkansas System Division of Agriculture.

"We don't have a good nationwide - even at many state levels - understanding of where livestock are in the landscape, which really hinders our ability to do some of the studies that I was interested in," she said.

Muenich said these feeding operations have risen in response to the increasing population size and global demand for livestock products.

Considering key predictors of feeding operation presence, such as surface temperature, phosphorus levels, and surrounding vegetation, Muenich's team built a machine learning model that can predict the location of feeding operation locations without using aerial images. Machine learning models are a type of computer program that can use algorithms to make predictions based on data patterns.

The model was developed using data from 18 U.S. states, which were divided into individual parcels based on ownership. When tested against a dataset of known animal feeding operations, the model predicted their location with an accuracy of 87 percent.

The study, "Machine learning-based identification of animal feeding operations in the United States on a parcel-scale," was published in the journal Science of the Total Environment in January.

Filling in the gaps

Muenich said previous attempts to identify animal feeding operations have often relied on aerial images. However, livestock facilities usually look different between states and by animal, so she and her team aimed to employ further strategies.

She explained the lack of understanding surrounding livestock locations often comes from differences in how states interpret the Clean Water Act, which requires farms classified as "concentrated animal feeding operations" to get permits through the National Pollutant Discharge Elimination System. These facilities are a type of animal feeding operation with more than 1,000 animal units.

Despite the national regulation, states administer this permitting differently, leading to differences in available data.

For example, Muenich built a watershed model in an area between Michigan and Ohio that included multiple feeding operations. Due to the state's permitting requirements, data was readily available through Michigan's pollutant elimination system. However, the same data wasn't available for the same operations in Ohio, which led Muenich down this path of investigation.

Muenich said that advancing towards better livestock accounting can help develop strategies that can improve the environmental outcomes of livestock management while creating economic opportunities for farmers by scaling up technologies to combat animal waste. She explained that scaling these technologies in economically feasible ways requires knowledge of where livestock are most prevalent and spatially connected.

The study's coauthors included Arghajeet Saha, formerly a postdoctoral researcher at the University of Arkansas and currently an assistant scientist with the Kansas Geological Survey; Barira Rashid, a Ph.D. student at the University of Arkansas; Ting Liu, a research associate with the University of Arkansas biological and agricultural engineering department; and Lorrayne Miralha, an assistant professor with Ohio State University's department of food, agricultural, and biological engineering.

The Science and Technologies for Phosphorus Sustainability Center supported the research under National Science Foundation award number CBET-2019435. The data used in the research came from Regrid's Data with Purpose program, a source of nationwide land parcel data.