Machine learning maps animal feeding operations to improve sustainability
Model predicts presence of animal feeding operations with 87 percent accuracy.
University of Arkansas System Division of Agriculture
image:
Becca Muenich, associate professor of biological and agricultural engineering.
view moreCredit: U of A System Division of Agriculture photo.
FAYETTEVILLE, Ark. — Understanding where farm animals are raised is crucial for managing their environmental impacts and developing technological solutions, but gaps in data often make it challenging to get the full picture.
Becca Muenich, biological and agricultural engineering researcher, set out to fill the gap with 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 there has been a rise in these feeding operations in response to 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 encompassing 18 U.S. states. The data was broken up into individual parcels based on ownership. Testing against a dataset of known animal feeding operations, the model predicted their location with 87 percent accuracy.
The study, “Machine learning-based identification of animal feeding operations in the United States on a parcel-scale,” was published in Science of the Total Environment in January.
Filling in the gaps
Previous attempts at identifying animal feeding operations have often relied on aerial images, Muenich said, but livestock facilities often 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 with of Michigan and Ohio that included multiple feeding operations. Data was readily available through the pollutant elimination system for Michigan due to the state’s permitting requirements. The same data, however, wasn’t available for the same operations in Ohio, which set Muenich down this path of investigation.
Advancing towards a better accounting of livestock can help with developing strategies that can improve environmental outcomes of livestock management while creating economic opportunities for farmers through the scaling up of technologies aimed at combating animal waste, Muenich said. Scaling these technologies in economically feasible ways requires knowledge of where livestock are most prevalent and spatially connected, she explained.
Co-authors of the study included Arghajeet Saha, formerly a postdoctoral researcher at the University of Arkansas and currently an assistant scientist with the Kansas Geological Survey; Barira Rashid, 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 The Ohio State University’s department of food, agricultural and biological engineering.
The research was supported by the Science and Technologies for Phosphorus Sustainability Center under National Science Foundation award number CBET-2019435. The Data with Purpose program from Regrid, a source for nationwide land parcel data, provided data used in the research.
To learn more about the Division of Agriculture research, visit the Arkansas Agricultural Experiment Station website. Follow us on 𝕏 at @ArkAgResearch, subscribe to the Food, Farms and Forests podcast and sign up for our monthly newsletter, the Arkansas Agricultural Research Report. To learn more about the Division of Agriculture, visit uada.edu. Follow us on 𝕏 at @AgInArk. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit uaex.uada.edu.
Becca Muenich, associate professor of biological and agricultural engineering and a researcher with the Arkansas Agricultural Experiment Station, used machine learning tools to model the locations of animal feeding operations in the U.S.
Credit
U of A System Division of Ag photo by Paden Johnson
About the Division of Agriculture
The University of Arkansas System Division of Agriculture’s mission is to strengthen agriculture, communities, and families by connecting trusted research to the adoption of best practices. Through the Agricultural Experiment Station and the Cooperative Extension Service, the Division of Agriculture conducts research and extension work within the nation’s historic land grant education system.
The Division of Agriculture is one of 20 entities within the University of Arkansas System. It has offices in all 75 counties in Arkansas and faculty on three campuses.
The University of Arkansas System Division of Agriculture offers all its Extension and Research programs to all eligible persons without regard to race, color, sex, gender identity, sexual orientation, national origin, religion, age, disability, marital or veteran status, genetic information, or any other legally protected status, and is an Affirmative Action/Equal Opportunity Employer.
Journal
Science of The Total Environment
Article Title
Machine learning-based identification of animal feeding operations in the United States on a parcel-scale
Sweet molasses feed key to understanding grazing behavior in cattle
Recognizing behavior could optimize herd distribution, enhance nutrition
image:
Nomad cows spreading out from the herd to graze at the UC Sierra Foothill Research and Extension Center.
view moreCredit: Kristina Horback / UC Davis
Researchers tempted grazing cattle with sweet molasses feed to discover whether cows would roam far and wide to graze or stick close to the herd, water supplies and feed stations.
The findings by animal scientists at the University of California, Davis, and published in the journal Scientific Reports, offer a low-cost way for ranchers and others to identify the best cows for their landscapes to optimize grazing while meeting the nutritional needs of cattle.
This is the third in a series of papers about research seeking to better understand the grazing personalities of cattle. The first studies established that the cows weren’t mindless wanderers or followers but had personalities that differentiated how far and wide they would graze, said Kristina Horback, the senior author on the paper and an associate professor in the Department of Animal Science.
“This final study is trying to figure out, ‘Can we have any early indicators so that we don't have to put GPS collars on all cows, but just do a quick practical test?’” Horback said.
Water quality, soil health and habitats can be degraded by cattle grazing unevenly or concentrated in specific areas. A herd with animals that wander around a landscape to graze can benefit the landscape by distributing grazing areas and defecation sites while also reducing fuel loads for wildfires.
Routine checks yield grazing personality
The research took place from June to August over two years at the UC Sierra Foothill Research and Extension Center in Browns Valley. Horback and others tracked 50 pregnant Angus and Hereford beef cows wearing GPS collars across the 625-acre site, which is a mix of grassland and treed areas. The elevation ranged from 600 to 2,028 feet.
Researchers were able to predict cows’ likely grazing personalities by analyzing behavior in situations such as pregnancy checks or vaccinations, which require the cows to walk through chutes or narrow passageways.
At the end of the chutes, the cows had two choices: go one direction to join the herd or another direction to pursue sweet molasses feed placed at different distances. The animals that moved slowly through the chutes and would go out of the way for the feed were consistently the grazing wanderers.
“They were the ones on range that would go far and wide, that would also not really be that motivated to be closely, tightly packed with the rest of the herd,” Horback said.
The homebodies consistently sought out the herd.
“They would not choose that sweet molasses,” Horback said. “They would go right back to the herd as quickly as they could, and then on range, they would just stay together. They have their social group there.”
Future generations
Next up in the research is to see if grazing personalities pass down to later generations. Horback is looking at the female calves of the studied cows to see if they pick up on the same patterns as their moms.
“If there are any calves who are fostered off to another cow, do they pick up the grazing patterns of their birth mom or their adopted mom?” Horback said. “There’s no guarantee that genetics alone will determine the grazing behavior of a cow, but it could increase the likelihood that a cow is a hill-climber or a bottom-dweller.”
She is also working with colleagues in New Zealand and New Mexico to analyze blood samples from the cows that were tracked as part of related studies to see if genetic testing can provide some insight into behavior.
UC Davis emeritus professor Juan Medrano published research a decade ago about genetic markers in cows that could indicate either hill-climbers or bottom-dwellers.
“I hope to build on that knowledge with a larger, international dataset to understand whether grazing personalities are heritable,” Horback said.
Maggie Creamer, who earned her Ph.D. in animal behavior at UC Davis, contributed to the research, which was supported by the Russell L. Rustici Rangeland and Cattle Research Endowment.
Journal
Scientific Reports
Method of Research
Experimental study
Subject of Research
Animals
Article Title
Cows that are less active in the chute have more optimal grazing distribution
No comments:
Post a Comment