Add BrightSurf on Google Email

University of Arkansas System Division of Agriculture


Machine learning maps animal feeding operations to improve sustainability

Researchers developed a machine learning model that predicts the presence of animal feeding operations with high accuracy, filling a data gap crucial for managing their environmental impacts. The model uses predictors such as surface temperature and phosphorus levels to identify locations without relying on aerial images.

SourceUniversity of Arkansas System Division of Agriculture·JournalScience of The Total Environment·DateFeb 18, 2025

Chicken ‘woody breast’ detection improved with advanced machine learning model

A new machine learning model, NAS-WD, has improved the accuracy of detecting 'woody breast' in chicken meat to 95%, allowing for better quality assurance and customer confidence. The model uses hyperspectral imaging to analyze complex data from images, enabling more accurate detection than traditional methods.

SourceUniversity of Arkansas System Division of Agriculture·JournalArtificial Intelligence in Agriculture·TypeImaging analysis·DateFeb 10, 2025

How flooding soybeans in early reproductive stages impacts yield, seed composition

Researchers at the University of Arkansas System Division of Agriculture conducted a two-year study exposing 31 soybean varieties to flood conditions during the early reproductive stage. The study found that four-day flooding did not significantly alter the seed composition of any variety, but grain yield losses were observed across al...

SourceUniversity of Arkansas System Division of Agriculture·JournalCrop Science·TypeExperimental study·DateFeb 3, 2025

New software package drives deeper understanding of trait evolution

A new software package called TraitTrainR offers a framework for replicating the evolutionary process many times over. It can perform flexible evolutionary experiments through probabilistic simulations on a computer, allowing researchers to generate thousands-to-millions of evolutionary replicates.

SourceUniversity of Arkansas System Division of Agriculture·JournalBioinformatics Advances·TypeComputational simulation/modeling·DateJan 22, 2025

Arkansas Clean Plant Center leads global effort to wipe ‘phantom agents’ from pathogen regulatory lists

The Arkansas Clean Plant Center is leading a global effort to remove over 120 'phantom agents' from pathogen regulatory lists. These outdated agents impede access to clean plant materials, hindering crop production and food security. The center's efforts aim to streamline global germplasm exchange using modern molecular techniques.

SourceUniversity of Arkansas System Division of Agriculture·JournalPlant Disease·TypeObservational study·DateJan 7, 2025

Hot water best for sanitizing in-shell pecans, sanitizers prevent cross-contamination

In-shell pecans are susceptible to pathogens due to soil contact with wildlife and livestock. A recent study found that hot water treatment significantly reduced Shiga toxin-producing E. coli populations on pecans, regardless of treatment time, and prevented cross-contamination.

SourceUniversity of Arkansas System Division of Agriculture·JournalJournal of Food Protection·TypeExperimental study·DateNov 25, 2024

Survey assesses Mexican consumers’ opinions on GMO corn import ban

A recent study found that over 90% of Mexican consumers would be willing to pay a premium of up to 73% for non-genetically modified products, including chicken, eggs, and tortillas. The ban on genetically modified corn could have significant impacts on US farmers who rely heavily on Mexico as their second-largest importer.

SourceUniversity of Arkansas System Division of Agriculture·JournalJournal of Food Security·TypeSurvey·DateOct 29, 2024

Multi-state study offers recommendations for keeping bermudagrass greener all season

A new multi-state study identified three management tips to extend green color and reduce cold-weather injury in hybrid bermudagrass: raising mowing height, applying nitrogen fertilizer in the fall, and maintaining adequate soil moisture. The research found that slow-release nitrogen applications through mid-September had positive impa...

SourceUniversity of Arkansas System Division of Agriculture·JournalCrop Forage & Turfgrass Management·DateSep 26, 2024

Study offers improvements to food quality computer predictions

A study from the University of Arkansas System Division of Agriculture has improved food quality computer predictions by using human perception data. The researchers trained a computer model to mimic human adaptation to environmental conditions, resulting in more consistent predictions under different lighting conditions.

SourceUniversity of Arkansas System Division of Agriculture·JournalJournal of Food Engineering·TypeComputational simulation/modeling·DateSep 24, 2024

New machine learning model offers simple solution to predicting crop yield

A new machine-learning model developed by a University of Arkansas student improves upon existing genotype-by-environmental interaction models, achieving higher prediction accuracy. The model uses feature engineering to process environmental data, leading to a 7% improvement in mean prediction accuracy.

SourceUniversity of Arkansas System Division of Agriculture·JournalTheoretical and Applied Genetics·TypeData/statistical analysis·DateSep 3, 2024

Researchers uncover what makes some chickens more water efficient than others

A team of researchers discovered a line of chickens bred for water conservation that can thrive under heat stress while consuming significantly less water than standard broiler lines. The high water-efficient chickens showed a 32-point improvement in water conversion and six-point improvement in feed conversion.

SourceUniversity of Arkansas System Division of Agriculture·JournalPhysiological Reports·TypeExperimental study·DateMay 14, 2024

Soil testing time saver predicts key soil health characteristics

A new study predicts key soil health indicators such as organic matter content and soil texture using standard tests. This can guide fertilization, irrigation, and herbicide decisions, reducing turnaround time by at least half. The models are accurate for fine and medium soils but less so for sandy soils.

SourceUniversity of Arkansas System Division of Agriculture·JournalAgrosystems Geosciences & Environment·TypeData/statistical analysis·DateMay 13, 2024