We unite quantitative genetics, statistics, and artificial intelligence to make plant breeding faster, more accurate, and more predictable across diverse environments.
We are a research group in the Center for Agricultural Data Analytics (CADA) at the University of Arkansas, led by Dr. Samuel B. Fernandes. We build the statistical methods, predictive models, and open-source software that make plant breeding faster and more predictable across diverse environments — approaches designed to apply to any crop. Through CADA, we also provide statistical consulting to researchers across the University of Arkansas.
Five connected areas drive the questions we ask and the tools we build — methods designed to work for any crop.
Mixed models and experimental design that turn noisy field trials into reliable insight.
Genomic prediction, association mapping (GWAS & TWAS), and simulation to connect genotype with phenotype.
Crop-agnostic tools for faster, more predictable selection — applied with partner programs in crops such as soybean, rice, maize, and blackberry.
Machine learning for high-throughput phenotyping and for prediction models that fuse genomic and environmental data.
Machine-learning pipelines that turn images and sensor data into traits for GWAS and TWAS, and Bayesian optimization to search trait space efficiently.
We develop quantitative-genetics and AI methods that help breeders predict the performance of any genotype in any environment — shortening breeding cycles and strengthening food security.
Read our mission, vision & goalsSept. 11, 2025
Dr. Samuel B. Fernandes received the Foundation for Food & Agriculture Research (FFAR) New Innovator Award, recognizing early-career scientists making transformative contributions to food and agriculture research.
Jun. 12, 2025
Carlos, a U of A master's student in statistics and analytics researching plant breeding through the Center for Agricultural Data Analytics, attended the 30th Bruce Weir Summer Institute in Statistical Genetics (SISG) at the Georgia Institute of Technology, sharpening his work in genomic prediction and GWAS.
Jan. 14, 2025
Igor Fernandes placed first in a contest sponsored by the Sixth International Machine Learning for Cyber-Agricultural Systems workshop, combining satellite data with machine learning for crop prediction.
We're always looking for curious people with backgrounds in statistics, genetics, computer science, or agronomy. See our open positions, or reach out.
Type to search · Esc to close · ⌘K to open anywhere
