In May of 2021 the USDA announced 24 awards totaling $2.3 million USD as part of their Small
Business Innovation and Research (SBIR) award program. Of the eight awards given to small
business’s to improve animal production UC Davis spin-off AgriNerds was granted a $100,000
award for it’s research focused on software and hardware solutions for the poultry industry. The
software solutions are focused on validating the best machine learning based methods for
predicting production and food safety outcomes and the hardware solutions are focused on the
development of a novel egg counting device to reduce the error rates that are currently occurring
on many layer farms.

The goal of the USDA-SBIR grant program is to “stimulate technological innovation in the
private sector and strengthen the role of federal research and development in support of small
businesses, “ according to USDA-NIFA director Dr. Carrie Castille.

AgriNerds is a UC Davis Spin-off co-founded by several UCD faculty and staff. If you are keen
to collaborate on either the software or hardware SBIR funded research please contact Dr. Maurice Pitesky at mepitesky@ucdavis.edu.

Leveraging data collected by commercial poultry requires a deep understanding of the data that are
collected. This article provides practical definitions and examples of ML-based statistical approaches for the analysis of poultry production and poultry food safety-based data. Two real examples of the supervised machine learning ensemble technique, random forest (RF), are provided with respect to predicting egg weights from a commercial layer farm and identifying the potential causes of a Salmonella outbreak from a commercial broiler facility. Results identified multiple variables including Age, Farm Location, Body Weight, Total Eggs, Hens Housed, and House Style which were predictive of the continuous variable Egg Weight. Predictors of Salmonella that included livability, density of birds in the grow-out farm, and breeder age were identified. The task of choosing the most appropriate ML-based model(s) that accounts for the large number of variables common to the poultry industry and addresses the intricate interdependence between several production parameters and inputs while predicting multiple sequential outputs is complex. The use of ML techniques in combination with new data streams including sensors (e.g., visual and audio), IoT, and Web-scraping could offer a more comprehensive, efficient, and timely approach toward evaluating productivity, food safety, and profitability in commercial poultry.