How do nutritionists turn model outputs into better rations on the farm? This article explores the journey from data to the barn, focusing on the application of nutritional models in real-world farm settings.
Recorded live at the American Dairy Science Association (ADSA) 2026 Annual Meeting, this episode explores how nutritional models for dairy cattle are developed, applied and refined to support dairy ration formulation.
Researchers and consulting nutritionists cover the history of the Cornell Net Carbohydrate and Protein System (CNCPS). They also compare mechanistic and empirical models and explain how to pair model outputs with on-farm observation, sensor data and experience.
Episode 226: From Data to the Barn: The Application of Nutritional Models
Timestamps:
Introductions and Symposium Previews
Dr. Andrew Lapierre shares the nearly 50-year history of CNCPS, and Dr. Jonas de Souza previews his work on fatty acid modeling. Dr. Veridiana Daley reviews milk protein modeling, amino acid nutrition and new technologies that could sharpen decision-making. (00:00 – 10:45)
Models in the Field
The consulting nutritionists explain how they use models day to day. They discuss how ration software has evolved and why model outputs still need practical farm management and observation behind them. (10:46 – 15:12)
NASEM vs. CNCPS
The panel compares empirical and mechanistic models. Models are the best interpretation of available data, not perfect pictures of biology. That’s why it’s critical to understand each model’s assumptions before acting on its recommendations. (15:13 – 19:25)
Protein and Rumen Degradable Protein Predictions
NASEM and CNCPS often reach different answers because they rely on different assumptions, microbial compositions and prediction methods. Neither is perfect, but both are useful for evaluating amino acid supply and nutrient responses. (19:26 – 24:08)
Modeling the Modern Dairy Cow
Genetic progress has raised production potential, yet many post-absorptive efficiency assumptions still come from older datasets. The panel names nutrient use efficiency and variable animal responses as key areas for future research. (24:09 – 29:46)
Making Practical Ration Changes
Nutritionists use models to guide gradual ration changes within real-world constraints. They also point out that management decisions can affect performance as much as the diet itself. (29:47 – 33:32)
Adding Sensor Data to Models
Rumination, rumen health and other precision dairy sensor data could improve intake predictions, flag health events and support nutritional decisions. (33:33 – 37:43)
Dry Matter Intake and Forage Quality
The panel looks at dry matter intake optimization and forage quality challenges. They also ask whether maximizing intake is always the most profitable strategy. (37:44 – 43:29)
Improving Feed Libraries and Response Models
The group sees room to expand response modeling and improve feed libraries. They also want to better characterize ingredients and add amino acid and fatty acid data, all while validating models against research and field datasets. (43:30 – 58:41)
The Future of Nutritional Modeling
Looking ahead, the panel discusses better fatty acid and amino acid prediction systems, sensor integration, artificial intelligence and stochastic modeling. They also call for stronger collaboration between researchers and field nutritionists, with better data and ongoing validation driving progress. (58:42 – End)
Join Us at the Real Science Exchange
If you enjoyed this episode, subscribe to the Real Science Exchange and share it with your colleagues in the dairy industry. That way, they can join the conversation at our virtual pub table.
Continue learning from leading researchers and dairy industry experts by registering for an upcoming Real Science Lecture Series webinar.
And don’t forget your Real Science Exchange T-shirt! Screenshot your rating, review, or subscription, then email the image to anh.marketing@balchem.com along with your shirt size and mailing address.
FAQ
What are nutritional models for dairy cattle?
They are mathematical systems that predict nutrient supply and requirements to help nutritionists formulate rations. CNCPS and NASEM are two widely used examples.
What is the difference between CNCPS and NASEM?
CNCPS takes a mechanistic approach, simulating processes such as rumen fermentation. NASEM relies more on empirical relationships drawn from research data. Because their assumptions differ, their predictions can differ too.
Which dairy nutrition model is most accurate?
Neither model is perfect. The best results come from understanding each model’s assumptions and checking outputs against what you see on the farm.
How will sensors and AI change dairy ration formulation?
Sensor data on rumination and rumen health may improve intake predictions and flag health events earlier. AI and stochastic modeling could help account for variable animal responses.
Is maximizing dry matter intake always the most profitable strategy?
Not always. The right intake target depends on forage quality, available resources and environmental conditions on each operation.
