Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows

A reliable estimation of protein requirements in lactating dairy cows is necessary for formulating nutritionally adequate diets, improving feed efficiency, and minimizing nitrogen excretion. This study aimed to develop machine learning-based models to predict net protein requirements for maintenance...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingyung Lee, Dong Hyeon Kim, Seongwon Seo, Luis O. Tedeschi
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Animals
Subjects:
Online Access:https://www.mdpi.com/2076-2615/15/14/2127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077382328713216
author Mingyung Lee
Dong Hyeon Kim
Seongwon Seo
Luis O. Tedeschi
author_facet Mingyung Lee
Dong Hyeon Kim
Seongwon Seo
Luis O. Tedeschi
author_sort Mingyung Lee
collection DOAJ
description A reliable estimation of protein requirements in lactating dairy cows is necessary for formulating nutritionally adequate diets, improving feed efficiency, and minimizing nitrogen excretion. This study aimed to develop machine learning-based models to predict net protein requirements for maintenance (NPm) and lactation (NPl) using random forest regression (RFR) and support vector regression (SVR). A total of 1779 observations were assembled from 436 peer-reviewed publications and open-access databases. Predictor variables included farm-ready variables such as milk yield, dry matter intake, days in milk, body weight, and dietary crude protein content. NPm was estimated based on the National Academies of Sciences, Engineering, and Medicine (NASEM, 2021) equations, while NPl was derived from milk true protein yield. The model adequacy was evaluated using 10-fold cross-validation. The RFR model demonstrated higher predictive performance than SVR for both NPm (R<sup>2</sup> = 0.82, RMSEP = 22.38 g/d, CCC = 0.89) and NPl (R<sup>2</sup> = 0.82, RMSEP = 95.17 g/d, CCC = 0.89), reflecting its capacity to model the rule-based nature of the NASEM equations. These findings suggest that RFR may provide a valuable approach for estimating protein requirements with fewer input variables. Further research should focus on validating these models under field conditions and exploring hybrid modeling frameworks that integrate mechanistic and machine learning approaches.
format Article
id doaj-art-e4f2a02cf66d40cca58d6e52a1580fb7
institution DOAJ
issn 2076-2615
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Animals
spelling doaj-art-e4f2a02cf66d40cca58d6e52a1580fb72025-08-20T02:45:49ZengMDPI AGAnimals2076-26152025-07-011514212710.3390/ani15142127Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy CowsMingyung Lee0Dong Hyeon Kim1Seongwon Seo2Luis O. Tedeschi3Department of Animal Science, Texas A&M University, College Station, TX 77843-2471, USADairy Science Division, National Institute of Animal Science, Rural Development Administration, Cheonan 31000, Republic of KoreaDivision of Animal and Dairy Sciences, Chungnam National University, Daejeon 34134, Republic of KoreaDepartment of Animal Science, Texas A&M University, College Station, TX 77843-2471, USAA reliable estimation of protein requirements in lactating dairy cows is necessary for formulating nutritionally adequate diets, improving feed efficiency, and minimizing nitrogen excretion. This study aimed to develop machine learning-based models to predict net protein requirements for maintenance (NPm) and lactation (NPl) using random forest regression (RFR) and support vector regression (SVR). A total of 1779 observations were assembled from 436 peer-reviewed publications and open-access databases. Predictor variables included farm-ready variables such as milk yield, dry matter intake, days in milk, body weight, and dietary crude protein content. NPm was estimated based on the National Academies of Sciences, Engineering, and Medicine (NASEM, 2021) equations, while NPl was derived from milk true protein yield. The model adequacy was evaluated using 10-fold cross-validation. The RFR model demonstrated higher predictive performance than SVR for both NPm (R<sup>2</sup> = 0.82, RMSEP = 22.38 g/d, CCC = 0.89) and NPl (R<sup>2</sup> = 0.82, RMSEP = 95.17 g/d, CCC = 0.89), reflecting its capacity to model the rule-based nature of the NASEM equations. These findings suggest that RFR may provide a valuable approach for estimating protein requirements with fewer input variables. Further research should focus on validating these models under field conditions and exploring hybrid modeling frameworks that integrate mechanistic and machine learning approaches.https://www.mdpi.com/2076-2615/15/14/2127lactating Holstein cowsnet protein for lactationnet protein for maintenancerandom forest regressionsupport vector regression
spellingShingle Mingyung Lee
Dong Hyeon Kim
Seongwon Seo
Luis O. Tedeschi
Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
Animals
lactating Holstein cows
net protein for lactation
net protein for maintenance
random forest regression
support vector regression
title Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
title_full Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
title_fullStr Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
title_full_unstemmed Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
title_short Development of Machine Learning-Based Sub-Models for Predicting Net Protein Requirements in Lactating Dairy Cows
title_sort development of machine learning based sub models for predicting net protein requirements in lactating dairy cows
topic lactating Holstein cows
net protein for lactation
net protein for maintenance
random forest regression
support vector regression
url https://www.mdpi.com/2076-2615/15/14/2127
work_keys_str_mv AT mingyunglee developmentofmachinelearningbasedsubmodelsforpredictingnetproteinrequirementsinlactatingdairycows
AT donghyeonkim developmentofmachinelearningbasedsubmodelsforpredictingnetproteinrequirementsinlactatingdairycows
AT seongwonseo developmentofmachinelearningbasedsubmodelsforpredictingnetproteinrequirementsinlactatingdairycows
AT luisotedeschi developmentofmachinelearningbasedsubmodelsforpredictingnetproteinrequirementsinlactatingdairycows