Hiring in life sciences? Share your open positions with our professional community. Read more Close

Advertisement

A comparative study on predicting energy requirements for layer pullets using mathematical model and machine learning methods.

Created on 16 Nov 2026

Authors

Qiuyu Jiang, Kaichen Zheng, Zhibin Ban, Xiaojian Deng, Bingkun Zhang

Published in

Animal nutrition (Zhongguo xu mu shou yi xue hui). Volume 27. Pages 667-677. Epub Oct 10, 2026.

Abstract

The objective of this study was to evaluate energy intake and energy partitioning in layer pullets and to compare the performance of mathematical model and machine learning approaches on predicting energy requirements. A total of 480 one-d-old "Jing Tint 6" layer pullets, with an initial body weight (BW) of approximately 36 g were randomly assigned to 30 pens (16 hens per pen), and utilized for the present study consisting of 16 indirect calorimetry measurements and 23 serial slaughters performed between 1 and 18 wk of age to determine dynamic heat production (HP) and body energy (BE). The BW and body weight gain (BWG) were split in JMP software as variables to predict apparent metabolizable energy (AME) intake and net energy (NE) intake using algorithms including artificial neural networks (ANN), k-nearest neighbor (KNN) and random forest (RF). By linear regression (LR) analysis, the ME for maintenance (MEm) of layer pullets was estimated to be 551.86, 467.04, 478.19, 439.58, and 463.38 kJ/kg BW0.75·d for 1 to 6 wk of age, 7 to 10 wk of age, 11 to 14 wk of age, 15 to 18 wk of age and the overall period, respectively, while the NE for maintenance (NEm) was estimated at 510.81, 356.38, 367.23, 324.73, and 346.89 kJ/kg BW0.75·d, respectively. The regression between BE and BW yielded NE for growth (NEg) and ME for growth (MEg), with values of 9.73 and 13.12 kJ/g, respectively (1-18 wk of age). The combination of energy for maintenance and growth yielded energy requirement models (1-18 wk of age): AME intake = 463.38 BW0.75 + 13.12 BWG; NE intake = 346.89 BW0.75 + 9.73 BWG. However, the equation derived from LR demonstrated lower accuracy and precision compared to machine learning models. Among machine learning models, ANN exhibited superior performance with maximal R 2 and minimal root mean squared error (RMSE) in predicting AME requirement (R 2 = 0.8870, RMSE = 52.989) and NE requirement (R 2 = 0.8221, RMSE = 50.742) for layer pullets from 1 to 18 wk of age. Hence, the application of ANN models in predicting energy requirement could promote the optimization of dietary formulations in the pullet industry.

PMID:
43036800
Bibliographic data and abstract were imported from PubMed on 16 Nov 2026.

Read full publication at:
Please sign in to see all details.

Advertisement

Stats

  • Community rating n/a 0 votes
  • Reviewers' rating n/a 0 votes
  • Your rating

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

  • Recommendations n/a n/a positive of 0 vote(s)
  • Views 6
  • Comments 0

Recommended by

  • No recommendations yet.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.

Advertisement