Accurate measurement of dry matter intake (DMI) in sheep is logistically challenging and costly, particularly under commercial conditions and across diverse production systems. This study evaluated whether methane (CH4), carbon dioxide (CO2) and oxygen (O2) gas measurements from portable accumulation chambers (PAC), combined with bodyweight (BW) and eating time (ET), can predict DMI in gestating ewes. Two indoor feeding trials were conducted at a single research facility using Norwegian White Sheep (NWS) and Old Norwegian Spaelsau (ONS). Trial 1 used two grass silage qualities in a 2 × 2 factorial design; Trial 2 used fresh-cut herbage in a repeated-measures design. Ewes (n = 40 per trial; 29 in common) were individually housed with access to one feed bin and fed ad libitum. Daily DMI was recorded using automated feed bins, and PAC measurements of CH4, CO2, and O2 were collected on 20 d per ewe per trial. After quality control, 1,830 ewe d records remained. Supervised learning models were trained on ewe-identity-blocked training sets and evaluated on external test sets stratified by trial and breed. In this particular dataset, random forest (RF) models outperformed regularized regression, partial least squares, k-nearest neighbors, support vector machines, and a deep neural network. The best RF model, using PAC traits, LW, and ET (Pred_DMI3), achieved R2 = 0.77, root means square error of 279 g/d, and mean absolute percentage error = 13.8% in the combined test set. Models using only PAC traits performed comparably to models including BW and ET with only marginal losses in validation metrics. Mixed-model analyses indicated strong individual-level correlations between predicted and observed DMI (rᵢ = 0.79-0.81) after adjusting for breed, diet, and trial. These results demonstrate that short-term PAC-derived gas traits can provide scalable proxies for daily DMI in gestating ewes under controlled indoor conditions, with potential application in intake phenotyping and benchmarking.
Keywords: carbon dioxide; dry matter intake; machine learning; methane; portable accumulation chambers; sheep.
How much grass or silage a sheep eats each day is important for both farm profitability and climate impact, but measuring individual feed intake is expensive and time-consuming. In this study, we tested whether we can “read” an ewe’s daily feed intake from a short term measurement of the gases she breathes out. We worked with two Norwegian sheep breeds and measured their methane and carbon dioxide emissions in portable accumulation chambers, along with their body weight and time spent eating. At the same time, we recorded exactly how much each ewe ate each day using electronic feed bins. We then used machine learning methods to predict daily feed intake from these gas and on-farm measurements. The best model, based on a random forest algorithm, predicted daily intake with good accuracy, typically within about 300 grams per day. Models using only gas measurements performed almost as well as those that also used body weight and eating time. Our results show that gas measurements can be used as a more rapid, practical way to estimate how much feed gestating ewes eat when housed indoors. This approach could help farmers and breeders monitor feed use and identify animals that use feed more efficiently.
© The Author(s) 2026. Published by Oxford University Press on behalf of the American Society of Animal Science.