Prediction of body condition in Jersey dairy cattle from 3D-images using machine learning techniques.

The body condition of dairy cows is a crucial health and welfare indicator that is widely acknowledged. Dairy herds with a well-management body condition tend to have more fertile and functional cows. Therefore, routine recording of high-quality body condition phenotypes is required. Automated prediction of body condition from 3D images can be a cost-effective approach to current manual recording by technicians. Using 3D-images, we aimed to build a reliable prediction model of body condition for Jersey cows. The dataset consisted of 808 individual Jersey cows with 2,253 phenotypes from three herds in Denmark. Body condition was scored on a 1 to 9 scale and transformed into a 1 to 5 scale with 0.5-unit differences. The cows' back images were recorded using a 3D camera (Microsoft Xbox One Kinect v2). We used contour and back height features from 3D-images as predictors, together with class predictors (evaluator, herd, evaluation round, parity, lactation week). The performance of machine learning algorithms was assessed using H2O AutoML algorithm (h2o.ai). Based on outputs from AutoML, DeepLearning (DL; multi-layer feedforward artificial neural network) and Gradient Boosting Machine (GBM) algorithms were implemented for classification and regression tasks and compared on prediction accuracy. In addition, we compared the Partial Least Square (PLS) method for regression. The training and validation data were divided either through a random 7:3 split for 10 replicates or by allocating two herds for training and one herd for validation. The accuracy of classification models showed the DL algorithm performed better than the GBM algorithm. The DL model achieved a mean accuracy of 48.1% on the exact phenotype and 93.5% accuracy with a 0.5-unit deviation. The performances of PLS and DL regression methods were comparable, with mean coefficient of determination of 0.67 and 0.66, respectively. When we used data from two herds for training and the third herd as validation, we observed a slightly decreased prediction accuracy compared to the 7:3 split of the dataset. The accuracies for DL and PLS in the herd validation scenario were > 38% on the exact phenotype and > 87% accuracy with 0.5-unit deviation. This study demonstrates the feasibility of a reliable body condition prediction model in Jersey cows using 3D-images. The approach developed can be used for reliable and frequent prediction of cows' body condition to improve dairy farm management and genetic evaluations.

The body condition of dairy cows is a crucial health and welfare indicator that is widely acknowledged in dairy cattle management. Routine recording of high-quality body condition phenotypes is required for adaptation in dairy herd management. The use of machine learning to predict the body condition of dairy cows from 3D images can offer a cost-effective approach to the current manual recording performed by technicians. We aimed to build a reliable prediction, based on data from 808 Jersey cows with 2,253 body condition phenotypes from three commercial herds in Denmark. We tested different machine-learning models. All models showed high prediction accuracy, and comparable levels with other published studies on Holstein cows. In a validation test across project herds, prediction accuracy ranged between 87% and 96%.

Genetic parameters for feed intake and body weight in dairy cattle using high-throughput 3-dimensional cameras in Danish commercial farms.

Recording complex phenotypes on a large scale is becoming possible with the incorporation of recently developed new technologies. One of these new technologies is the use of 3-dimensional (3D) cameras on commercial farms to measure feed intake and body weight (BW) daily. Residual feed intake (RFI) has been proposed as a proxy for feed efficiency in several species, including cattle, pigs, and poultry. Dry matter intake (DMI) and BW records are required to calculate RFI, and the use of this new technology will help increase the number of individual records more efficiently. The aim of this study was to estimate genetic parameters (including genetic correlations) for DMI and BW obtained by 3D cameras from 6,000 cows in commercial farms from the breeds Danish Holstein, Jersey, and Nordic Red. Additionally, heritabilities per parity and genetic correlations among parities were estimated for DMI and BW in the 3 breeds. Data included 158,000 weekly records of DMI and BW obtained between 2019 and 2022 on 17 commercial farms. Estimated heritability for DMI ranged from 0.17 to 0.25, whereas for BW they ranged from 0.44 to 0.58. The genetic correlations between DMI and BW were moderately positive (0.58-0.65). Genetic correlations among parities in both traits were highly correlated in the 3 breeds, except for DMI between first parity and late parities in Holstein where they were down to 0.62. Based on these results, we conclude that DMI and BW phenotypes measured by 3D cameras are heritable for the 3 dairy breeds and their heritabilities are comparable to those obtained by traditional methods (scales and feed bins). The high heritabilities and correlations of 3D measurements with the true trait in previous studies demonstrate the potential of this new technology for measuring feed intake and BW in real time. In conclusion, 3D camera technology has the potential to become a valuable tool for automatic and continuous recording of feed intake and BW on commercial farms.

Sharing of either phenotypes or genetic variants can increase the accuracy of genomic prediction of feed efficiency.

BACKGROUND: Sharing individual phenotype and genotype data between countries is complex and fraught with potential errors, while sharing summary statistics of genome-wide association studies (GWAS) is relatively straightforward, and thus would be especially useful for traits that are expensive or difficult-to-measure, such as feed efficiency. Here we examined: (1) the sharing of individual cow data from international partners; and (2) the use of sequence variants selected from GWAS of international cow data to evaluate the accuracy of genomic estimated breeding values (GEBV) for residual feed intake (RFI) in Australian cows. RESULTS: GEBV for RFI were estimated using genomic best linear unbiased prediction (GBLUP) with 50k or high-density single nucleotide polymorphisms (SNPs), from a training population of 3797 individuals in univariate to trivariate analyses where the three traits were RFI phenotypes calculated using 584 Australian lactating cows (AUSc), 824 growing heifers (AUSh), and 2526 international lactating cows (OVE). Accuracies of GEBV in AUSc were evaluated by either cohort-by-birth-year or fourfold random cross-validations. GEBV of AUSc were also predicted using only the AUS training population with a weighted genomic relationship matrix constructed with SNPs from the 50k array and sequence variants selected from a meta-GWAS that included only international datasets. The genomic heritabilities estimated using the AUSc, OVE and AUSh datasets were moderate, ranging from 0.20 to 0.36. The genetic correlations (rg) of traits between heifers and cows ranged from 0.30 to 0.95 but were associated with large standard errors. The mean accuracies of GEBV in Australian cows were up to 0.32 and almost doubled when either overseas cows, or both overseas cows and AUS heifers were included in the training population. They also increased when selected sequence variants were combined with 50k SNPs, but with a smaller relative increase. CONCLUSIONS: The accuracy of RFI GEBV increased when international data were used or when selected sequence variants were combined with 50k SNP array data. This suggests that if direct sharing of data is not feasible, a meta-analysis of summary GWAS statistics could provide selected SNPs for custom panels to use in genomic selection programs. However, since this finding is based on a small cross-validation study, confirmation through a larger study is recommended.