The purpose of this study was to devise an optimal method for estimating outside temperatures of pig farms using air temperature data obtained from multiple meteorological stations. Using daily average, daily maximum, and daily minimum temperatures recorded at nine selected Japan Meteorological Agency meteorological stations, we used data masking and inverse distance weighting to estimate temperature based on data from 1-8 stations in the vicinity of each point. The daily range was estimated from the daily maximum and minimum temperatures. Our results showed that daily average and daily maximum temperatures can be estimated with high accuracy by using data from the three nearest stations. The absolute value of the mean error and the root mean square error for all temperatures are low from June to October and the correlation coefficient is generally high in September. Based on these results, we conclude that the daily average and daily maximum temperatures can be estimated with high accuracy using this method, especially in hot weather.

The objectives of this study were to investigate the efficiency of measuring individual feed intake and to clarify the relationships between residual feed intake (RFI) and economic traits of fattening cattle in the field progeny test. The feed intake, body weight and carcass traits were obtained for the total of 480 Japanese Black steers (240) and heifers (240), and their RFI were calculated by their feed intake and body weight. Fattening period was separated early and late, and correlations between the periods and the whole fattening period were calculated to investigate their relationships. To clarify the relationships between RFI and economic traits, the RFI was divided into four quartiles and means of the traits were compared among the RFI quartile groups. In the correlations for RFI of each diet among fattening period, there were strong correlations between the late and whole fattening periods on concentrate and total feed intakes. This suggested that the RFI of the animals for the whole fattening period could estimate by the RFI based on concentrate feed intake in the late period. The daily TDN intake during the fattening period in the first (best) RFI group was 12% lower than that in the fourth (worst) RFI group. In steers, mean RFI in the first group was -0.921 kg/day which was 1.8 kg/day lesser than that in the fourth group, implying that animals with superior RFI can reduce the production cost for farmers. Means of growth and carcass traits in the first group were similar to the fourth group. These results suggest that feed intake in the field progeny test can measure efficiently and selection for the RFI from the test can reduce feed intake and improve productivity without affecting growth and carcass traits.

Recently, the use of artificial intelligence in animal science field has garnered attention. Beef marbling standard (BMS) is one of the most important carcass traits for determining the value of carcasses. This study aimed to estimate BMS using information obtained from carcass cross sectional images at the 6th and 7th rib with Random Forest, a type of machine learning. Rib eye images of 2,498 Japanese Black cattle that were shipped to one market in Hokkaido between January and December 2022 were analyzed. Twenty-three image analysis traits gained in the rib eye were used as explanatory variables. Stratified k-fold cross-validation with k＝5 was performed to evaluate the estimation performance of Random Forest, including the difference between grading BMS and estimated BMS, the importance of variables, and Shapley values. The percentages of difference between grading BMS and estimated BMS within ±0, ±1, and ±2 were 51.8%, 94.1%, and 99.7%, respectively. The importance of each variable, in descending order, was 0.8634 for marbling percentage, 0.0297 for new fineness index, and 0.0121 for coarseness index 1-10. The results showed that the amount and shape of marbling were particularly important for estimating BMS. The amount and fineness of marbling had positive effects on estimates, while the coarseness of marbling acted as a negative factor, especially in intermediate BMS (7 to 10). Therefore, using Random Forest has suggested that highly accurate and interpretable estimation of BMS predictions is feasible.