Individual feedlot beef cattle identification represents a critical component in cattle traceability in the supply food chain. It also provides insights into tracking disease trajectories, ascertaining ownership, and managing cattle production and distribution. Animal biometric solutions, e.g., identifying cattle muzzle patterns (unique features comparable to human fingerprints), may offer noninvasive and unique methods for cattle identification and tracking, but need validation with advancement in machine learning modeling. The objectives of this research were to (1) collect and publish a high-quality dataset for beef cattle muzzle images, and (2) evaluate and benchmark the performance of recognizing individual beef cattle with a variety of deep learning models. A total of 4923 muzzle images for 268 US feedlot finishing cattle (>12 images per animal on average) were taken with a mirrorless digital camera and processed to form the dataset. A total of 59 deep learning image classification models were comparatively evaluated for identifying individual cattle. The best accuracy for identifying the 268 cattle was 98.7%, and the fastest processing speed was 28.3 ms/image. Weighted cross-entropy loss function and data augmentation can increase the identification accuracy of individual cattle with fewer muzzle images for model development. In conclusion, this study demonstrates the great potential of deep learning applications for individual cattle identification and is favorable for precision livestock management. Scholars are encouraged to utilize the published dataset to develop better models tailored for the beef cattle industry.

Two commercial feedlot experiments and a metabolism study were conducted to evaluate the effects of monensin concentrations and bunk management strategies on performance, feed intake, and ruminal metabolism. In the feedlot experiments, 1,793 and 1,615 steers were used in Exp. 1 and 2, respectively, in 18 pens for each experiment (six pens/treatment). Three treatments were evaluated: 1) ad libitum bunk management with 28.6 mg/kg monensin and clean bunk management strategies with either 2) 28.6 or 3) 36.3 mg/kg monensin. In both experiments, 54 to 59% of the clean bunk pens were clean at targeted clean time, or 2200, compared with 24 to 28% of the ad libitum pens. However, only 13% of the pens were clean by 2000 in Exp. 1 (summer), whereas 44% of the pens in Exp. 2 (winter) were clean by 2000. In Exp. 1, bunk management and monensin concentration did not affect carcass-adjusted performance. In Exp. 2, steers fed ad libitum had greater DMI (P < 0.01) and carcass-adjusted ADG (P < 0.01) but feed efficiency (P > 0.13) similar to that of clean bunk-fed steers. Monensin concentration had no effect on carcass-adjusted performance (P > 0.20) in either experiment. A metabolism experiment was conducted with eight fistulated steers in a replicated 4 × 4 Latin square acidosis challenge experiment. An acidosis challenge was imposed by feeding 125% of the previous day's DMI, 4 h later than normal. Treatments consisted of monensin concentrations (mg/kg) of 0, 36.7, 48.9, or 36.7 until challenged and switched to 48.9 on the challenge day and 4 d following. Each replicate of the Latin square was managed with separate bunk management strategies (clean bunk or ad libitum). Feeding any concentration of monensin increased number of meals and decreased DMI rate (%/h) (P < 0.12) for the 4 d following the acidosis challenge. Meal size, pH change, and pH variance were lower (P < 0.10) for steers fed monensin with clean bunk management. However, no monensin effect was observed for steers fed ad libitum. Bunk management strategy has the potential to decrease DMI and ADG when steers managed on a clean bunk program are restricted relative to traditional, ad libitum bunk programs. Monensin helps control intake patterns for individuals, but increasing concentration above currently approved levels in this study seemed to have little effect.

Steers (n = 480; 22% with black hides and 78% with red hides) were used to study the effects of shade and feeding zilpaterol hydrochloride (ZH) on performance, carcass quality, heat stress, mobility, and body temperature (BT). A randomized block design with a 2 × 2 factorial treatment arrangement was used with 4 replicates per treatment. Factors included housing type (open or shaded pens) and the feeding of ZH (0 or 8.33 mg/kg DM) the last 21 d on feed with a 3-d withdrawal. Cattle were blocked by BW into a heavy or light block and randomly assigned to pen within each block. Rumen boluses to record BT were inserted before ZH feeding. Respiration rate and panting scores were recorded daily during the ZH feeding period. Mobility scores were collected at various time points from before ZH feeding through harvest. Interactions between ZH and housing type were not significant (P > 0.26) for animal performance, carcass characteristics, and respiration or panting score. No differences (P > 0.44) were observed for DMI, ADG, or G:F on a live basis due to ZH; however, cattle fed in open pens tended (P = 0.08) to have a greater ADG than cattle in shaded pens. Cattle fed ZH had 14 kg heavier carcasses with larger LM area (P < 0.01) than control cattle. Respiration rates for cattle fed ZH were greater (P = 0.05) with no differences (P = 0.88) due to housing. Time affected (P < 0.01) mobility scores, with observations on the morning of harvest at the abattoir being the worst for all groups of cattle. An interaction (P < 0.01) was observed between ZH and housing type for BT. Cattle fed ZH, in both shaded and open pens, had lower (P < 0.05) average, maximum, and area under the curve BT than control cattle fed in the same housing type. However, the observed reduction in BT due to ZH was greater for cattle fed ZH in open pens than for cattle fed ZH in shaded pens. From these results, we conclude that ZH improved HCW with little impact on heat stress or mobility, suggesting that animal welfare was not affected by feeding ZH for 21 d at the end of the feeding period. Copyright © 2015. American Society of Animal Science .

Three experiments evaluated the effects of corn oil removal using centrifugation in ethanol plants, on animal performance and digestion characteristics by finishing cattle fed by-products. In Exp. 1, 225 crossbred steers (300 ± 9.1 kg) were utilized in a randomized block design with a 2 × 2 + 1 factorial arrangement of treatments. Factors consisted of oil concentration [de-oiled (DO) or full fat (FF)] and by-product type [condensed distillers solubles (CDS) or modified distillers grains plus solubles (MDGS)] compared to a corn-based control. Fat concentration was 6.0% for DO CDS, 21.1% for FF CDS, 9.2% for DO MDGS, and 11.8% for FF MDGS. No oil concentration by by-product type interactions (P ≥ 0.17) were observed. There were no differences in DMI, ADG, or G:F between DO and FF CDS (P ≥ 0.29) or DO and FF MDGS (P ≥ 0.58). No differences (P ≥ 0.25) due to oil concentration were observed for carcass characteristics. Experiment 2 was a 5 × 5 Latin Square digestion trial with treatments similar to Exp. 1. Fat concentration was 8.7% or 15.4% for DO or FF CDS and 9.2% or 12.3% for DO or FF MDGS. Intake and total tract digestibility of fat were greater (P ≤ 0.02) for FF CDS compared with DO CDS. Digestible energy (megacalorie per kilogram), adjusted for intake, was greater (P = 0.02) for steers fed FF CDS compared to DO CDS. Average ruminal pH for cattle fed FF MDGS was greater than DO MDGS (P = 0.06). In Exp. 3, 336 yearling, crossbred steers (352 ± 19 kg) were utilized in a randomized block design with a 2 × 3 + 1 factorial arrangement of treatments. Factors included oil concentration (DO or FF) and inclusion [35%, 50%, and 65% wet distillers grains plus solubles (WDGS)] along with a corn-based control. The fat concentrations of DO and FF WDGS were 7.9% and 12.4%, respectively. A linear interaction (P < 0.01) was observed for DMI, which produced different slopes for DO and FF WDGS. No linear or quadratic interactions were observed for BW, ADG, or G:F (P ≥ 0.31). For the main effect of oil concentration, there were no statistical differences (P > 0.19) for final BW, ADG, or G:F. No statistical differences were observed for all carcass traits (P ≥ 0.34). Corn oil removal via centrifugation had minimal impact on finishing performance suggesting that cattle fed DO by-products will have similar performance to cattle fed FF by-products in dry-rolled and high-moisture corn diets.

Effects of S from wet or dry distillers grains with solubles (DGS) containing 0.82 or 1.16% S on animal growth performance, carcass characteristics, apparent total tract digestibility, and ruminal parameters were evaluated. In Exp. 1, crossbred beef steers (n = 120; 345 ± 34 kg BW) were individually fed ad libitum using Calan gates. Treatments were applied as a 2 × 2 × 3 + 1 factorial treatment arrangement with factors of DGS type (wet or dry), S content in DGS (0.82 or 1.16% DM basis), and DGS inclusion (20, 30, and 40%, DM basis), as well as a corn control diet (no DGS). In Exp. 2, ruminally cannulated crossbred beef steers (n = 6; 381 ± 31 kg BW) were assigned to 1 of 5 diets in a 5 × 6 unbalanced Latin Square design and fed ad libitum through five 14-d periods. A 2 × 2 + 1 factorial treatment arrangement was used with the factors of DGS type and S content in DGS (similar to Exp. 1). Inclusion of DGS was 40%, except for a MATCH diet containing wet 1.16% S DGS included at 31.4% (DM basis). Intake of DM decreased linearly (P < 0.01) and quadratically (P < 0.01) for steers fed wet and dry DGS that was 1.16% S, respectively. In addition, steers fed dry DGS consumed 9% more DM (P < 0.01) than those fed wet. Gain decreased linearly (P = 0.02) when wet 1.16% S DGS increased in the diet, representing a 12% drop in ADG between the Control and 40% DGS inclusion. A quadratic (P = 0.02) improvement in G:F was observed for steers fed wet DGS compared with dry, regardless of S content (P = 0.52). Feeding diets with wet 1.16% S DGS linearly decreased (P = 0.03) HCW. In Exp. 2, molar proportion of propionate declined (P = 0.01) 9% and A:P ratio tended (P = 0.13) to be greater when 1.16 compared with 0.82% S DGS was fed. Apparent total tract DMD was not affected (P > 0.16) and only subtle changes (P < 0.01) in ruminal pH parameters were observed. Greater (P = 0.02) ruminal H₂S concentration for steers fed wet compared with dry DGS was observed, while 1.16% S DGS tended (P = 0.12) to produce greater ruminal H₂S than 0.82% S. Sulfur in wet DGS appears to be more prone to be converted to ruminal H₂S, because feeding 1.16% S as wet DGS had a greater impact on ADG, DMI, and ruminal H₂S compared with dry DGS. Copyright © 2013. American Society of Animal Science .

A total of 3,632 crossbred steers were used in 3 separate randomized complete-block designed finishing experiments. Data from Exp. 1 were analyzed separately whereas data were combined for Exp. 2 and 3, based on corn processing method used [Exp.1 = equal combination of dry-rolled and high-moisture (DRC:HMC); Exp. 2 and 3 = steam-flaked (SFC)]. Steers were fed 1 of 5 treatments to evaluate the effects of monensin and tylosin in feedlot diets containing 25% corn wet distillers grains with solubles (WDGS; DM basis). Treatments included: 1) corn-based diet (no WDGS) with 360 mg/d monensin and 90 mg/d tylosin (CORN+MT), 2) 25% wet distillers grains with solubles (WDGS-CON), 3) 25% WDGS with 360 mg/d monensin (WDGS+M), 4) WDGS with monensin and tylosin at same levels as treatment 1, and 5) WDGS with 480 mg/d monensin and 90 mg/d tylosin (WDGS+HIMT). In Exp. 1, WDGS+MT increased (P < 0.01) ADG (6.5%), G:F (6.9%), and HCW (3.0%) compared with CORN+MT. Alternatively, in Exp. 2 and 3, WDGS+MT had no effect on ADG (P = 0.18), decreased (P < 0.01) G:F by 3.2%, and did not affect HCW (P = 0.57) compared with CORN+MT. In Exp. 1, addition of monensin to a WDGS diet increased G:F by 3.1% (P = 0.03) and tended to increase G:F in Exp. 2 and 3 (P = 0.09) compared with WDGS-CON. For all experiments, addition of monensin and tylosin in a diet containing WDGS increased G:F (P < 0.01) and reduced total and severe liver abscesses (P < 0.01) compared with WDGS-CON. Additionally, HCW was increased in Exp. 2 and 3 (P < 0.01) and tended to increase in Exp. 1 (P = 0.09) when monensin and tylosin were fed in a WDGS diet compared with WDGS-CON. Feeding WDGS+MT reduced total liver abscesses by 79.3% (Exp. 1) and 57.6% (Exp. 2 and 3) compared with WDGS-CON. Compared with WDGS+MT, minimal differences were observed when monensin was fed at 480 mg/steer daily with tylosin in diets containing WDGS. Inclusion of WDGS in finishing steer diets did not alter effectiveness of monensin with tylosin in improving G:F and reducing prevalence of liver abscesses, regardless of corn processing method. Corn processing method appears to be an important factor in performance response to WDGS with feeding value of WDGS, measured as an increase in feed efficiency, being greater in a DRC:HMC-based diet compared with a SFC-based diet. Copyright © 2013. American Society of Animal Science .