Estimates of global population growth are often cited as a significant challenge for global food production. It is estimated that by 2050 there will be approximately two- billion additional people on earth, with the greatest proportion of that growth occurring in central Africa. To meet recommended future protein needs (60 g/d), approximately 120 million kg of protein must be produced daily. The production of ruminant meat (particularly beef cattle) offers the potential to aid in reaching increased global protein needs. However, advancements in beef cattle production are necessary to secure the industry’s future sustainability. This article draws attention to a subset of sustainable beef cattle production challenges, including the role of ruminant livestock in meeting global human protein needs, the environmental relationships of advanced beef cattle production, and big data and machine learning in beef cattle production. Considering the significant quantities of resources necessary to produce this form of protein, such advancements are not just a moral imperative but critical to developing advanced beef cattle production practices and predictive models that will reduce costs and liabilities and advance industry sustainability.

As increasing climate variability continues to strain agricultural production, priorities must be aligned with methods to maintain or improve current production processes, including advanced, technology-based methods of measuring individual feed and water intakes and increasing water use efficiency in cattle. A total of 745 animals were evaluated in eight test groups from 11/25/19 to 9/2/21 in a dry lot equipped with In-Pen Weighing Positions and Feed and Water-Intake Nodes. Relationships among average daily gain (ADG), dry matter intake (DMI), residual feed intake (RFI), water intake (WI), residual water intake (RWI), animal performance variables, and environmental variables at the individual animal level were investigated on a first test group of Angus bulls (n = 125) and crossbred steers (n = 53). Root mean square error (RMSE) was used as a measure of error between model-predicted and observed DMI. Random Forest (RF) analysis predicted the daily DMI, with RMSE 0.92 kg for bulls and 0.85 kg for steers. When performance measures were averaged across the entire test period, the RMSE using RF were 0.39 and 0.34 kg DMI for bulls and steers, respectively. Repeated measures Analysis of Variance (RM ANOVA) was used with the same set of predictive variables as in RF. DMI was strongly related to body weight, WI, short wave radiation (MJ), and relative humidity (%; all p< 0.0001). RM ANOVA predicted the daily DMI with (RMSE) 1.5 kg for bulls and 1.41 kg for steers and 0.75 and 0.61 kg DMI for bulls and steers across the entire testing period. Study results identify relationships between DMI, WI and other growth metrics in a dry lot, which must be explored in pasture to identify biomarkers of feed and water efficiency in cattle to improve sustainability of beef production in grazing systems.

Public opinion has focused on animal agriculture being in competition with growing urban populations for land and water resources. With much of the US in drought conditions, improving water use efficiency is critical for the sustainability of animal agriculture. To date, little has been done to assess water efficiency in cattle. There is evidence for a positive relationship between water intake and DMI, but relationships between water and feed use efficiencies are likely more complex. Our objectives were to understand the magnitude of variation in water use efficiency and make comparisons with feed efficiency, as measured by residual feed intake (RFI). Our study utilized yearling bulls, steers, and heifers (n=745) between the summer of 2019 and the summer of 2021. Individual feed and water intakes were determined using a real-time feed intake system and an In Pen Weighing system (IPW). Water use efficiency, residual water intake (RWI), was calculated similarly to RFI where an expected water intake was determined for the group by regressing average daily water intake on metabolic mid-body test weight and either ADG or DMI. RWI was then calculated as actual daily water intake minus expected daily water intake. The estimation of expected water intake using DMI had a greater R2 than when ADG was used (.36-.51 vs .31-.35). The range in off-test RFI was about one order of magnitude smaller than the range of RWI (e.g., RFI -0.90 to 0.73 kg vs RWI -7.34 to 8.49 L), indicating greater variability in water intake compared with feed intake and a relationship among DMI, ADG, and RWI that needs to be further explored. As animal agriculture strives to be more sustainable, water use efficiency needs to become a common measure and genetic progress needs to be made. There appears to be sufficient variation in the trait to make this feasible.

No abstract

Technology that facilitates estimations of individual animal dry matter intake rates in group-housed settings will improve production and management efficiencies. Estimating dry matter intake in pasture settings or facilities where feed intake cannot be monitored may benefit from predictive algorithms that use other variables as proxies. This study examined the relationships between dry matter intake (DMI), animal performance, and environmental variables. Here we determined whether a machine learning approach can predict DMI from measured water intake variables, age, sex, full body weight, and average daily gain (ADG). Two hundred and five animals were studied in a drylot setting (152 bulls for 88 days and 53 steers for 50 days). Collected data included daily DMI, water intake, daily predicted full body weights, and average daily gain using In-Pen-Weighing Positions and Feed Intake Nodes. After exclusion of 26 bulls of low-frequency breeds and one severe (greater than 3 standard deviations) outlier, the final number of animals used for modeling were 178 (125 bulls, 53 steers). Climate data were recorded at 30-minute intervals throughout the study period. Random Forest Regression (RFR) and Repeated Measures Random Forest (RMRF) were used as a machine learning approaches to develop a predictive algorithm. Repeated Measures ANOVA (RMANOVA)was used as the traditional approach. Using the RMRF method, an algorithm was constructed that predicts an animal’s DMI within 0.75 kg. Evaluation and refining of algorithms used to predict DMI in drylot by adding more representative data will allow for future extrapolation to controlled small plot grazing and, ultimately, more extensive group field settings.