Search

The lack of real-life experiences, such as handling livestock at a production facility (e.g., ranch), exists for a variety of reasons such as availability, liability, time, and cost, amongst others. As more students enter undergraduate animal science programs without prior exposure to animal handling, the necessity for more hands-on, real-life experiences has increased dramatically. Complementary, educational simulation games (edugames) might provide means to overcome the lack of "hands-on" experiential learning by providing similar interactions in a virtual context. The primary goal of this study was to document the design and construction phase of a virtual cattle-handling simulation (CowSim) edugame, and to analyse preliminary survey data. An association exists between students' notion of cattle being mishandled (or not) depending on students' previous opportunity to work with animals (X[superscript 2]P value = 0.0017). Furthermore, students with previous experience handling cattle did not feel more prepared to handle cattle after playing CowSim, but students with previous experience handling cattle indicated they learned more about cattle handling after playing CowSim. After playing the CowSim game, students were, in general, optimistic about their playing experience. They perceived the CowSim game was realistic enough to increase their preparedness towards handling cattle. Our findings suggested there is heightened interest was for the use of an edugame to help visualize difficult concepts. Virtual learning tools such as the CowSim edugame are essential for advancing animal science education through the integration of virtual technology. However, improvements are warranted in the CowSim to capture more realistic scenarios given the complexity of the simulation game.

Simple Summary: In this study, we wanted to find the best way to predict the overall chemical composition of Boer × Saanen male kids by evaluating different parts of their bodies. We conducted two experiments where goats were fed different intake levels and slaughtered at various weights. We used various body parts such as the neck, ribs, leg, shoulder, loin, hide, head + feet, and organs to see which ones best estimate the whole body composition regarding nutrients such as fat, protein, and minerals. We found that the neck, loin, and 9–11th ribs could precisely predict the body composition. However, using the loin or 9–11th ribs to do this can lower the price one can obtain from selling the meat because they are valuable parts of the carcass. Our study suggests that the neck can be used as effectively as the 9–11th ribs to estimate the chemical body composition. This finding is useful for farmers, nutritionists, and meat processors as it helps them choose a cost-effective method for evaluating body composition without sacrificing valuable parts of the goat carcass. Two experiments were conducted to determine which part of the empty body of Boer × Saanen intact male kids can be used to predict the chemical composition of the whole body. In the first experiment, kids were fed ad libitum and slaughtered at 5, 10, and 15 kg body weight (BW). Eighteen animals were group-fed at three intake levels (ad libitum or restricted to 30% and 60% of the ad libitum level). When the ad libitum animal in the group reached 15 kg BW, all animals in the group were slaughtered. In the second experiment, kids were fed ad libitum and slaughtered at 15, 20, and 25 kg BW. Twenty-one animals were group-fed at three intake levels and slaughtered when the ad libitum animal within the group reached 25 kg BW. Analyzed body parts included head + feet, hide, organs, neck, shoulder, ribs, loin, leg, 9–11th ribs, and half carcass. Principal component and cluster analyses showed that the neck, 9–11th ribs, and loin had the highest frequency of grouping with the empty body. These body parts were used to develop prediction models for estimating body composition. The neck, loin, and 9–11th ribs accurately and precisely predicted the dry matter, ash, fat, protein, and energy body composition of goats, with most models also incorporating BW as a predictor variable. The equations showed root mean squared error (RMSE) lower than 13.5% and a concordance correlation coefficient (CCC) greater than 0.84. Fat and protein concentrations in the loin and neck were also reliable predictors of empty body energy composition (RMSE = 2.9% of mean and concordance correlation coefficient = 0.93). Removing the loin and 9–11th ribs could reduce the carcass retail price. Using the neck to estimate body composition in growing Boer × Saanen goats provides a valuable alternative for nutrition studies, given its low commercial value. [ABSTRACT FROM AUTHOR]

We used systems thinking (ST) to identify the critical components of beef cattle production through the lens of ecosystem services (ES), offering a holistic approach to address its adverse externalities. We identified eight critical feedback loops in beef production systems: (i) grazing and soil health, (ii) manure management and soil fertility, (iii) feed efficiency and meat production, (iv) water use and soil moisture, (v) cultural services and community engagement, (vi) energy use, (vii) carbon sequestration and climate regulation, and (viii) environmental impact. Our analysis reveals how these interconnected loops influence each other, demonstrating the complex nature of beef production systems. The dynamic hypothesis identified through the loops indicated that improved grazing and manure management practices enhance soil health, leading to better vegetation growth and cattle nutrition, which, in turn, have a positive impact on economic returns to producers and society, all of which encourage the continuation of interlinked beef and ecosystem stewardship practices. The management of beef production ES using ST might help cattle systems across the globe to contribute to 9 of the 17 different United Nations' Sustainable Development Goals, including the "zero hunger" and "climate action" goals. We discussed the evaluation framework for agrifood systems developed by the economics of ecosystems and biodiversity to illustrate how ST in beef cattle systems could be harnessed to simultaneously achieve the intended environmental, economic, social, and health impacts of beef cattle systems. Our analysis of the literature for modeling and empirical case studies indicates that ST can reveal hidden feedback loops and interactions overlooked by traditional practices, leading to more sustainable beef cattle production outcomes. ST offers a robust framework for enhancing ES in beef cattle production by recognizing the interconnectedness of ecological and agricultural systems, enabling policymakers and managers to develop more effective and sustainable strategies that ensure the long-term health and resilience of humans and ES. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurate and precise predictions of microbial crude protein (MCP) synthesis are crucial to predicting the supply of metabolizable protein in cattle. Inaccurate estimates of MCP can lead to over- or underfeeding of protein in beef cattle diets, which can have important animal performance and economic consequences. Extant MCP prediction equations are generally based on the intake of energy (e.g., total digestible nutrients (TDN) or digestible energy) and protein. We developed new equations based on the intake of organic matter, which yielded similar fit statistics to the extant equations for observed vs. predicted values, but the precision of all MCP predictions was less than desired, with errors averaging more than 28% of the observed mean. A simple approach of calculating MCP as 10% of the TDN intake was as effective as more complex equations. To move forward and improve the accuracy and precision of MCP prediction equations, research is needed to develop consistent and more precise techniques to measure MCP synthesis in cattle that will yield reliable estimates across a wide range of diets and production situations. Meta-omics tools might be a useful component of these new methods, but additional research is needed. Predictions of microbial crude protein (MCP) synthesis for beef cattle generally rely on empirical regression equations, with intakes of energy and protein as key variables. Using a database from published literature, we developed new equations based on the intake of organic matter (OM) and intakes or concentrations of crude protein (CP) and neutral detergent fiber (NDF). We compared these new equations to several extant equations based on intakes of total digestible nutrients (TDN) and CP. Regression fit statistics were evaluated using both resampling and sampling from a simulated multivariate normal population. Newly developed equations yielded similar fit statistics to extant equations, but the root mean square error of prediction averaged 155 g (28.7% of the mean MCP of 540.7 g/d) across all equations, indicating considerable variation in predictions. A simple approach of calculating MCP as 10% of the TDN intake yielded MCP estimates and fit statistics that were similar to more complicated equations. Adding a classification code to account for unique dietary characteristics did not have significant effects. Because MCP synthesis is measured indirectly, most often using surgically altered animals, literature estimates are relatively few and highly variable. A random sample of individual studies from our literature database indicated a standard deviation for MCP synthesis that averaged 19.1% of the observed mean, likely contributing to imprecision in the MCP predictions. Research to develop additional MCP estimates across various diets and production situations is needed, with a focus on developing consistent and reliable methodologies for MCP measurements. The use of new meta-omics tools might improve the accuracy and precision of MCP predictions, but further research will be needed to assess the utility of such tools. [ABSTRACT FROM AUTHOR]

This review delves into the intricate realm of ruminal microbes, shedding light on their complexity beyond previously recognized dimensions. Existing publications have probed the essential facets of these microorganisms on a finer scale than previously acknowledged. Mathematical models have emerged to simulate the behavior of approximately 200 distinct bacterial species, 25 genera of ciliate protozoa, and five genera of anaerobic fungi, constituting about 10% of the total viable bacteria in the rumen. However, the expansive diversity and density of rumen microbes challenge the complete characterization of species or genera in relation to substrates or end products. Consequently, continuous revision and re-engineering of mathematical models become imperative. In the context of ruminants, prevalent models often categorize bacteria into fiber-fermenting and nonfiber-fermenting groups. An additional subgroup featuring hyper-ammoniaproducing bacteria has been proposed, but its explicit integration into nutrition models remains unexplored. Furthermore, incorporating a more mechanistic evaluation of protozoa and fungal growth may be warranted to improve nutrition models. The time horizon and intervals at which models are constructed present another critical consideration, with feed efficiency variations among ruminants believed to be closely tied to differences in the ruminal microbiota. Addressing immediate concerns, this review underscores the need for a comprehensive exploration of factors influencing microbial growth in the rumen. Several indices have been suggested and adopted to predict microbial efficiencies, but they may provide simplification for practical application. Thus, a mechanistic approach should be considered to remove dependencies between estimates and improve predictive accuracy and precision. While artificial intelligence holds promise in elucidating gaps within empirical and mechanistic models, the generation of accurate, vetted datasets is paramount. Furthermore, this review posits that factors such as recycled nitrogen, endotoxins, and microbial population dynamics (i.e., cross-feeding and competition) may be limiting our understanding of microbial growth, suggesting the necessity of modeling these intricacies concurrently to achieve a more nuanced comprehension. This multifaceted approach aims to propel the understanding of ruminal microbial dynamics into new frontiers, paving the way for more informed and effective modeling in the future. [ABSTRACT FROM AUTHOR]

Considering the growing accessibility of dried distillers grains with solubles (DDGS) in Brazil, coupled with the limited research examining its integration into conventional confinement diets in the southeast region, comprising ingredients such as flint corn, citrus pulp, and whole cottonseed, there is a clear imperative for conducting studies to deter- mine optimal inclusion levels of this product in such diets. The objective of the study was to compare the performance (experiment 1) and metabolism (experiment 2) of Nellore bulls finished with diets containing 0, 10, 20, 30, or 40% DDGS (% DM) in total replacement of whole cottonseed and partial replacement of ground flint corn and citrus pulp. In experiment 1, Nellore bulls [n = 368; body weight (BW) = 420 ± 30 kg] were used, allocated in 60 experimental pens for 125 d (n = 12 pens per treatment), evaluating variables such as dry matter intake, average daily gain (ADG), feed efficiency, observed net energy (NE) for maintenance and gain, and carcass characteristics. In experiment 2, rumen-cannulated Nellore bulls (n = 30; BW = 503 ± 46) were kept in individual pens for 21 d (n = 6 animals per treatment), evaluating ruminal parameters (proportion of short-chain fatty acids, ammonia concentration, ruminal pH) and apparent digestibility of nutrients in the total tract. The experimental design adopted was randomized blocks, and the data were analyzed using R v. 4.3.1 (R Core Team, 2023). Linear increases were observed in carcass adjusted final BW (P = 0.013), carcass adjusted ADG (P = 0.024), carcass adjusted feed efficiency (P = 0.0003), hot carcass weight (P = 0.0004), and dressing percentage (P < 0.0001) with the incremental inclusion of DDGS in the diets (Table 1). For every 10-percentage unit inclusion in these type of diets, hot carcass weight is increased by 2.56 kg. Additionally, the inclusion of DDGS resulted in linear increases in observed NE for maintenance (P = 0.001) and NE for gain (P = 0.001), calculated according to Zinn and Shen (1998). Digestibility out- comes, determined through the difference of nutrients present in the consumed diet and in the feces, exhibited linearly decreasing effects with the escalating inclusion of DDGS for dry matter (P = 0.004), organic matter (P = 0.004), neutral detergent fiber (P = 0.01), acid detergent fiber (P = 0.04), and total digestible nutrients (P = 0.004). We also observed linear increases for isobutyrate (P = 0.004) and isovalerate (P = 0.002) as the DDGS level in the diet increased. The 40% DDGS diet exhibited 0.6 mmol/100 mol and 0.7 mmol/100 mol more of isobutyrate and isovalerate, respectively, compared with the 0% DDGS diet. In summary, a high inclusion of DDGS emerges as a viable alternative in the nutrition of Bos indicus cattle fed diets containing ground flint corn and citrus pulp, manifesting significant improvements in performance and carcass quality. [ABSTRACT FROM AUTHOR]

The inclusion of the coproduct dry distil- lers grains plus soluble (DDGS) in the diet of finishing cattle can lead to changes in the nutritional profile of the diets, causing an increase in protein content and a reduction in starch. It is necessary to understand how changes in rumen substrates affect rumen metabolic activity, acids, and enteric methane (CH4) production. Five treatments were used, considering levels of DDGS inclusion in the dry matter (DM) of 1) 0 g/kg of DDGS, 2) 150 g/kg of DDGS, 3) 300 g/kg of DDGS, 4) 450 g/kg DDGS, or 5) 600 g/kg DDGS in finishing diets. The metabolism experiment was conducted with rumen-cannulated Nellore bulls (n = 20) with initial body weight (BW) of 401.8 ± 27.0 kg. The production of short-chain fatty acids (SCFA) and CH4 were determined using the ex-situ ruminal fermentation technique. Rumen content was manually collected from 0, 4, 8 and 12 h post-feeding. The liquid and solid fractions of rumen content were used in four 50 mL penicillin-type flasks per animal. Of the four flasks prepared, two are called “blank” and inactivated in boiling water to stop fermentation, and the other two (microrumen) are incubated in a thermostatic bath, simulating the conditions existing in the rumen of animals (presence of microorganisms, anaerobes, temperature of 39ºC, natural animal saliva, physiological pH) for 30 min. After 30 min, incubated flasks were also inactivated in boiling water to stop fermentation. Subsequently, measurements of the final products of rumen fermentation (SCFA and CH4) were carried out in each bottle. Total rumen emptying was performed to determine the rumen pool of DM. The data will be analyzed in the SAS software, the mean of the treatments will be compared using test of mean and orthogonal contrasts. The declared significance is P ≤ 0.05. The inclusion or levels of DDGS did not affect CH4 production of gּ·kg DM-1ּ·d-1ּ and gּ·kg DM-1ּ d-1ּ (P > 0.05). There was an effect of the treatments on the production of propionate (gּ·kg DM-1ּ d-1ּ; P = 0.0448), with a decreasing linear effect (P = 0.0087) with the increase in the inclusion of DDGS in diet (0; 150; 300; 450; 600 g/kg of DDGS; means 137.20; 160.32; 117.60; 87.09; 91.52 gּ·kg DM-1ּ d-1ּ propionate, respectively). There was no effect of DDGS levels on the production of Acetate, Butyrate, or total SCFAs (gּ·kg DM-1ּ d-1ּ). In summary, DDGS inclusion affects rumen metabolic activity, decreasing propionate production, but does not affect the production of other SCFAs nor CH4 production. [ABSTRACT FROM AUTHOR]

Integrating tannin extracts (TE) into the diet of growing and finishing beef cattle has shown promise in optimizing protein utilization while potentially mitigating methane emissions. Despite these potential benefits, there is a notable gap in a comprehensive analysis of the influence of TE on growth rate. This study addressed this gap by collecting data on the supplementation of a blend of condensed (from Schinopsis spp.) and hydrolyzable (from Castanea spp.) tannins, which has about 70% total tannins, and its impact on critical metrics, such as average daily gain (ADG, kg/d), dry matter intake (DMI, kg/d), and feed efficiency ratio (FER, g/kg). Our objective was to conduct meta-regression analyses to understand better the nuanced effects of condensed tannin supplementation on the overall performance of beef cattle during the critical stages of growth and finishing. The dataset was constructed by collecting published studies that reported in vivo experimental data on growing and finishing beef cattle supplemented with different levels of TE. It contained 132 observations from 35 publications. The meta-analysis was conducted by linear regression with a mixed-effects model fitted by the restricted maximum likelihood method using the nlme package of R software (ver. 4.3.1). Studies were assumed as random variables, and their interaction with the intercept and slope were included in the regression. The number of animals per treatment was used as a study-specific weight. Studies accounted for 32%, 35%, or 27% of the total variance when regressing ADG, DMI, or FER, respectively, on TE (% DM). After adjusting for random effects, the ADG increased (P < 0.001) with increasing levels of dietary TE (P < 0.001): 1.344 (± 0.0071) + 0.240 (±0.0298) × TE (n = 99, r2 = 0.40). It was observed that as the dietary TE level increased, its impact on the ADG tended to decrease from 0.33 kg d-1 % TE-1 when fed up to 0.5% TE to 0.24 kg d-1 % TE-1 when fed up to 1.5% TE, suggesting a possible nonlinear relationship between these two variables. Similarly, DMI decreased slightly (P < 0.001) at 0.61 kg/d/% TE, but with a lower precision (n = 115, r² = 0.14). Consequently, FER increased (P < 0.001) at 17 kg d-1 % TE-1 (n = 93, r² = 0.34). Initial findings suggest that incorporating TE into the diet of growing and finishing cattle, up to a concentration of 0.5% DM, positively influences the growth rate and enhances FER while minimally affecting DMI. Subsequent research endeavors should delve into a more intricate examination of optimal TE inclusion levels and explore additional performance indicators for a comprehensive understanding of its impact. [ABSTRACT FROM AUTHOR]

Agent-based modeling (ABM) is a powerful tool that offers the flexibility to represent the stochasticity exhibited by swine systems due to individual animal nutritional requirements. ABM can also accurately mimic the biological dynamic growth performance of pigs. Addressing and simulating the biological growth dynamics enables precision nutrition and sustainable production management. To realistically replicate the nutrient requirement and growth performance of growing-finishing pigs, we developed an ABM based on the principles and equations from the eleventh Swine Nutrient Requirement Council Model. Each individual pig (agent) in the model had a starting weight of 20 kg and a fixed finishing weight of 140 kg, with a variable number of days on feed. Our model considers three sexes: gilt, barrow, and intact male. Pigs move through the farm, feed, and interact with the environment. Our model dynamically simulates the complex interactions between feed intake, metabolism, and growth processes of growing pigs, thereby being a virtual visualizable growing-finishing swine farm (Figure 1). The basic parameters of the biological growth of pigs, including the body weight, feed intake, metabolizable energy (ME) intake, maintenance ME requirements, protein deposition (Pd), lipid deposition (Ld), and probe backfat thickness Figure 2), were modeled based on NRC equations. In addition to the above parameters, the daily amino acid, calcium (Ca), and phosphorus (P) requirements for individual pigs were calculated daily. To demonstrate ABM responsiveness to feeding strategies, ractopamine supplementation is included to evaluate the impact on protein deposition. The ABM offers more personalized nutrition management by considering unique pig growth potential and nutritional needs based on characteristics such as age and sex, which can lead to improved growth performance and feed efficiency. Besides, the ABM enables the modeling of population-level dynamics and the evaluation of different feeding scenarios to optimize growth outcomes by allocating optimized feed based on individual nutritional needs. Our ABM will be used to test different feeding management strategies and scenarios, providing valuable insights into the impact of various factors on pig nutrition and growth outcomes while minimizing both time and financial expenditures. Our ABM aims to provide a robust framework for simulating and optimizing feeding strategies and enhancing overall pig production efficiency by leveraging the comprehensive and scientifically validated guidelines provided in the NRC. To verify the accuracy and reliability of the proposed ABM, the results generated by the model were rigorously evaluated and compared with the NRC model results. The results demonstrated a highly satisfactory prediction performance by our ABM, paving the way for more real-time decisions to be made for daily feed management on growing-finishing swine operations. [ABSTRACT FROM AUTHOR]

Western rangelands represent approximately 58% of the total arable land in the U.S. and are used primarily for cow-calf production, which has the largest greenhouse gas (GHG) emission footprint of all beef production phases. Further, beef production sustainability concerns involve climate mitigation (reducing GHG output) and adaptation (climate-resilient soil-plant-animals). Precision livestock farming (PLF) may help address sustainability concerns by providing innovative solutions and new opportunities for extensive rangeland production. The use of precision measurement and management tools with precision system models can connect measurement data to inform management capabilities. For example, real-time individual weighing and remote sensing (precision measurement tools) can be used to inform and implement dynamic rotational grazing management using virtual fencing technology (precision management; Menendez et al., 2022, 2023). Recent USDA investment in climatesmart agriculture (CSA) commodities has provided over $3 billion in funding to implement practices to reduce GHG emissions in agriculture production, for which PLF may be one approach to accomplish these goals. The overall purpose is to develop commodities produced using NRCS climate-smart practices (e.g., prescribed grazing, 528) and document reductions to provide market opportunities associated with inset GHG. Currently, South Dakota State University is leading two simultaneous programs, which include precision ranching (virtual fencing, precision weighing, and GHG evaluation) and a beef and bison CSA program (GHG evaluation; 7 producer-owned research ranches, representing more than 1.09 million ha). The scale of the CSA program has revealed that current PLF research has only been a prelude to providing the precision tools necessary to successfully implement CSA practices and document their impact through monitoring, measuring, reporting, and verification (MMRV). This presentation will include rangeland grazing case studies that cover the application of virtual fencing, animal location, behavior tracking, remote sensing, precision weighing, feeding, supplementation, and enteric emissions and soil moisture monitoring on extensive rangelands. Case studies will include an overview of big data processing and precision system model development methods. Increasing awareness of available PLF tools for optimizing grazing management, animal performance, productivity, and associated challenges (maintenance, costs) is essential for meeting livestock and sustainability goals. PLF and data-driven approaches aid in the creation of scalable, cost-effective MMRV protocols and models (soil carbon and enteric GHG) for extensive rangelands (20 to 70,000 ha areas) that allow producers to realize potential CSA market incentives. Further, MMRV will likely help guide management decisions by identifying CSA strategies that build climate-resilient landscapes for sustainable livestock production and other environmental synergies (soil microbiome, bird and insect habit, water retention). [ABSTRACT FROM AUTHOR]

This article provides a science-based, data-driven perspective on the relevance of the beef herd in the U.S. to our society and greenhouse gas (GHG) contribution to climate change. Cattle operations are subject to criticism for their environmental burden, often based on incomplete information disseminated about their social, economic, nutritional, and ecological benefits and detriments. The 2019 data published by the U.S. Environmental Protection Agency reported that U.S. beef cattle emitted 22.6% of the total agricultural emissions, representing about 2.2% of the total anthropogenic emissions of CO2 equivalent (CO2e). Simulations from a computer model developed to address global energy and climate challenges, set to use extreme improvements in livestock and crop production systems, indicated a potential reduction in global CO2e emissions of 4.6% but without significant enhancement in the temperature change by 2030. There are many natural and anthropogenic sources of CH4 emissions. Contrary to the increased contribution of peatlands and water reservoirs to atmospheric CO2e, the steady decrease in the U.S. cattle population is estimated to have reduced its methane (CH4) emissions by about 30% from 1975 to 2021. This CH4 emission deacceleration of 2.46 Mt CO2 e/yr2 might be even more significant than reported. Many opportunities exist to mitigate CH4 emissions of beef production, leading to a realistic prospect of a 5% to 15% reduction in the short term after considering the overlapping impacts of combined strategies. Reduction strategies include feeding synthetic chemicals that inactivate the methyl-coenzyme M reductase (the enzyme that catalyzes the last step of methanogenesis in the rumen), red seaweed or algae extracts, ionophore antibiotics, phytochemicals (e.g., condensed tannins and essential oils), and other nutritional manipulations. The proposed net-zero concept might not solve the global warming problem because it will only balance future anthropogenic GHG emissions with anthropogenic removals, leaving global warming on a standby state. Recommendations for consuming red meat products should consider human nutrition, health, and disease and remain independent of controversial evidence of causational relationships with perceived negative environmental impacts of beef production that are not based on scientific data. [ABSTRACT FROM AUTHOR]

Constructing dynamic mathematical models of biological systems requires estimating unknown parameters from available experimental data, usually using a statistical fitting procedure. This procedure is usually called parameter identification, parameter estimation, model fitting, or model calibration. In animal science, parameter identification is often performed without analytic considerations on the possibility of determining unique values of the model parameters. These analytical studies are related to the mathematical property of structural identifiability, which refers to the theoretical ability to recover unique values of the model parameters from the measures defined in an experimental setup and use the model structure as the sole basis. The structural identifiability analysis is a powerful tool for model construction because it informs whether the parameter identification problem is well-posed (i.e., the problem has a unique solution). Structural identifiability analysis is helpful to determine which actions (e.g., model reparameterization, choice of new data measurements, and change of the model structure) are needed to render the model parameters identifiable (when possible). The mathematical technicalities associated with structural identifiability analysis are very sophisticated. However, the development of dedicated, freely available software tools enables the application of identifiability analysis without needing to be an expert in mathematics and computer programming. We refer to such a non-expert user as a practitioner for hands-on purposes. However, a practitioner should be familiar with the model construction and software implementation process. In this paper, we propose to adopt a practitioner approach that takes advantage of available software tools to integrate identifiability analysis in the modeling practice in the animal science field. The application of structural identifiability implies switching our regard of the parameter identification problem as a downstream process (after data collection) to an upstream process (before data collection) where experiment design is applied to guarantee identifiability. This upstream approach will substantially improve the workflow of model construction toward robust and valuable models in animal science. Illustrative examples with different levels of complexity support our work. The source codes of the examples were provided for learning purposes and to promote open science practices. [ABSTRACT FROM AUTHOR]

Over the last three decades, agent-based modeling/model (ABM) has been one of the most powerful and valuable simulation-based decision modeling techniques used to study the complex dynamic interactions between animals and their environment. ABM is a relatively new modeling technique in the animal research arena, with immense potential for routine decision-making in livestock systems. We describe ABM’s fundamental characteristics for developing intelligent modeling systems, exemplify its use for livestock production, and describe commonly used software for designing and developing ABM. After that, we discuss several aspects of the developmental mechanics of an ABM, including (1) how livestock researchers can conceptualize and design a model, (2) the main components of an ABM, (3) different statistical methods of analyzing the outputs, and (4) verification, validation, and replication of an ABM. Then, we perform an overall analysis of the utilities of ABM in different subsystems of the livestock systems ranging from epidemiological prediction to nutritional management to livestock market dynamics. Finally, we discuss the concept of hybrid intelligent models (i.e., merging real-time data streams with intelligent ABM), which have applications in artificial intelligence-based decision-making for precision livestock farming. ABM captures individual agents’ characteristics, interactions, and the emergent properties that arise from these interactions; thus, animal scientists can benefit from ABM in multiple ways, including understanding system-level outcomes, analyzing agent behaviors, exploring different scenarios, and evaluating policy interventions. Several platforms for building ABM exist (e.g., NetLogo, Repast J, and AnyLogic), but they have unique features making one more suitable for solving specific problems. The strengths of ABM can be combined with other modeling approaches, including artificial intelligence, allowing researchers to advance our understanding further and contribute to sustainable livestock management practices. There are many ways to develop and apply mathematical models in livestock production that might assist with sustainable development. However, users must be experienced when choosing the appropriate modeling technique and computer platform (i.e., modeling development tool) that will facilitate the adoption of mathematical models by certifying that the model is field-ready and versatile enough for untrained users. [ABSTRACT FROM AUTHOR]

Several ruminant animals rely almost exclusively on the complex polysaccharide matrix from the plant cell wall (CW) as their primary energy source via volatile fatty acids produced through ruminal and some hindgut fermentation processes. The CW contains different types and proportions of polysaccharides, proteins, phenolic compounds, and minerals in their macromolecular structure that influence the rate and extent of fiber digestion and selective retention of particulate matter due to its physical characteristics (buoyancy and comminuting) in the reticulorumen. The biosynthetic formation of the CW dictates possible manipulation mechanisms (targeted plant and microbes selection) and processing methods (physical, chemical, microbial, and enzymatic treatments and the use of genetically engineered bacteria) to increase its digestibility, leading to better utilization of the CW by the ruminant animal and hopefully lower the contribution of ruminants’ greenhouse gas emissions. Early studies on lignin biosynthesis have led to more advanced studies focusing on replacing traditional monolignols with homopolymers that are easier to deconstruct or degrade. Concurrently, laboratory methods must be developed, evaluated, and modified to accurately reflect the digestibility and nutritive value of CW brought about by modern manipulation mechanisms or processing methods. However, the laboratory methods must also be reliable, precise, feasible, trivial, easy to implement, and cost-effective, but at the same time environmentally friendly and aware. For instance, although the acid detergent lignin has been demonstrated to behave uniformly as a nutritional entity, its chemical determination and association with carbohydrates still lack consensus. Spectroscopy (near-infrared and Raman) and in vitro gas production techniques have been adopted to assess plant chemical composition and nutritive value, but an incomplete understanding of the impacts caused by disrupting the CW for sample processing still exists. Different variations of multicompartmental and time- and age-dependent mathematical models have been proposed to determine the ruminal rates of degradation and passage of fiber. However, low-quality and incomplete data due to inconsistent marker results used to determine passage rates and transit time of fiber in the gastrointestinal tract have hindered advancements and adoptions of the next generation of computer models to understand ruminal fiber degradation. [ABSTRACT FROM AUTHOR]

Advancements in precision livestock technology have resulted in an unprecedented amount of data being collected on individual animals. Throughout the data analysis chain, many bottlenecks occur, including processing raw sensor data, integrating multiple streams of information, incorporating data into animal growth and nutrition models, developing decision support tools for producers, and training animal science students as data scientists. To realize the promise of precision livestock management technologies, open-source tools and tutorials must be developed to reduce these bottlenecks, which are a direct result of the tremendous time and effort required to create data pipelines from scratch. Open-source programming languages (e.g., R or Python) can provide users with tools to automate many data processing steps for cleaning, aggregating, and integrating data. However, the steps from data collection to training artificial intelligence models and integrating predictions into mathematical models can be tedious for those new to statistical programming, with few examples pertaining to animal science. To address this issue, we outline how open-source code can help overcome many of the bottlenecks that occur in the era of big data and precision livestock technology, with an emphasis on how routine use and publication of open-source code can help facilitate training the next generation of animal scientists. In addition, two case studies are presented with publicly available data and code to demonstrate how open-source tutorials can be utilized to streamline data processing, train machine learning models, integrate with animal nutrition models, and facilitate learning. The National Animal Nutrition Program focuses on providing research-based data on animal performance and feeding strategies. Open-source data and code repositories with examples specific to animal science can help create a reinforcing mechanism aimed at advancing animal science research. [ABSTRACT FROM AUTHOR]

Static quantification measures of chemical components are commonly used to make certain assumptions about forage or feed nutritive value and quality. In order for modern nutrient requirement models to estimate intake and digestibility more accurately, kinetic measures of ruminal fiber degradation are necessary. Compared to in vivo experiments, in vitro (IV) and in situ (IS) experimental techniques are relatively simple and inexpensive methods to determine the extent and rate of ruminal fiber degradation. This paper summarizes limitations of these techniques and statistical analyses of the resulting data, highlights key updates to these techniques in the last 30 yr, and presents opportunities for further improvements to these techniques regarding ruminal fiber degradation. The principle biological component of these techniques, ruminal fluid, is still highly variable because it is influenced by ruminally fistulated animal diet type and timing of feeding, and in the case of the IV technique by collection and transport procedures. Commercialization has contributed to the standardization, mechanization, and automation of the IV true digestibility technique, for example, the well-known DaisyII Incubator. There has been limited commercialization of supplies for the IS technique and several review papers focused on standardization in the last 30 yr; however, the IS experimental technique is not standardized and there remains variation within and among laboratories. Regardless of improved precision resulting from enhancements of these techniques, the accuracy and precision of determining the indigestible fraction are fundamental to modeling digestion kinetics and the use of these estimates in more complex dynamic nutritional modeling. Opportunities for focused research and development are additional commercialization and standardization, methods to improve the precision and accuracy of indigestible fiber fraction, data science applications, and statistical analyses of results, especially for IS data. In situ data is typically fitted to one of a few first-order kinetic models, and parameters are estimated without determining if the selected model has the best fit. Animal experimentation will be fundamental to the future of ruminant nutrition and IV and IS techniques will remain vital to bring together nutritive value with forage quality. It is feasible and important to focus efforts on improving the precision and accuracy of IV and IS results. [ABSTRACT FROM AUTHOR]

Monensin and virginiamycin are included in beef cattle finishing diets as prophylaxis to minimize the incidence of ruminal acidosis and liver abscesses. Due to different and probably complementary modes of action, this study aimed to determine the effects of a combination of monensin and virginiamycin, both included in the diet at recommended doses, on ruminal health, the occurrence of liver abscesses, and growth performance of feedlot-finished cattle. One hundred and forty-four steers (6 animals/pen) were fed 1 of 3 corn-based finishing diets containing 30 mg of monensin (MN), 25 mg of virginiamycin (VM), or 30 and 25 mg of monensin and virginiamycin (MN + VM), respectively, per kilogram of dry matter. Ruminal pH probes were inserted into two animals per pen and set to record pH every 10 min. On d 100, animals were slaughtered, and rumens and livers were recovered, on which occurrence and degree of ruminal damage, prevalence and number of liver abscesses, and liver scores (A−: livers with no more than two small abscesses; A+: livers with at least one large abscess or more than four medium abscesses; A: any other abscessed liver) were determined. Simultaneous inclusion of monensin and virginiamycin resulted in a 4.3% decrease (P < 0.04) in dry matter intake (DMI ; 8.8, 9.2, and 9.2 ± 0.19 kg/d for MN + VM, MN, and VM-fed animals, respectively) and similar (P > 0.13) average daily body weight gain (ADG ; 1.49 ± 0.021 kg/d) and hot carcass weight (HCW ; 269 ± 1.7 kg), compared with feeding diets containing one additive or the other. Therefore, in terms of ADG, a 9.4% improvement (P < 0.01) in feed efficiency was observed in MN + VM-fed animals. Backfat thickness (5.6 ± 0.08 mm) and ribeye area (69.9 ± 0.53 cm2) remained unaffected (P ≥ 0.74), as well as the minimum (4.98 ± 0.047), mean (6.11 ± 0.037), and maximum ruminal pH (7.23 ± 0.033) values and the time (125 ± 22.3 min/d), area (57.67 ± 12.383 pH × h), and episodes (22 ± 3.8 bouts) of pH below 5.6 (P ≥ 0.12). Overall, prevalence (24 ± 3.4%) and the number of liver abscesses (1.6 ± 0.14 abscesses/abscessed liver), liver scores (20 ± 3.1% of A− and 4 ± 1.8% of A livers), and prevalence (67 ± 3.5%) and degree of damage to the ruminal epithelium (2.5 ± 0.22% affected surface) were similar (P ≥ 0.18) across treatments; however, the occurrence of ruminal lesions tended (P ≤ 0.07) to be associated with that of liver abscesses and reduced ADG when feeding monensin alone. [ABSTRACT FROM AUTHOR]

Quantum computing (QC) is not a futuristic notion in agriculture, though its full potential has yet to be realized. QC is an emerging field at the intersection of physics and computer science that holds immense potential to revolutionize various sectors, including agriculture production and artificial intelligence (AI) modeling. While QC is still in the early stages of development and practical applications within agriculture are not yet widespread, researchers are actively exploring its potential benefits in various agricultural domains, including crop optimization, livestock breeding, and environmental monitoring. QC harnesses the principles of quantum mechanics to perform computations using quantum bits or qubits, which can exist in multiple states simultaneously. Unlike classical computers, which rely on binary bits representing 0 or 1, quantum computers exploit phenomena such as superposition and entanglement to process information in parallel, potentially offering exponential speedup for certain types of problems. In agriculture production, particularly in animal science, QC offers promising avenues for optimizing processes and enhancing productivity. Quantum algorithms can analyze vast amounts of genomic data to improve breeding programs, leading to the development of more resilient and productive livestock breeds. Furthermore, QC can facilitate precision farming techniques by modeling complex environmental factors and animal behavior to optimize feeding strategies, disease management, and overall farm management practices. Moreover, QC can significantly benefit AI modeling by accelerating computations and enabling more efficient training of AI models. Quantum algorithms can enhance the performance of AI algorithms in various tasks, including pattern recognition, natural language processing, and predictive analytics. By leveraging quantum-enhanced optimization algorithms, AI models can achieve better convergence and accuracy, leading to more effective decision-making and problem-solving capabilities. While hybrid intelligent models also represent a novel frontier in agriculture, QC has the potential to expedite the merging of mechanistic and AI modeling paradigms, facilitating a more holistic understanding of complex systems in agriculture and beyond. By integrating mechanistic models, which describe the underlying physical processes, with AI models, which learn patterns from data, quantum computing can enable comprehensive simulations and predictions of agricultural systems. This fusion of modeling paradigms can lead to more accurate and robust predictions of crop yields, livestock performance, and environmental impacts, facilitating informed decision-making for farmers and policymakers. The application of QC in agriculture, however, requires interdisciplinary collaborations between physicists, computer scientists, agronomists/animal scientists, and AI researchers. These collaborations can drive the development of quantum algorithms tailored to agricultural applications, the integration of quantum-enhanced AI techniques into existing modeling frameworks, and the deployment of QC resources in real-world agricultural systems. Ultimately, harnessing the power of QC holds the potential to revolutionize agriculture production practices, including regenerative agriculture, and advance AI modeling capabilities, paving the way for a more sustainable and efficient agricultural industry [ABSTRACT FROM AUTHOR]

Self-directed learning harnesses intrinsic drive of students to create and preserve knowledge fostering comprehension of broader concepts and real world applicability. Principles of animal nutrition, a re quired course in animal science curricula nationwide, is foundational to sustainable management of livestock and companion animals. Mastery of the principles governing nutrient digestion and metabolism is impera tive as students progress into upper-level classes and pursue careers in the agriculture field. In this study, 304 students, enrolled in an upper-level animal nutrition class were invited to participate in an honors contract, entailing the completion of the “Explorer” project to earn honors credit. Throughout the semester, students (n = 27) researched a unique herbivore or omnivore, to create novel visual models illustrating nutrient diges tion and metabolism (e.g., carbohydrates, lipids, pro teins). We hypothesized that explaining these processes and models through writing would build confidence and proficiency in lecture material. The honors cohort convened weekly for 1 h sessions on campus; meetings offered scientific writing seminars, collaborative brain storming activities, and project feedback. A Likert scale survey was generated and administered using Qualtrics software during the last weekly meeting to those who completed the “Explorer” project (88.8% response rate). Additionally, participating students completed a learning reflection addressing prompts regarding engagement, critical thinking, comparison with lec ture writing assignments, and proposed design modi fications. An open coding methodology was employed, utilizing MAXQDA Analytics Pro (Version 24.1.0) to analyze reflections qualitatively. Subsequently, the AI assist feature was used to enhance inter-coder reliability by generating summaries and sub-codes that aided in the exploration of common themes across reflections. Our analysis revealed that writing to learn in a nutri tion course provided an authentic avenue for scientific expression, fostering skills such as communication, time management, research, comprehension of litera ture, and effective citation usage. Information gathering improved confidence in their ability to interpret and integrate concepts from lectures and external sources. Incorporating group activities and peer-reviews bol stered project efficacy, motivating students to revise, incorporate feedback, and consider alternative per spectives iteratively. Moreover, the learner-generated drawing enhanced critical thinking by encouraging students to dissect processes thoroughly. In conclu sion, the combination of creating visual models alongside written explanations proved highly effective in simplifying complex nutritional concepts, facilitating deeper comprehension, and providing a high-impact learning experience. Future research should focus on peer teaching following similar writing activities to further improve student engagement and foster avenues for autonomy. Efforts should be made to encourage participation from a more diverse range of students that represent all backgrounds in animal science. [ABSTRACT FROM AUTHOR]

The objectives of this study were to develop sub-models for predicting protein requirements and supply, encompassing 1) net protein for maintenance (NPm), 2) lactation (NPl), 3) rumen undegradable protein (RUP), and 4) duodenal microbial nitrogen (MicN) from the feed protein. The dataset used in this study was constructed by integrating in vivo experimental data collected from open databases (the National Animal Nutrition Program) and articles (Journal of Dairy Science), which includes a total of 1,779 observations from 436 publications. In the development of the model, animal information and feed chemical components were used as candidate variables, and two types of machine learning algorithms, Random Forest Regression (RFR) and Support Vector Regression (SVR) were employed. After testing, the following predictors were selected for predicting: 1) NPm: body weight (BW) and dry matter intake (DMI), 2) NPl: BW, DMI, days in milk (DIM), and dietary organic matter (OM) and crude protein (CP) contents, 3) RUP: DIM, DMI, dietary DM content, and CP fraction intake (B and C), and 4) MicN: DIM, DMI, DM, dietary neutral detergent fiber (NDF) content, CP fraction intake (A, B, and C). The selected models were assessed using a cross-validation method with the following statistical metrics including the coefficient of determination (R²), root-mean-square error of prediction (RMSEP), residual analyses, and concordance correlation coefficient (CCC). For the RUP and MicN models, they were compared with the NASEM (2021) model. In predicting NPm, both SVR and RFR algorithms demonstrated increased precision (R² = 0.965 vs. 0.969) and accuracy (RMSEP = 9.7 vs. 9.2 g/d); however, during residual analysis, the RFR model showed a statistically significant slope bias (P < 0.05). In the NPl prediction, the RFR algorithm showed slightly greater performance compared with SVR (R² = 0.864 vs. 0.814 and RMSEP = 86.7 vs. 98.5 g/d). However, similar to the NPm prediction, the RFR model displayed a statistically significant slope bias (P < 0.05). In the supply model, the RFR model exhibited the greatest precision and accuracy in predicting RUP (R² = 0.60, RMSEP = 0.326 kg/d, and CCC = 0.71) without any biases. This model achieved a 2.37-fold increase in R² and a decrease of 0.111 kg/d in RMSEP compared with the NASEM model. As for MicN prediction, the SVR model performed the best (R² = 0.76, RMSEP = 42.4 g/d, and CCC = 0.86) without biases. This model attained a 19-times improvement in R² and a reduction of 38.7 g/d in RMSEP when compared with the NASEM model. In conclusion, the models developed using machine learning algorithms can be helpful for accurately and precisely predicting protein requirements and supply based on animal information and the chemical composition of feed. [ABSTRACT FROM AUTHOR]

Solving complex livestock production problems is a pressing issue for achieving long-term sustainability and profitability and often requires modeling techniques. The use of mathematical models is undoubtedly a daily practice in the livestock industry, especially nutrition, and has improved animal performance, productivity, and environmental sustainability while maintaining or reducing costs. Although many students and professionals use spreadsheets and existing empirical models for nutrition and management [NASEM (2016)], there is still a need to understand the complexity of livestock systems and the utility of flight simulator models. At the same time, more complex models (although robust) may fail to provide new insights for experienced nutritionists due to poor userfriendliness. A systems understanding goes beyond simply obtaining a desired output, such as optimizing a total mixed ration, but instead leads to identifying high-leverage solutions and gaining insight. Further, parameterizing and calibrating variables and equations and testing management scenarios is straightforward. However, developing causal feedback linkages (A to B and B to A) and identifying time delays is less intuitive and more challenging for novices. Model flight simulators grounded in fully documented, calibrated models provide a means to introduce practitioners to a methodology of insight generation because the user designs and runs the model scenarios for themselves, challenging their mental models. Such approaches are generally more impactful (compared with someone telling them) because they have gained insight into the system themselves, and, in the case of open source (white box models), they can explore equations and parameters. Therefore, understanding how to utilize dynamic models in scenario-based simulations is critical in training current and future modelers in animal science. This hands-on model training will cover the basics of System Dynamics modeling and allow participants to run real-time animal production simulations. Finally, participants will be “debriefed” to unpack “ah ha” moments that were unexpected. The debrief will include using models to develop accurate guidelines and recommendations for those who cannot use computer models and developing experimental designs to test hypotheses and “validate” model recommendations (proof in the pudding). Participants will gain knowledge of System Dynamics applications for animal production systems, experience using flight simulators, and their utility in teaching, informing, and guiding their livestock production or that of a client. The “flight simulator” will focus on production and nutrition with species-agnostic principles. Participants will also have a new tool to identify areas for improvement in model development (i.e., what is missing?), research questions, or industry needs. The need for modelers who can turn big data into insight, knowledge, and wisdom using a systems approach is becoming even more critical due to the increasing use of precision livestock farming. Thus, providing the livestock industry with trained systems modelers will help achieve current and future sustainability challenges. [ABSTRACT FROM AUTHOR]

Recent developments in computer vision (CV) technology have significantly improved the management of beef cattle feeding systems by enabling precise monitoring and adjustment of feed intake based on individual needs. This study introduces an automated approach for identifying cattle at feeding bunks using CV and evaluates the effectiveness of a feeding bunk scoring system to optimize cattle feeding strategies. Utilizing a high-definition video capture setup, our research focused on the feeding behaviors of 6 heifers in one pen with the Calan Feeding System (American Calan, Northwood, NH). We deployed three Reolink PoE cameras (Model D400) strategically positioned above the feeding bunks, each overseeing two feeding bunks, to monitor feeding activity comprehensively. The cameras were set to record in Full HD (1920 x 1080 pixels) at 30 frames per second. We processed the frames using Python’s OpenCV, resulting in 600 images that composed an array with dimensions 600 x 400x450 (pixels) x 3 (RGB). These images served as the basis for our analysis, which involved feature extraction via a ResNet-50 convolutional neural network, followed by dimensionality reduction through Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE). Our methodology included the use of k-means clustering to detect the presence of cattle at the bunk, achieving an Adjusted Rand Index (ARI) of 0.9933. We applied the DBSCAN clustering algorithm in the ‘cattle present’ images for individual animal identification, obtaining an ARI of 0.9174, indicating high model accuracy. To assess feeding efficiency, we analyzed 12,156 images of feeding bunks obtained using the same Python’s OpenCV approach and then classified them into six categories based on Lundy et al., 2015: S00 (no feed), S05 (scattered feed), S10 (thin layer), S20 (25 to 50%), S30 (>50%), and S40 (untouched). Using a training, validation, and testing split of 70%, 15%, and 15%, respectively, our model demonstrated exceptional precision, recall, and F1 scores of 0.9989 and predictions in the Confusion Matrix testing accuracy of 99.89%, showcasing the model accuracy. However, when applied to a similar classification using the same Calan gate system, with 7,905 images, the performance of the model decreased, with less precision (0.5868), recall (0.3982), and F1 score (0.3653), most related to classes S10, S20, and S40, underscoring the need for further model refinement. Our findings highlight the potential of integrating CV into precision livestock farming, automating the identification of cattle at feeding bunks, and correlating it with feeding scores to estimate individual consumption accurately. This integration promises to enhance sustainable farming by enabling more precise resource utilization and optimizing individual animal performance. With CV technology, producers can significantly improve production efficiency, health management, and environmental sustainability within their operations. The technology also has a crucial role in reducing operational costs, making it a cost-effective and sustainable production method. [ABSTRACT FROM AUTHOR]

A renewed interest in data analytics and decision support systems in developing automated computer systems is facilitating the emergence of hybrid intelligent systems by combining artificial intelligence (AI) algorithms with classical modeling paradigms such as mechanistic modeling (HIMM) and agent-based models (iABM). Data analytics have evolved remarkably, and the scientific community may not yet fully grasp the power and limitations of some tools. Existing statistical assumptions might need to be re-assessed to provide a more thorough competitive advantage in animal production systems towards sustainability. This paper discussed the evolution of data analytics from a competitive advantage perspective within academia and illustrated the combination of different advanced technological systems in developing HIMM. The progress of analytical tools was divided into three stages: collect and respond, predict and prescribe, and smart learning and policy making, depending on the level of their sophistication (simple to complicated analysis). The collect and respond stage is responsible for ensuring the data is correct and free of influential data points, and it represents the data and information phases for which data are cataloged and organized. The predict and prescribe stage results in gained knowledge from the data and comprises most predictive modeling paradigms, and optimization and risk assessment tools are used to prescribe future decision-making opportunities. The third stage aims to apply the information obtained in the previous stages to foment knowledge and use it for rational decisions. This stage represents the pinnacle of acquired knowledge that leads to wisdom, and AI technology is intrinsic. Although still incipient, HIMM and iABM form the forthcoming stage of competitive advantage. HIMM may not increase our ability to understand the underlying mechanisms controlling the outcomes of a system, but it may increase the predictive ability of existing models by helping the analyst explain more of the data variation. The scientific community still has some issues to be resolved, including the lack of transparency and reporting of AI that might limit code reproducibility. It might be prudent for the scientific community to avoid the shiny object syndrome (i.e. AI) and look beyond the current knowledge to understand the mechanisms that might improve productivity and efficiency to lead agriculture towards sustainable and responsible achievements. [ABSTRACT FROM AUTHOR]

Modern animal scientists, industry, and managers have never faced a more complex world. Precision livestock technologies have altered management in confined operations to meet production, environmental, and consumer goals. Applications of precision technologies have been limited in extensive systems such as rangelands due to lack of infrastructure, electrical power, communication, and durability. However, advancements in technology have helped to overcome many of these challenges. Investment in precision technologies is growing within the livestock sector, requiring the need to assess opportunities and challenges associated with implementation to enhance livestock production systems. In this review, precision livestock farming and digital livestock farming are explained in the context of a logical and iterative five-step process to successfully integrate precision livestock measurement and management tools, emphasizing the need for precision system models (PSM s). This five-step process acts as a guide to realize anticipated benefits from precision technologies and avoid unintended consequences. Consequently, the synthesis of precision livestock and modeling examples and key case studies help highlight past challenges and current opportunities within confined and extensive systems. Successfully developing PSM requires appropriate model(s) selection that aligns with desired management goals and precision technology capabilities. Therefore, it is imperative to consider the entire system to ensure that precision technology integration achieves desired goals while remaining economically and managerially sustainable. Achieving long-term success using precision technology requires the next generation of animal scientists to obtain additional skills to keep up with the rapid pace of technology innovation. Building workforce capacity and synergistic relationships between research, industry, and managers will be critical. As the process of precision technology adoption continues in more challenging and harsh, extensive systems, it is likely that confined operations will benefit from required advances in precision technology and PSMs, ultimately strengthening the benefits from precision technology to achieve short- and long-term goals. [ABSTRACT FROM AUTHOR]

The field of animal science, and especially animal nutrition, relies heavily on modeling to accomplish its day-to-day objectives. New data streams ("big data") and the exponential increase in computing power have allowed the appearance of "new" modeling methodologies, under the umbrella of artificial intelligence (AI). However, many of these modeling methodologies have been around for decades. According to Gartner, technological innovation follows five distinct phases: technology trigger, peak of inflated expectations, trough of disillusionment, slope of enlightenment, and plateau of productivity. The appearance of AI certainly elicited much hype within agriculture leading to overpromised plug-and-play solutions in a field heavily dependent on custom solutions. The threat of failure can become real when advertising a disruptive innovation as sustainable. This does not mean that we need to abandon AI models. What is most necessary is to demystify the field and place a lesser emphasis on the technology and more on business application. As AI becomes increasingly more powerful and applications start to diverge, new research fields are introduced, and opportunities arise to combine "old" and "new" modeling technologies into hybrids. However, sustainable application is still many years away, and companies and universities alike do well to remain at the forefront. This requires investment in hardware, software, and analytical talent. It also requires a strong connection to the outside world to test, that which does, and does not work in practice and a close view of when the field of agriculture is ready to take its next big steps. Other research fields, such as engineering and automotive, have shown that the application power of AI can be far reaching but only if a realistic view of models as whole is maintained. In this review, we share our view on the current and future limitations of modeling and potential next steps for modelers in the animal sciences. First, we discuss the inherent dependencies and limitations of modeling as a human process. Then, we highlight how models, fueled by AI, can play an enhanced sustainable role in the animal sciences ecosystem. Lastly, we provide recommendations for future animal scientists on how to support themselves, the farmers, and their field, considering the opportunities and challenges the technological innovation brings. [ABSTRACT FROM AUTHOR]

This study determined the energy requirement for maintenance of purebred Nellore cattle and its crossbreds using data from a comparative slaughter trial in which animals were raised under the same plane of nutrition from birth through slaughter and born from a single commercial Nellore cowherd. A total of 79 castrated steers (361 ± 54 kg initial body weight [ BW ]) were used in a completely randomized design by age (22 mo ± 23 d of age) with four genetic groups (GG): Nellore (NL), ½ Angus × ½ Nellore (AN), ½ Canchim × ½ Nellore (CN), and ½ Simmental × ½ Nellore (SN). The experimental design provided ranges in metabolizable energy (ME) intake (MEI), BW, and average daily gain needed to develop regression equations to predict net energy for maintenance (NEm) requirements. Four steers of each GG were slaughtered to determine the initial body composition. The remaining 63 steers were assigned to different nutritional treatments (NT) by GG; ad libitum or limit-fed treatments (receiving 70% of the daily feed of the ad libitum treatment of the same GG). Full BW was recorded at birth, weaning, 12, 18, and 22 mo. In the feedlot, steers were fed for 101 d a diet containing (DM basis) 60% corn silage and 40% concentrate. No difference in age at weaning (P = 0.534) and slaughter (P = 0.179 and P = 0.896, for GG and NT, respectively) were observed. AN steers were heavier at weaning weight, yearling weight and had higher empty BW (EBW ; P = 0.007, P = 0.014, and P < 0.001, respectively) in comparison to NL, CN, and SN. There were no interactions (P > 0.05) between GG and NT for any variable evaluated. When fed ad libitum, AN steers had higher daily MEI (Mcal/d; P < 0.001) in comparison to NL, CN, and SN. On a constant age basis, differences were observed on body composition (P < 0.05) between GG. The slope (P = 0.600) and intercept (P = 0.702) of the regression of log heat production on MEI were similar among GG. Evaluating at the same age and the same frame size, there were no differences in NEm requirement between Nellore and AN (P = 0.528), CN (P = 0.671), and SN (P = 0.706). The combined data indicated a NEm requirement of 86.8 kcal/d/kg0.75 EBW and a ME required for maintenance requirement had a common value of 137.53 kcal/d/kg0.75 EBW. The efficiency of energy utilization for maintenance and the efficiency of energy utilization for growth values were similar among GG (P > 0.05 and P > 0.05, respectively) and were on average 63.2% and 26.0%, respectively. However, although not statistically different, the NEm values from NL showed a decrease in NEm of 5.76% compared with AN steers. [ABSTRACT FROM AUTHOR]

Our objectives were to 1) investigate the difference in chemical composition and disappearance kinetics between loose dried distillers' grains (DDG) and extruded DDG cubes and 2) evaluate the effects of supplementation rate of extruded DDG cubes on voluntary dry matter intake (DMI), rate and extent of digestibility, and blood parameters of growing beef heifers offered ad libitum bermudagrass (Cynodon dactylon) hay. To characterize the changes in chemical composition during the extrusion process, loose and extruded DDG were evaluated via near-infrared reflectance spectroscopy, and dry matter (DM) disappearance kinetics were evaluated via time point in situ incubations. Extruded DDG cubes had greater (P ≤ 0.01) contents of fat, neutral detergent insoluble crude protein, and total digestible nutrients, but lower (P ≤ 0.01) neutral and acid detergent fiber than loose DDG. Additionally, the DM of extruded DDG cubes was more immediately soluble (P < 0.01), had greater (P < 0.01) effective degradability and lag time, and tended (P = 0.07) to have a greater disappearance rate than loose DDG. In the 29-d supplementation rate study, 23 Charolais-cross heifers were randomly assigned to one of four supplemental treatments: 1) control, no supplement; 2) low, 0.90 kg DDG cubes per d; 3) intermediate, 1.81 kg DDG cubes per d; or 4) high, 3.62 kg DDG cubes per d. Titanium dioxide was used as an external marker to estimate fecal output and particulate passage rate (K p ). Blood was collected from each animal to determine supplementation effects on blood metabolites. Indigestible neutral detergent fiber was used as an internal marker to assess the rate and extent of hay and diet DM digestibility (DMD). Increasing supplementation rate increased Kp and total diet DMI linearly (P < 0.01), yet linearly decreased (P < 0.01) hay DMI. Hay DMD decreased quadratically (P < 0.01), while total diet DMD increased linearly (P < 0.01) with increased DDG cube inclusion. Supplemented heifers had greater (P = 0.07) blood urea nitrogen concentrations than control animals 4 h post-supplementation. Intermediate and high rates of supplementation resulted in lower (P < 0.01) serum nonesterified fatty acid concentrations post-supplementation than control heifers. Concentrations of serum glucose and lactate were greatest (P ≤ 0.06) 8 h post-supplementation. Our results suggest that extruded DDG cubes may be an adequate supplement for cattle consuming moderate-quality forage, and further research is warranted. [ABSTRACT FROM AUTHOR]

Reliable predictions of metabolizable energy (ME) from digestible energy (DE) are necessary to prescribe nutrient requirements of beef cattle accurately. A previously developed database that included 87 treatment means from 23 respiration calorimetry studies has been updated to evaluate the efficiency of converting DE to ME by adding 47 treatment means from 11 additional studies. Diets were fed to growing-finishing cattle under individual feeding conditions. A citation-adjusted linear regression equation was developed where dietary ME concentration (Mcal/kg of dry matter [ DM ]) was the dependent variable and dietary DE concentration (Mcal/kg) was the independent variable: ME = 1.0001 × DE – 0.3926; r 2 = 0.99, root mean square prediction error [ RMSPE ] = 0.04, and P < 0.01 for the intercept and slope. The slope did not differ from unity (95% CI = 0.936 to 1.065); therefore, the intercept (95% CI = −0.567 to −0.218) defines the value of ME predicted from DE. For practical use, we recommend ME = DE – 0.39. Based on the relationship between DE and ME, we calculated the citation-adjusted loss of methane, which yielded a value of 0.2433 Mcal/kg of dry matter intake (DMI ; SE = 0.0134). This value was also adjusted for the effects of DMI above maintenance, yielding a citation-adjusted relationship: CH4, Mcal/kg = 0.3344 – 0.05639 × multiple of maintenance; r 2 = 0.536, RMSPE = 0.0245, and P < 0.01 for the intercept and slope. Both the 0.2433 value and the result of the intake-adjusted equation can be multiplied by DMI to yield an estimate of methane production. These two approaches were evaluated using a second, independent database comprising 129 data points from 29 published studies. Four equations in the literature that used DMI or intake energy to predict methane production also were evaluated with the second database. The mean bias was substantially greater for the two new equations, but slope bias was substantially less than noted for the other DMI-based equations. Our results suggest that ME for growing and finishing cattle can be predicted from DE across a wide range of diets, cattle types, and intake levels by simply subtracting a constant from DE. Mean bias associated with our two new methane emission equations suggests that further research is needed to determine whether coefficients to predict methane from DMI could be developed for specific diet types, levels of DMI relative to body weight, or other variables that affect the emission of methane. [ABSTRACT FROM AUTHOR]

The beef cow-calf sector accounts for 70% of feed consumed and greenhouse gases emitted for the beef industry, but there is no straightforward method to measure biological efficiency in grazing conditions. The objective of this study was to evaluate a mathematical nutrition model to estimate the feed intake and biological efficiency of mature beef cows. Data from dams (N = 160) and their second and third progeny (312 pairs) were collected from 1953 through 1980. Individual feed intake was measured at 28-d intervals year-round for dams and during 240-d lactation for progeny. Body weights of progeny were measured at 28-d intervals from birth to weaning, and of dams at parturition and weaning each production cycle. The milk yield of dams was measured at 14-d intervals. Dam metabolizable energy intake (DMEI) and milk energy yield (MEL) of each cow were predicted using the Cattle Value Discovery System beef cow (CVDSbc) model for each parity. Biological efficiency (Mcal/kg) was computed as the ratio of observed or predicted DMEI to observed calf weaning weight (PWW). Pearson correlation coefficients were computed using corr.test function and model evaluation was performed using the epiR function in R software. Average (SD) dam weight, PWW, DMEI, and observed MEL were 527 (86) kg, 291 (47) kg, 9584 (2701) Mcal/production cycle, and 1029 (529) Mcal, respectively. Observed and predicted DMEI (r = 0.93 and 0.91), and observed and predicted MEL (r = 0.58 and 0.59) were positively correlated for progeny 2 and 3, respectively. The CVDSbc model under-predicted DMEI (mean bias [MB] = 1,120 ± 76 Mcal, 11.7% of observed value) and MEL (MB = 30 ± 25 Mcal, 2.9% of observed value). Observed and predicted progeny feed intake were not correlated (r = 0.01, P -value = 0.79). Observed and predicted biological efficiency were positively correlated (r = 0.80 and 0.80, P -value ≤ 0.05) for parity 2 and 3, respectively, and the CVDSbc model under-predicted biological efficiency by 11% (MB = 3.59 ± 0.25 Mcal/kg). The CVDSbc provides reasonable predictions of feed intake and biological efficiency of mature beef cows, but further refinement of the relationship between calf feed intake and milk yield is recommended to improve predictions. Mathematical nutrition models can assist in the discovery of the biological efficiency of mature beef cows. [ABSTRACT FROM AUTHOR]

The objective was to evaluate the effect of including low-fat dried distillers grains (DDG) in finishing diets on protein and energy intake and retention and to estimate the protein and energy requirement of young Nellore bulls. Thirty-five animals were used: baseline (n = 4), maintenance (n = 4), and ad libitum intake (n = 27). Ad libitum animals were divided into four groups: diets with the inclusion of DDG at the levels of 0, 150, 300, and 450 g/kg (dry matter basis). At the end of the experiment, all animals were slaughtered. There was a linear reduction with increasing DDG levels in the total digestible nutrients intake (p = 0.008), metabolizable energy (ME) intake (p < 0.010), in total retained energy (p = 0.065), and in heat production (p < 0.001). Metabolizable protein (MP) intake increased linearly (p < 0.010) but retained protein did not differ (p = 0.499). Daily net energy and ME requirement for maintenance were 75.9 and 122 kcal/kg0.75 EBW, respectively. Daily MP for maintenance was 3.6 g/kg0.75 shrunk body weight. DDG inclusion in finishing diets reduces energy intake and deposition, and we recommend the equations of this study to estimate the requirements of young Nellore bulls. [ABSTRACT FROM AUTHOR]

The addition of natural plant secondary compounds to ruminant feed has been extensively studied because of their ability to modify digestive and metabolic functions, resulting in a potential reduction in greenhouse gas emissions, among other benefits. Condensed tannin (CT) supplementation may alter ruminal fermentation and mitigate methane (CH4 ) emissions. This study’s objective was to determine the effect of quebracho CT extract [QT; Schinopsis quebracho-colorado (Schltdl.) F.A. Barkley & T. Meyer] within a roughage-based diet on ruminal digestibility and kinetic parameters by using the in situ and in vitro gas production techniques, in addition to blood urea nitrogen (BUN) and ruminal (volatile fatty acid [VFA], NH3 -N, and protozoa count) parameters. Twenty rumen-cannulated steers were randomly assigned to four dietary treatments: QT at 0%, 1%, 2%, and 3% of dry matter (DM; QT0: 0% CT, QT1: 0.70% CT, QT2: 1.41% CT, and QT3: 2.13% CT). The in situ DM digestibility increased linearly (P = 0.048) as QT inclusion increased, whereas in situ neutral detergent fiber digestibility (NDFD) was not altered among treatments (P = 0.980). Neither total VFA concentration nor acetate-to-propionate ratio differed among dietary treatments (P = 0.470 and P = 0.873, respectively). However, QT3 had lower isovalerate and isobutyrate concentrations compared with QT0 (P ≤ 0.025). Ruminal NH3 and BUN tended to decline (P ≤ 0.075) in a linear fashion as QT inclusion increased, suggesting decreased deamination of feed protein. Ruminal protozoa count was reduced in quadratic fashion (P = 0.005) as QT inclusion increased, where QT1 and QT2 were lower compared with QT0 and QT3. Urinary N excretion tended to reduce in a linear fashion (P = 0.080) as QT increased. There was a treatment (TRT) × Day interaction for in vitro total gas production and fractional rate of gas production (P = 0.013 and P = 0.007, respectively), and in vitro NDFD tended to be greater for QT treatments compared with no QT inclusion (P = 0.077). There was a TRT × Day interaction (P = 0.001) on CH4 production, with QT3 having less CH4 production relative to QT0 on day 0 and QT2 on days 7 and 28. Feeding QT up to 3% of the dietary DM in a roughage-based diet did not sacrifice the overall DM digestibility and ruminal parameters over time. Still, it is unclear why QT2 did not follow the same pattern as in vitro gas parameters. Detailed evaluations of amino acid degradation might be required to fully define CT influences on ruminal fermentation parameters and CH4 production. [ABSTRACT FROM AUTHOR]

Grasslands cover approximately 40.5% of the surface of the earth and 80% of agriculturally productive land. After forests, grasslands are the primary carbon sink source and the most used feed source for livestock production. Regularly monitoring grasslands assures efficient management and sustainability of pasture-based production systems. Conventional ground-based methods to monitor grassland production and management rely on field measurements, which are time-consuming and usually restricted to small-scale assessment. Using satellite information allows for large-scale monitoring of grasslands and capturing the spatial variability of the land surface with high temporal resolution. Various methods for grassland monitoring based on satellite data can be applied, such as classifications, correlations/regression analyses, and time series analyses. Depending on the purpose of the application, these methods are sometimes combined to derive grassland management and production information. The ability of satellite-based data to quantify vegetation characteristics depends on the type of sensor and instrumentation features, such as spectral, radiometric, spatial, and temporal resolution, polarization, and angularity. The models to estimate grassland biomass based on remote sensing have been chiefly focused on optical systems. The spectral reflectance of raw bands and vegetation indices were used as proxies to investigate spatial and temporal patterns of grassland production. Optical (multispectral or hyperspectral) sensors are passive and require sunlight, so they depend highly on the weather (cloud) and light conditions. Thus, there has been increasing interest in active sensors, such as Synthetic Aperture Radar (SAR) and Light Detection and Ranging (LIDAR) sensors, which are not constrained due to clouds but are more complex. Using satellite data in combination with field measurements has commonly yielded regression models (e.g., linear, power, logarithmic, multiple linear) for estimating grassland biomass or biophysical characteristics (e.g., chlorophyll, leaf area index) of different types of grasslands. The exponential evolution of digital computers has pushed forward machine learning-based regression methods to estimate biomass. Random forest, support vector machines, and artificial neural networks are the most used algorithms. The possibility of accurate mapping and monitoring of biomass and nutritional attributes of grasslands based on satellite provides essential insights into the decision support system for pasture management. A better understanding of the nitrogen status of pastures, forage biomass, and its nutritive value is instrumental in livestock and forage management. Timely prediction of these variables can help improve decision-making by grazing land managers on, for instance, the adjustment of stocking rate or adequate supplementation to match the needs of animals toward more sustainable production. Future use of satellite-based grazing models in tandem with ruminant nutrition models will enable to development of decision-support tools to assist with many aspects of livestock production in diverse environmental conditions and accounting for temporal variability. (FAPESP #2020/14367-7). [ABSTRACT FROM AUTHOR]

Virginiamycin (VM) possesses antimicrobial properties due to its blocking of protein synthase in Gram-positive bacteria, allowing it to reduce lactic acidosis and the incidence of liver abscesses in ruminants. Ruminal acidosis is a common metabolic disorder that affects feedlot and dairy cattle and occurs when the supply of organic acids from fermentation exceeds its absorption and degradation, accumulating acid content in the rumen. The objective of this study was to evaluate the effects of three different doses of VM administration on in vivo and in vitro ruminal digestion kinetics of beef steers consuming a high-grain diet [metabolizable energy (ME): 2.99 Mcal/kg; Crude Protein (CP): 15.2 % dry matter basis (DM)]. Nine ruminally cannulated British-crossbred steers (596 ± 49 kg) were assigned to this experiment. Animals were housed in three pens (n = 3/pen) equipped with a Calan gate feed system and water trough. Pens were enrolled in a 3×3 Latin square design containing three periods of 16 d, and a 5-d washout interval between periods. Dietary treatments consisted of VM administration at 0 mg/d (VM0), 180 mg/d (VM180), and 240 mg/d (VM240). During d 15 and 16 of each period, about 600 mL of rumen fluid was collected before (0 h) and at 4, 8, 12, and 16 h relative to the morning feed (0730 h) pH and redox potential (Eh) measurements were taken immediately after collection using a portable pH and redox meter, and subsamples were taken for volatile fatty acids (VFA), and NH3-N analyses. During the 4-h post-morning feed rumen collection, rumen inoculum was utilized to perform in vitro gas production (IVGP) measurements. All statistical procedures were performed using SAS software where steer was considered the experimental unit, and period and square were included as random. Acetate, propionate, and total VFA did not differ among treatments (P = 0.50), whereas butyrate increased linearly (P = 0.033) as the VM dose increased. Acetate:propionate ratio did not differ among treatments (P = 0.273). Lactate concentration decreased linearly (P = 0.027) as the VM dose increased; likewise, pH increased linearly (P = 0.019) as the VM dose increased. Branched-chain VFA and NH3-N concentrations increased linearly (P = 0.056) as the VM dose increased. The total and rate of gas production were similar among treatments (P = 0.161). However, second-pool gas production increased linearly as VM inclusion increased (P = 0.023). The in vitro neutral detergent fiber digestibility did not differ among treatments (P = 0.984). The provision of VM altered the rumen dynamics in a dose-dependent manner. Animals consuming high-grain diets will likely promote rumen health through a more stable pH and fermentation profile. [ABSTRACT FROM AUTHOR]

Bovine respiratory disease (BRD) is a complex multifactorial disease that results in more than $1 billion in economic losses for the United States beef cattle industry, accounting for approximately 30% of the total antimicrobial use (AMU) in food animal production systems. The prevalence and production losses due to BRD vary significantly between different production systems, and is influenced by the host, pathogen, and environmental risk factors. These multiple risk factors together have a cumulative effect and will increase the prevalence of the disease if no preventive strategies are implemented in the system. Moreover, the increased AMU to treat BRD results in antimicrobial resistance, further complicating the issue. A linear, event-based solution to address such a complex problem will fail to consider the feedback loops and time delays in the system and may cause unintended consequences that might make the problem even more complex. Hence, we propose a more comprehensive system dynamic model to simulate an integrated beef production system with respect to BRD and predict the dynamic behavior of the system under different preventive strategies currently available to the beef industry. Our conceptual model accounts for host risk factors (auxiliary variables in the model) like age, nutritional status, daily weight gain, prior exposure to pathogens, and genetics. The environmental risk factors such as air quality, transportation, temperature humidity index, overcrowding, and source of animals were also included in the model. The various preventative strategies to reduce the incidence of BRD, including vaccination, biosecurity, adequate colostrum, and nutrition, were also added to the model. The key outcome variables considered were net profitability and AMU. The model simulates multiple scenarios by leveraging the auxiliary variables and can provide information about the system's net profitability and total AMU. The model explains the interconnected effect of various risk factors associated with BRD in multiple complex scenarios and helps understand the combined effect of adopting various preventive strategies and host-environmental factors in controlling BRD. The initial result from our dynamic model suggests that using a combination of preventive measures and avoiding the selected host-environmental risk factors can minimize AMU while improving profit. The long-term goal of our modeling effort is to enable the beef system stakeholders to make informed decisions and strategies to mitigate the impact of BRD, thereby contributing to improved profitability. Through a systems-thinking approach, our model can contribute to addressing the challenges in BRD management currently faced by the US-based integrated beef production systems. [ABSTRACT FROM AUTHOR]

Sub-acute rumen acidosis (SARA) is a ruminal digestive disorder with a prevalence of 24 to 30% in United States-based feedlots and is responsible for a lost economic opportunity of approximately $1 billion annually. Our objective for this study was to develop a decision tool which feedlot decision-makers could use to make routine managemental interventions that can mitigate the prevalence of SARA. The continuous reduction in rumen pH (pH < 5.6) is the primary causative factor that triggers its onset. However, this prolonged lower rumen pH results from the interaction between multiple other etiological factors. We developed a random forest-based decision tree prediction tool which used seventeen plausible etiological factors, which we broadly classified under four categories, namely 1) animal factors, 2) nutritional factors, 3) environmental factors, and 4) management factors (Table 1), to predict the probability of SARA in a typical US feedlot. A synthetic dataset of 100 observations was created based on a survey conducted among subject matter experts, including ruminant nutritionists, epidemiologists, and decision modelers to chart out the alleged relationship between the above seventeen etiological factors and the probability of a beef cattle population contracting SARA. The random forest model (R, 2021) was used to train as well as test the boot-strapped (80:20 split) synthetic dataset. Ability of random forest to limit overfitting without substantially increasing error due to bias contributed to the high positive predictive value (84%) of the model. Our results indicated that beef yearling cattle with mild temperament, with a rumen pH maintained above 5.6, while being fed three or more times a day, for more than 150 days on concentrate feed, with a stocking density greater than 7 m2, with excellent preconditioning, fed either sorghum or oats which are tempered with a physically effective fiber of 15% and above, under ambient temperature and humidity, along with the feeding of prebiotics, probiotics and ionophores had the least probability to contract SARA. In conclusion, our model can be used by feedlot decision modelers to test different permutations and combinations of these seventeen etiological factors customized to their respective operations to predict the probability of SARA in their herd. Future studies will improve the accuracy of the model by training it on more robust epidemiological datasets sourced from beef herds located in multiple geographic regions. [ABSTRACT FROM AUTHOR]

Leveraging computer vision (CV) methods to study pen-fed cattle feeding behavior presents several advantages, including monitoring animal health and identifying feed efficient animals. This research employed a region-based convolutional neural network (RCNN) combined with the common objects in context (COCO) dataset for automatic livestock recognition using CV techniques in experimental feedlot pens. Thirty Angus-influenced steers were allocated in one pen with four automated feed intake systems (AFIS; Vytelle SENSE). CV data were recorded during daylight hours using a webcam (Microsoft LifeCam Cinema) with a resolution of 1280x720 pixels at ten frames per second connected to a video surveillance camera software (Contaware, Switzerland). The CV dataset obtained by the cameras, Figure 1, was benchmarked with feeding behavior data obtained from observed annotations (OA) and AFIS. The CV model utilized was a Mask-RCNN with pre-trained weights on the COCO dataset. The Mask RCNN algorithm can identify and locate multiple objects, objects of different scales, and overlapping objects within an image. The COCO dataset is a large and diverse set of annotated images that can be used for training and evaluating object detection models. The fully trained Mask-RCNN model takes each video frame as input and outputs the pixel segmentation of each object detected. For the CV analyses, each animal bounding box was associated with a score threshold, and each pixel within was assigned a probability threshold; both ranging from 0 to 100. The higher the score and probability thresholds are, the fewer the boxes and pixels will be marked as the animal boxing shape, resulting in less feeding detection from the CV system. In contrast, a low score and probability thresholds produce many predictions, including false detections, which might be misleading. Therefore, a dataset analysis was conducted to optimize the best threshold combination. We evaluated the accuracy and precision of the CV model compared with OA and AFIS by analyzing a dataset section of feeding events of one feed bunk using a 0.5 score and 0.5 probability thresholds. We obtained the values for the true positive (TP), false positive (FP), true negative (TN), and false negative (FN) to calculate the accuracy = [TP+TN]/[TP+TN+FP+FN], and precision = [TP]/[TP+FP], Table 1. As a result, the CV model achieved 95.39% and 99.82% accuracy and 93.60% and 99.90%precision when compared with OA and AFIS, respectively. Our findings showcase the promising capabilities of employing the Mask-RCNN algorithm and COCO datasets for detecting beef cattle feeding behavior in feedlot pens. This approach holds significant value for the cattle industry by enabling precise monitoring and analysis of individual animal behavior within feedlot pens, facilitating early detection of behavioral abnormalities. [ABSTRACT FROM AUTHOR]

Nutrition models are important tools in management decisions, but improvements are needed for cow–calf producers to accurately predict nursing calf performance. Therefore, the objective of this study was to assess the ability of published milk yield (MY) and forage intake equations to predict calf feed intake and weaning weight (WW) using an independent, multi-breed dataset. A dataset with 406 nursing calves was used to evaluate two MY equations: 1) National Academies of Sciences, Engineering, and Medicine (2016) (NASEM) and 2) Wood (1967) (WOOD) and five feed intake equations: 1) equations from Table 9.1 in Tedeschi et al. (2006) (TED06), 2) equations 2 to 7 in Baker et al. (1976) (BAK76), 3) equation 25 in Tedeschi and Fox (2009) (TED09A), 4) equations 17, 19, and 24 in Tedeschi and Fox (2009) (TED09B), and 5) equation from Holloway et al. (1982) (HOL82). MY was measured at 14-d interval by hand milking, and individual feed intake of nursing calves was determined during a 240-d nursing period. Calf birth and WW were measured on days 0 and 240, respectively. Each combination of MY and feed intake equation was used to predict calf feed intake and WW from observed MY, calf birth weight, and calf slaughter weight. Predicted and observed values were compared using concordance correlation coefficient (CCC) and mean bias (MB). Factors affecting the deviation between observed and predicted values were analyzed using regression, and a revised equation was developed. Feed intake equations poorly predicted observed feed intake with CCC < 0.4 and MB ranged from −108% to 69%. However, statistics were slightly improved when using WOOD rather than the NASEM MY equation. BAK76 and TED09B feed intake equations were considerably more accurate (MB = −14.4% to 13.0%) in predicting feed intake but still not precise (CCC < 0.30). Predictions of WW had CCC ranging from 0.19 to 0.71 and MB ranging from −25.9% to 41.8% and were not significantly affected by the MY equation. TED06 and BAK76 feed intake equations were the most precise (CCC > 0.60) and accurate (MB = 1.7% to 8.5%) in predicting WW. Sire breed accounted for significant variation in the deviation between observed and predicted values of feed intake and in a revised equation to predict total feed energy intake from total milk energy intake. In conclusion, refinements of feed intake equations for nursing calves need to account for breed to improve current nutrition models. [ABSTRACT FROM AUTHOR]