AI-enhanced real-time cattle identification system through tracking across various environments.

Video-based monitoring is essential nowadays in cattle farm management systems for automated evaluation of cow health, encompassing body condition scores, lameness detection, calving events, and other factors. In order to efficiently monitor the well-being of each individual animal, it is vital to automatically identify them in real time. Although there are various techniques available for cattle identification, a significant number of them depend on radio frequency or visible ear tags, which are prone to being lost or damaged. This can result in financial difficulties for farmers. Therefore, this paper presents a novel method for tracking and identifying the cattle with an RGB image-based camera. As a first step, to detect the cattle in the video, we employ the YOLOv8 (You Only Look Once) model. The sample data contains the raw video that was recorded with the cameras that were installed at above from the designated lane used by cattle after the milk production process and above from the rotating milking parlor. As a second step, the detected cattle are continuously tracked and assigned unique local IDs. The tracked images of each individual cattle are then stored in individual folders according to their respective IDs, facilitating the identification process. The images of each folder will be the features which are extracted using a feature extractor called VGG (Visual Geometry Group). After feature extraction task, as a final step, the SVM (Support Vector Machine) identifier for cattle identification will be used to get the identified ID of the cattle. The final ID of a cattle is determined based on the maximum identified output ID from the tracked images of that particular animal. The outcomes of this paper will act as proof of the concept for the use of combining VGG features with SVM is an effective and promising approach for an automatic cattle identification system.

An evaluation form to aid dairy producers to systematically assess cows prior to culling.

Objective: The objective of this prospective observational research project was to have dairy producers use and assess the utility of a cull cow evaluation form. Animals: Cull dairy cows. Procedure: Veterinarians were recruited to enrol a purposively selected group of dairy producers into a project to evaluate a cull cow evaluation form. Producers were provided with evaluation forms and asked to complete a form for every cow they culled from their herd from January to June 2017, inclusive. Results: A total of 44 producers used the form to record information on 323 cows prior to transport. Conclusion and clinical relevance: Despite the completion of 323 forms, only ~1/3 were completed fully, with compliance highest for body condition score, lameness, and temperature recordings (> 90% of forms). A cull cow evaluation form may improve the thoroughness and consistency of dairy producer assessment of cull dairy cows for fitness for transport.

Un formulaire d'évaluation pour aider les producteurs laitiers à évaluer systématiquement les vaches avant la réforme. Objectif: L'objectif de ce projet de recherche observationnelle prospective était d'amener les producteurs laitiers à utiliser et à évaluer l'utilité d'un formulaire d'évaluation des vaches de réforme. Animaux: Vaches laitières réformées. Procédure: Des vétérinaires ont été recrutés pour inscrire un groupe de producteurs laitiers sélectionnés à dessein dans un projet visant à évaluer un formulaire d'évaluation des vaches réformées. Les producteurs ont reçu des formulaires d'évaluation et ont été invités à remplir un formulaire pour chaque vache qu'ils ont éliminée de leur troupeau de janvier à juin 2017 inclusivement. Résultats: Au total, 44 producteurs ont utilisé le formulaire pour enregistrer des informations sur 323 vaches avant le transport. Conclusion et pertinence clinique: Malgré la complétion de 323 formulaires, seulement environ 1/3 ont été entièrement remplis, avec une conformité plus élevée pour le score d'état corporel, les boiteries et les enregistrements de température (> 90 % des formulaires). Un formulaire d'évaluation des vaches laitières réformées peut améliorer la rigueur et la cohérence de l'évaluation par le producteur laitier des vaches laitières réformées quant à leur aptitude au transport.(Traduit par Dr Serge Messier).

Microbiome mapping in dairy industry reveals new species and genes for probiotic and bioprotective activities.

The resident microbiome in food industries may impact on food quality and safety. In particular, microbes residing on surfaces in dairy industries may actively participate in cheese fermentation and ripening and contribute to the typical flavor and texture. In this work, we carried out an extensive microbiome mapping in 73 cheese-making industries producing different types of cheeses (fresh, medium and long ripened) and located in 4 European countries. We sequenced and analyzed metagenomes from cheese samples, raw materials and environmental swabs collected from both food contact and non-food contact surfaces, as well as operators' hands and aprons. Dairy plants were shown to harbor a very complex microbiome, characterized by high prevalence of genes potentially involved in flavor development, probiotic activities, and resistance to gastro-intestinal transit, suggesting that these microbes may potentially be transferred to the human gut microbiome. More than 6100 high-quality Metagenome Assembled Genomes (MAGs) were reconstructed, including MAGs from several Lactic Acid Bacteria species and putative new species. Although microbial pathogens were not prevalent, we found several MAGs harboring genes related to antibiotic resistance, highlighting that dairy industry surfaces represent a potential hotspot for antimicrobial resistance (AR) spreading along the food chain. Finally, we identified facility-specific strains that can represent clear microbial signatures of different cheesemaking facilities, suggesting an interesting potential of microbiome tracking for the traceability of cheese origin.

Validating statistical properties of resilience indicators derived from simulated longitudinal performance measures of farmed animals.

Resilience is commonly defined as the ability of an individual to be minimally affected or to quickly recover from a challenge. Improvement of animals' resilience is a vital component of sustainable livestock production but has so far been hampered by the lack of established quantitative resilience measures. Several studies proposed that summary statistics of the deviations of an animal's observed performance from its target performance trajectory (i.e., performance in the absence of challenge) may constitute suitable quantitative resilience indicators. However, these statistical indicators require further validation. The aim of this study was to obtain a better understanding of these resilience indicators in their ability to discriminate between different response types and their dependence on different response characteristics of animals, and data recording features. To this purpose, milk-yield trajectories of individual dairy cattle differing in resilience, without and when exposed to a short-term challenge, were simulated. Individuals were categorised into three broad response types (with individual variation within each type): Fully Resilient animals, which experience no systematic perturbation in milk yield after challenge, Non-Resilient animals whose milk yield permanently deviates from the target trajectory after challenge and Partially Resilient animals that experience temporary perturbations but recover. The following statistical resilience indicators previously suggested in the literature were validated with respect to their ability to discriminate between response types and their sensitivity to various response features and data characteristics: logarithm of mean of squares (LMS), logarithm of variance (LV), skewness (S), lag-1 autocorrelation (AC1), and area under the curve (AUC) of deviations. Furthermore, different methods for estimating unknown target trajectories were evaluated. All of the considered resilience indicators could distinguish between the Fully Resilient response type and either of the other two types when target trajectories were known or estimated using a parametric method. When the comparison was between Partially Resilient and Non-Resilient, only LMS, LV, and AUC could correctly rank the response types, provided that the observation period was at least twice as long as the perturbation period. Skewness was in general the least reliable indicator, although all indicators showed correct dependency on the amplitude and duration of the perturbations. In addition, all resilience indicators except for AC1 were robust to lower frequency of measurements. In general, parametric methods (quantile or repeated regression) combined with three resilience indicators (LMS, LV and AUC) were found the most reliable techniques for ranking animals in terms of their resilience.

Effects of grass species and harvest date on cell wall components and feed efficiency of dairy cows.

There is a balance between DM yield and feed value when choosing types of grasses on a farm depending on the acreages of farmland and types of ruminants to be fed. Therefore, optimisation of the harvest strategy for grass silage is important for profitable dairy farming. Tall fescue has high DM yield and can replace traditional grasses, such as timothy, in Northern Europe in a changing climate as it has been shown to be more drought tolerant. As differences in climate responses previously have been related to differences in cell wall structure between grass species and, consequently, in digestibility, it is highly relevant to compare these species at similar maturity stages and to investigate if a very early harvest date will diminish potential differences between the species. This study evaluated the effects of harvest date and forage species on the concentration of hydroxycinnamic acids in silages and its relationship to feed efficiency of dairy cows. Tall fescue and timothy were harvested at very early date on May 25 or at early date on May 31 in the spring growth cycle. Forty lactating dairy cows were used in a block design. Cows received 1 of 4 treatments: (1) tall fescue harvested at very early date, (2) timothy harvested at very early date, (3) tall fescue harvested at early date, and (4) timothy harvested at early date. Diets were formulated to have the same forage-to-concentrate ratio (49:51 on DM basis). Tall fescue silages showed greater concentrations of DM, ash, and CP than timothy silages. Grasses harvested at early date showed greater concentrations of NDF, ADL, and cell wall than grasses harvested at very early date. Tall fescue silages showed greater concentration of p-coumaric acid and lower in vitro organic matter digestibility (IVOMD) compared to timothy silages. Milk production and composition were not affected by treatments but cows fed tall fescue-based diets showed lower milk protein yield and greater milk urea nitrogen than when timothy-based diets were fed. Furthermore, cows receiving timothy-based diets showed greater feed efficiency compared to cows receiving tall fescue-based diets. Thus, the lower concentration of p-coumaric acid and the higher IVOMD was associated with greater feed efficiency of cows fed timothy-based diets compared to tall fescue-based diets.

Comparative Analysis of Milking and Behavior Characteristics of Multiparous and Primiparous Cows in Robotic Systems.

Robotic milking systems are successful innovations in the development of dairy cattle. The objective of this study was to analyse the milking characteristics and behavior of dairy cows of different calving orders in "milk first" robotic milking systems. The data were collected from a commercial herd located in the Midwest region of Minas Gerais (Brazil), which uses an automatic milking system (AMS TM, DeLaval). Were analysed 26,574 observations of 235 Holstein cows were available. Data were evaluated by multivariate analysis of variance and the Tukey test. - Tthe characteristics milk flow and milking efficiency were more favourable for multiparous cows (p <0.01), while the time in the stall was more favourable for primiparous females (p <0.01). The values of handling time were better in the primiparous cows (p <0.01). Primiparous cows had higher amounts of kick-off (p <0.001), and multiparous cows had higher incomplete milkings (p <0.001). The number of incomplete milkings showed a higher ratio in terms of reduction in milk production in 26.6% in primiparous cows and 26.7% in multiparous cows (p <0.01). Regarding the behavioral characteristics, primiparous cows had higher amounts of kickbacks, while multiparous cows had greater quantities of incomplete milkings.

Cow-calf contact: a single-herd observational study of AMS yield during the first 100 days in milk.

An increasing number of dairy farmers plan to implement cow-calf contact (CCC) in their herd which necessitates descriptions of the cows` performance in different systems. The aim of the study was to describe (1) Automatic milking system (AMS) milk yield of cows in a CCC system during the first 100 days in milk (DIM) and (2) AMS milk yield before and after cow-calf separation. In a prospective study at a commercial Norwegian dairy farm, we included all calvings from Norwegian Red cows between January 2019 to April 2020. After calving, cow-calf pairs stayed in an individual calving pen during the first 5-6 d before they were moved to the loose housing unit with the remaining herd. Calves had whole-day (24 h/d) and full physical contact to the cows. Cows were milked in an AMS. From 14 individual cows of which one cow calved twice during the study period, we collected daily AMS yields from 15 different lactations, with parities ranging from 1 (n = 6), 2 (n = 5) and 3 (n = 4). Due to the sample size and structure of the data set, we only calculated descriptive statistics from DIM 7-100. All data is shown separately for primiparous and multiparous cows. Mean (± SD) calf age at (fence-line) separation was 52 d ± 14.8 beyond which suckling was prevented. Our data indicates great individual variation in the AMS milk yield. Prior to separation, primiparous cows` AMS yields ranged from 11.0 to 25.9 kg/d while that of multiparous cows ranged from 4.8 to 28.8 kg/d. Once calves were no longer allowed to suckle, the yield increased gradually. During the week after separation, AMS yields ranged from 17.3 to 30.4 kg/d for primiparous cows and 8.7 to 41.8 kg/d for multiparous cows and these yields increased in DIM 93-100 (26.5 to 34.3 and 20.6 to 38.3 kg/d respectively). This study is limited by a low sample size from a single-herd but may provide useful descriptions of AMS milk yield in a whole-day, full contact CCC system during the first 100 days of lactation.

Evaluating machine learning algorithms to predict lameness in dairy cattle.

Dairy cattle lameness represents one of the common concerns in intensive and commercial dairy farms. Lameness is characterized by gait-related behavioral changes in cows and multiple approaches are being utilized to associate these changes with lameness conditions including data from accelerometers, and other precision technologies. The objective was to evaluate the use of machine learning algorithms for the identification of lameness conditions in dairy cattle. In this study, 310 multiparous Holstein dairy cows from a herd in Northern Colorado were affixed with a leg-based accelerometer (Icerobotics® Inc, Edinburg, Scotland) to obtain the lying time (min/d), daily steps count (n/d), and daily change (n/d). Subsequently, study cows were monitored for 4 months and cows submitted for claw trimming (CT) were differentiated as receiving corrective claw trimming (CCT) or as being diagnosed with a lameness disorder and consequent therapeutic claw trimming (TCT) by a certified hoof trimmer. Cows not submitted to CT were considered healthy controls. A median filter was applied to smoothen the data by reducing inherent variability. Three different machine learning (ML) models were defined to fit each algorithm which included the conventional features (containing daily lying, daily steps, and daily change derived from the accelerometer), slope features (containing features extracted from each variable in Conventional feature), or all features (3 simple features and 3 slope features). Random forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Time series (ROCKET) were used as ML predictive approaches. For the classification of cows requiring CCT and TCT, ROCKET classifier performed better with accuracy (> 90%), ROC-AUC (> 74%), and F1 score (> 0.61) as compared to other algorithms. Slope features derived in this study increased the efficiency of algorithms as the better-performing models included All features explored. However, further classification of diseases into infectious and non-infectious events was not effective because none of the algorithms presented satisfactory model accuracy parameters. For the classification of observed cow locomotion scores into severely lame and moderately lame conditions, the ROCKET classifier demonstrated satisfactory accuracy (> 0.85), ROC-AUC (> 0.68), and F1 scores (> 0.44). We conclude that ML models using accelerometer data are helpful in the identification of lameness in cows but need further research to increase the granularity and accuracy of classification.

Accounting for minimum data required to train a machine learning model to accurately monitor Australian dairy pastures using remote sensing.

Precision in grazing management is highly dependent on accurate pasture monitoring. Typically, this is often overlooked because existing approaches are labour-intensive, need calibration, and are commonly perceived as inaccurate. Machine-learning processes harnessing big data, including remote sensing, can offer a new era of decision-support tools (DST) for pasture monitoring. Its application on-farm remains poor because of a lack of evidence about its accuracy. This study aimed at evaluating and quantifying the minimum data required to train a machine-learning satellite-based DST focusing on accurate pasture biomass prediction using this approach. Management data from 14 farms in New South Wales, Australia and measured pasture biomass throughout 12 consecutive months using a calibrated rising plate meter (RPM) as well as pasture biomass estimated using a DST based on high temporal/spatial resolution satellite images were available. Data were balanced according to farm and week of each month and randomly allocated for model evaluation (20%) and for progressive training (80%) as follows: 25% training subset (1W: week 1 in each month); 50% (2W: week 1 and 3); 75% (3W: week 1, 3, and 4); and 100% (4W: week 1 to 4). Pasture biomass estimates using the DST across all training datasets were evaluated against a calibrated rising plate meter (RPM) using mean-absolute error (MAE, kg DM/ha) among other statistics. Tukey's HSD test was used to determine the differences between MAE across all training datasets. Relative to the control (no training, MAE: 498 kg DM ha-1) 1W did not improve the prediction accuracy of the DST (P > 0.05). With the 2W training dataset, the MAE decreased to 342 kg DM ha-1 (P < 0.001), while for the other training datasets, MAE decreased marginally (P > 0.05). This study accounts for minimal training data for a machine-learning DST to monitor pastures from satellites with comparable accuracy to a calibrated RPM which is considered the 'gold standard' for pasture biomass monitoring.

Effect of harvesting strategy of second-cut orchardgrass silage on feed intake, digestion, and milk production in dairy cows.

We investigated the effects of regrowth interval and first-cut timing on the dietary characteristics of second-cut orchardgrass silage and feed intake and milk production in dairy cows fed second-cut orchardgrass silage. The second-cut grasses were harvested 7w after the first-cut at the early stage (E7w) or at the heading stage (H7w), or harvested 6w after the first-cut at the early stage (E6w) from orchardgrass sward, and then ensiled. We evaluated the effect of regrowth interval by comparing E7w and E6w, and the effect of first-cut timing by comparing E7w and H7w. Six multiparous Holstein cows were used in a replicated 3 × 3 Latin square design, with three dietary treatments: diets containing E7w, E6w, or H7w silage at 30% dietary dry matter. We observed that feeding E6w silage instead of E7w silage increased fiber digestibility, dry matter intake, and milk production; however, the first-cut timing (E7w vs. H7w) did not affect nutrient content and digestibility, feed intake, or lactation performance. These results show that harvesting at short regrowth intervals for second-cut orchardgrass can be an effective strategy for improving feed utilization and milk yield; however, the first-cut timing for second-cut orchardgrass has little impact.

Environmental assessment of phosphorus recovery from dairy sludge: A comparative LCA study.

Phosphate rock is a finite, non-renewable mineral resource that is used primarily in fertiliser production. The scarcity and the increasing demand for this finite material led the European Commission to include it in the critical raw material list in 2014. As a consequence, efforts have been directed towards enhancing material use efficiency, initiating recycling efforts, and formulating waste policies to mitigate the criticality of raw materials. Interest in the development of technologies for nutrient recovery from organic waste streams has increased in recent years, and dairy processing sludge (DPS) is a potential input waste stream. Although the recovery of P from DPS can contribute to more circular flows of nutrients in society, it has to be assessed whether there are also overall environmental gains. This paper reports on a life cycle assessment (LCA) of the environmental impacts of three scenarios for phosphorus (P) recovery involving hydrothermal carbonization (HTC) and struvite precipitation and a comparison to a reference drying scenario. HTC produces a solid fraction (hydrochar), and a liquid fraction (process water) and in one of the scenarios (Scenario 3), leaching the hydrochar for additional P recovery is considered. From the process water as well as from the hydrochar leachate, P is precipitated in the form of struvite. Scenarios 1 and 2 both consider HTC and struvite production with the only difference that the hydrochar is used as a fuel instead of as a fertilizer in the latter case, and Scenario 3 adds leaching of the hydrochar with subsequent struvite production and considers that hydrochar is used as a fuel. In the fourth (reference) scenario, dewatering and drying of DPS is considered. The recovered product use in agriculture was not assessed at this stage. The assessment of the emerging technologies in Scenarios 1-3 was done by studying the technologies in early stages of development but modelling them as more developed in the future. Additional functions beyond the functional unit of one kg of P recovered were handled through a system expansion by substitution approach. This way, the system was credited for calcium ammonium nitrate (CAN) production in all scenarios and for wood chips production in Scenarios 2 and 3. Looking at net outcomes for all scenarios, the life cycle impact indicator results for scenario 2 are lower than the other scenarios in several impact categories. Large gains in scenario 2 are related to the avoided production of wood chips.

An integral assessment of the impact of diet and manure management on whole-farm greenhouse gas and nitrogen emissions in dairy cattle production systems using process-based models.

Feed management decisions are crucial in mitigating greenhouse gas (GHG) and nitrogen (N) emissions from ruminant farming systems. However, assessing the downstream impact of diet on emissions in dairy production systems is complex, due to the multifunctional relationships between a variety of distinct but interconnected sources such as animals, housing, manure storage, and soil. Therefore, there is a need for an integral assessment of the direct and indirect GHG and N emissions that considers the underlying processes of carbon (C), N and their drivers within the system. Here we show the relevance of using a cascade of process-based (PB) models, such as Dutch Tier 3 and (Manure)-DNDC (Denitrification-Decomposition) models, for capturing the downstream influence of diet on whole-farm emissions in two contrasting case study dairy farms: a confinement system in Germany and a pasture-based system in New Zealand. Considerable variation was found in emissions on a per hectare and per head basis, and across different farm components and categories of animals. Moreover, the confinement system had a farm C emission of 1.01 kg CO2-eq kg-1 fat and protein corrected milk (FPCM), and a farm N emission of 0.0300 kg N kg-1 FPCM. In contrast, the pasture-based system had a lower farm C and N emission averaging 0.82 kg CO2-eq kg-1 FPCM and 0.006 kg N kg-1 FPCM, respectively over the 4-year period. The results demonstrate how inputs and outputs could be made compatible and exchangeable across the PB models for quantifying dietary effects on whole-farm GHG and N emissions.

A preliminary study on the feasibility of two different cow-calf contact systems in a pasture-based, seasonal calving dairy system: effects on cow production and health.

Internationally, consumer dissatisfaction with cow-calf separation at birth has led to increased interest in alternative calf-rearing methods, specifically cow-calf contact (CCC) systems. The objectives of this preliminary study were to estimate whether CCC could be incorporated into an Irish spring-calving, pasture-based system, and to investigate the effects on cow milk production and health. Three systems were compared: the conventional Irish system (CONV;18 cows), cow and calf were separated < 1 h postbirth, cows were pasture-based and milked twice-a-day; a full-time access system (FT;14 cows), cow and calf were allowed constant, unrestricted access, were pasture-based, and cows were milked twice-a-day; and a part-time access system (PT;18 cows), cow and calf had unrestricted access when indoors at night, cows grazed outdoors by day while calves remained indoors, and cows were milked once-a-day in the morning. Cows were blocked and balanced across the three systems by previous lactation machine milk yield (MMY), BW, and body condition score (BCS). Following an 8-week CCC period, all calves were weaned (FT and PT underwent a 7-d gradual weaning and separation process) and all cows were milked twice-a-day. Cow MMY was recorded daily and milk composition was recorded weekly; milk data were analysed from weeks 1 to 8 (CCC period), weeks 9 to 35 (post-CCC period), and weeks 1 to 35 (cumulative lactation). Cow BW and BCS were taken weekly for weeks 1-12, and at the end of the lactation. During the CCC period, all systems differed (P < 0.001) in MMY (mean ± SEM; 24.0, 13.6, and 10.3 ± 0.50 kg/d for CONV, FT, and PT cows, respectively). After the CCC period, CONV MMY (20.2 ± 0.48 kg/d) remained higher (P < 0.001) than the FT (16.6 kg/d) and PT cows (15.7 kg/d). The FT and PT cows yielded 24 and 31% less in cumulative lactation MMY and 26 and 35% less in cumulative lactation milk solids yield, respectively, compared to CONV (5 072 ± 97.0 kg and 450 ± 8.7 kg). During the CCC period, somatic cell score was higher (P = 0.030) in PT cows (5.15 ± 0.118) compared to FT cows (4.70 ± 0.118), while CONV (4.94 ± 0.118) were inconclusive to both. The PT cows (523 ± 4.9 and 520 ± 6.8 kg) were heavier than the CONV (474 ± 4.9 and 479 ± 6.8 kg) and FT (488 ± 4.9 and 487 ± 6.8 kg) cows at week 4 and week 8 (both P < 0.001). The PT cows had higher BCS than CONV and FT at all observed times. This preliminary research suggests that although CCC was incorporated without impacting cow health, the two CCC systems investigated negatively affected cow production.

Beliefs, mindset and personality of farm managers working in large commercial dairy herds: Association with calf on-farm mortality.

This study aimed to describe the attitudes and personalities of farm managers (FMs) in large Estonian dairy herds and analyse the potential associations with calf mortality. The study included FMs from 114 free-stall farms with at least 100 cows. Each participant completed a questionnaire that comprised questions about the respondent and various statements to reveal their attitudes towards calves, calf mortality, and farming in general. A 7-point Likert scale was used to record the responses. The data on the number of live births and deaths and animal movement data were gathered from farm records and the Estonian Agricultural Registers and Information Board. The yearly calf mortality risk (%) during the first 21 days (YAG) and mortality rate between 22-90 days of age (OAG) adjusted for the animal time-at-risk were then calculated for each herd. Univariate negative binomial regression analysis was used to identify associations between calf mortality risk/rate, and the studied statements and variables with a p-value < 0.25 were included in a k-modes clustering analysis. The mean calf mortality risk was determined to be 5.9 % (range 0.0-26.8 %) during the first 21 days and mean calf mortality rate was 1.8 (range 0.0-9.2) deaths per 100 calf-months during 22-90 days of age. In both age group analyses, two FMs´ clusters formed based on 17 pre-selected statements. The FMs of the high-mortality cluster were found to be dissatisfied with the calf mortality levels. In the YAG analysis, FMs from high-mortality cluster gave lower priority to the issue of calf mortality, placed high importance on the influence of workers on calf mortality, and were more satisfied with the staff's performance compared to FMs of the cluster of herds with lower calf mortality. They were additionally less satisfied with their own performance and felt less recognized by the farm staff. They were also more inclined to try new products and practices on the farm and demonstrated greater empathy towards cattle. In the OAG analysis, the FMs from the higher-mortality cluster viewed reducing calf mortality more costly, had a less ambitious and target-driven management style, and rated their self-performance lower. This study determined that FMs working in herds with high calf mortality were dissatisfied and did not prioritize addressing calf mortality compared to managers working in farms with lower calf mortality. FMs' attitudes and management styles were associated with calf mortality, while the respondents' personality traits had little influence.

Attention module incorporated transfer learning empowered deep learning-based models for classification of phenotypically similar tropical cattle breeds (Bos indicus).

Accurate breed identification in dairy cattle is essential for optimizing herd management and improving genetic standards. A smart method for correctly identifying phenotypically similar breeds can empower farmers to enhance herd productivity. A convolutional neural network (CNN) based model was developed for the identification of Sahiwal and Red Sindhi cows. To increase the classification accuracy, first, cows's pixels were segmented from the background using CNN model. Using this segmented image, a masked image was produced by retaining cows' pixels from the original image while eliminating the background. To improve the classification accuracy, models were trained on four different images of each cow: front view, side view, grayscale front view, and grayscale side view. The masked images of these views were fed to the multi-input CNN model which predicts the class of input images. The segmentation model achieved intersection-over-union (IoU) and F1-score values of 81.75% and 85.26%, respectively with an inference time of 296 ms. For the classification task, multiple variants of MobileNet and EfficientNet models were used as the backbone along with pre-trained weights. The MobileNet model achieved 80.0% accuracy for both breeds, while MobileNetV2 and MobileNetV3 reached 82.0% accuracy. CNN models with EfficientNet as backbones outperformed MobileNet models, with accuracy ranging from 84.0% to 86.0%. The F1-scores for these models were found to be above 83.0%, indicating effective breed classification with fewer false positives and negatives. Thus, the present study demonstrates that deep learning models can be used effectively to identify phenotypically similar-looking cattle breeds. To accurately identify zebu breeds, this study will reduce the dependence of farmers on experts.

Awareness and adoption of farm biosecurity practices in commercial dairy, pig and poultry farms of Uttar Pradesh (India).

India's livestock sector has been facing significant losses due to episodes of disease outbreaks since time immemorial. Hence, biosecurity measures are very important to maintain and improve animal health along with prevention of disease outbreak. Keeping these facts into consideration, the study was proposed with an objective to assess the existing biosecurity practices adopted by the commercial dairy, pig and poultry farms. The current study was undertaken in the state of Uttar Pradesh as it is the leading state in milk and meat production. A total of 120 farmers were selected randomly including 40 each practicing commercial dairy, pig and poultry farming. An ex-post facto research methodology was used with face-to-face interview and observation to collect data. The biosecurity practices were assessed under seven dimensions such as, location and design of farm, restricted access, isolation and quarantine, cleaning and disinfection, management of feed and water, disposal of carcass, manure and waste, and health management. Results elicited that about 50% of the farmers had medium level of adoption who adopted 18-34 practices out of 51 practices. The average overall adoption score was 34.17 out of 51 (67%) which makes an overall adoption gap of 33%. Maximum adoption gap was seen in case of restricted access (43%) whereas minimum gap in adoption was seen in case of management of feed and water (27%). Pig and poultry farmers showed significantly higher biosecurity measures than dairy farmers (p < 0.05). The more significant contributors to the adoption of biosecurity measures were the level of knowledge of the farmers (p < 0.01). Other factors such as education, income, herd/flock size, Information and Communication Technology utilization, number of trainings also had a significant contribution (p < 0.05) in actual implementation of biosecurity. Hence, better understanding of these measures among the farmers must be ensured by hands on training along with proper demonstration of various procedures involved in maintaining farm biosecurity is need of the hour.

Inseminate without hormonal treatment in dairy sheep farms: exploring the consequences on the sustainability of several contrasted production systems.

Alternatives to hormonal treatments (HTs) in dairy sheep reproduction management are being explored in response to increasing societal concerns regarding animal welfare and food safety. However, hormone-free reproduction implies higher variability in flock performances and additional constraints for timely synchronised artificial insemination (AI) in the flock, impacting the diffusion of genetic progress. The use of the male effect, a well-known practice to induce synchronised oestrus, combined with precision tools (e.g., heat detector), is a plausible way to implement AI without HT in dairy sheep farms. To date, the consequences of such alternative reproduction management on the whole farm sustainability remain unknown. To anticipate these potential impacts, a multiagent model (REPRIN'OV) was used to simulate dairy sheep farms' sustainability indicators (biotechnical, economic, environmental and workload). A reproduction management scenario, including the use of the male effect followed by AI on the adult ewes (HFAI), was simulated and compared to the current reproduction management of four case study farms (Early_conv, Late_conv, Early_org and Late_org). They were selected to represent the different agricultural models (Conventional or Organic) and reproduction seasons (Early - during spring, out of ewes' natural reproduction season - or Late -from early summer to the end of autumn) of the Roquefort Basin's farms in Southern France. Simulation results showed that the HFAI scenario had different consequences depending on the farm's production system type. A negative effect on most key sustainability indicators of the Conv farms was observed, as a significant reduction in the fertility rate, in the proportion of young ewes born from AI (-54% in both farms; P < 0.05) and in the flock's milk production were observed; while the workload and greenhouse gas (GHG) emissions were increased compared to the initial scenario. In the Org farms, HFAI had neutral to positive effects on most indicators as the fertility, milk production of the flock, workload during milking and GHG emissions were barely affected by this scenario, while an increase in the proportion of young ewes born from AI was observed (+39% and + 43% in each farm, respectively; P < 0.05), allowing a better farm gross margin. Still, the workload during lambing was increased in Early_org (+18%; P < 0.05), as Early farms, tended to be more negatively impacted by HFAI than Late ones. Overall, our simulation approach provides interesting elements to exchange with stakeholders on how to progress towards a socially acceptable reproduction management system, for the dairy sheep sector.

Assessing short-term feed efficiency and its association with biological markers in herbage-fed dairy cows.

Feed efficiency is an important trait of dairy production. However, assessing feed efficiency is constrained by the associated cost and difficulty in measuring individual feed intake, especially on pastures. The objective of this study was to investigate short-term feed efficiency traits of herbage-fed dairy cows and screening of potential biomarkers (n = 238). Derived feed efficiency traits were ratio-based (i.e., feed conversion ratio (FCR) and N use efficiency (NUE)) or residual-based (i.e., residual feed intake (RFI), residual energy intake (REI), and residual N intake (RNI)). Thirty-eight Holstein and 16 Swiss Fleckvieh dairy cows underwent a 7-d measurement period during mid- and/or late-lactation. The experimental data (n = 100 measurement points) covered different lactational and herbage-fed system situations: mid-lactation grazing (n = 56), late-lactation grazing (n = 28), and late-lactation barn feeding (n = 16). During each measuring period, the individual herbage intake of each cow was estimated using the n-alkane marker technique. For each cow, biomarkers representing milk constituents (n = 109), animal characteristics (n = 13), behaviour, and activity (n = 46), breath emissions (n = 3), blood constituents (n = 35), surface, and rectal temperature (n = 29), hair cortisol (n = 1), and near-infrared (NIR) spectra of faeces and milk (n = 2) were obtained. The relationships between biomarkers and efficiency traits were statistically analysed with univariate linear regression and for NIR spectra using partial least squares regression with feed efficiency traits. The feed efficiency traits were interrelated with each other (r: -0.57 to -0.86 and 0.49-0.81). The biomarkers showed varying R2 values in explaining the variability of feed efficiency traits (FCR: 0.00-0.66, NUE: 0.00-0.74, RFI: 0.00-0.56, REI: 0.00-0.69, RNI: 0.00-0.89). Overall, the feed efficiency traits were best explained by NIR spectral characteristics of milk and faeces (R2: 0.25-0.89). Biomarkers show potential for predicting feed efficiency in herbage-fed dairy cows. NIR spectra data analysis of milk and faeces presents a promising method for estimating individual feed efficiency upon further validation of prediction models. Future applications will depend on the ability to improve the robustness of biomarkers to predict feed efficiency in a greater variety of environments (locations), managing conditions, feeding systems, production intensities, and other aspects.

Unraveling the genetic basis of methane emission in dairy cattle: a comprehensive exploration and breeding approach to lower methane emissions.

Ruminant animals, such as dairy cattle, produce CH4, which contributes to global warming emissions and reduces dietary energy for the cows. While the carbon foot print of milk production varies based on production systems, milk yield and farm management practices, enteric fermentation, and manure management are major contributors togreenhouse gas emissions from dairy cattle. Recent emerging evidence has revealed the existence of genetic variation for CH4 emission traits among dairy cattle, suggests their potential inclusion in breeding goals and genetic selection programs. Advancements in high-throughput sequencing technologies and analytical techniques have enabled the identification of potential metabolic biomarkers, candidate genes, and SNPs linked to methane emissions. Indeed, this review critically examines our current understanding of carbon foot print in milk production, major emission sources, rumen microbial community and enteric fermentation, and the genetic architecture of methane emission traits in dairy cattle. It also emphasizes important implications for breeding strategies aimed at halting methane emissions through selective breeding, microbiome driven breeding, breeding for feed efficiency, and breeding by gene editing.

Effect of milking time on yield, composition, and antimicrobial components of milk in lactating goats.

Various studies have attempted to improve the milk yield and composition in dairy animals. However, no study has examined the effects of milking at different times on milk yield and composition. Therefore, this study aimed to compare the yield, composition, and antimicrobial components of milk obtained from milking at different times in lactating goats. Eight goats were milked once daily at different times for three consecutive weeks (first week: 06:00 h; second week: 09:00 h; and third week: 12:00 h). The light ranged from 06:30 to 19:00 h. Milk and blood samples were collected once a day during milking time. Milking at 09:00 h resulted in a significantly higher milk yield than that obtained after milking at 06:00 and 12:00 h. Prolactin levels in plasma and the fat, Na+, ß-defensin, and S100A7 (antimicrobial component) levels in milk were the lowest in the 09:00 h milking. These results indicate that milk yield, composition, and antimicrobial components can be affected by milking time, which may be related to the altered concentration of prolactin in the blood. These findings provide a rational basis for achieving maximal milk production with strong immunity by changing to a more effective milking time.