Milking System Research Articles

Exploring the oil-water interfacial behaviour of pea protein-guar gum/gellan gum mixtures relating to stability and in vitro protein digestion of model pea milk system

Polysaccharides are effective stabilisers for plant-based milks, but their interfacial adsorption behaviours in plant milk system and effects on plant protein digestibility are still unclear. This study analysed the oil-water interfacial adsorption behaviours of pea protein concentrate (PPC) and isolate (PPI) mixed with neutral guar gum and anionic gellan gum to understand the stability and in vitro protein digestion of corresponding model pea milk system. Adding guar gum or gellan gum enhanced the interfacial adsorption stability of pea proteins without compromising proteolysis during gastrointestinal digestion. Gellan gum performed better than guar gum for long-term co-stabilising the emulsion with pea proteins, due to its electrostatic repulsion with pea proteins and stronger steric hindrance induced by thicker adsorbed interfacial layers (~10 % or ~37 % higher thickness than guar gum counterparts) as detected by a quartz crystal microbalance with dissipation (QCM-D) after rinsing. The model pea milks with 0.1 % (wt%) gellan gum were stable at 4 °C for 28 days regardless of protein types. The presence of polysaccharides at the interface enabled oil droplets to be kept separate during in vitro gastrointestinal digestion, improving the final proteolysis by ~4 to ~27 %. This result is conducive to selecting polysaccharides for developing pea protein-based beverages.

Effect of training method and dairy cow personality traits on adaptation to an automated milking system

Training dairy cows on the automated milking system (AMS) can improve their performance, however, the ideal training method and how their individual personality relates to training is unknown. The objectives of this study were to determine: 1) the effect of AMS training method on adaptation of primiparous cows to an AMS, 2) whether the personality of a cow affects their adaptation to the AMS, and 3) whether certain personality types adapt better based on the type of training they receive. Forty-eight primiparous Holstein dairy cows, who had not previously been milked by an AMS, were enrolled in the study at ∼85 DIM and were assessed for personality traits using a combined arena test comprised of 3 parts: a novel arena test, a novel object test, and a novel human test. Cows were allocated into 1 of 4 AMS training treatments (n = 12): control (CON; no training), environment exposure only (ENV), environment and AMS concentrate provision (PEL), and environment and mechanics exposure (MEC). Cows in the ENV, PEL, and MEC treatments were subjected to training 4 × /d for 4 d, and then cows from all 4 treatments were milked on the AMS in the evening of the 4th training d. Milking activity and production were recorded for the first 14 d on the AMS. PEL cows had fewer visits to the AMS, fewer milkings, and fewer voluntary milkings compared with CON cows across the 14 d. Cows on all experimental treatments had more fetching events than CON cows, while MEC and ENV treatment cows had a higher milk yield compared with those on the CON treatment. Principal component analysis of the behaviors recorded during the personality assessment revealed 2 factors interpreted as personality traits, "explore-active" and "bold." Across all cows, more "explore-active" cows had greater milk yield. Only the performance of ENV cows was associated with personality; ENV cows who scored low for "explore-active" differed from CON cows, through increased visits and voluntary milkings. Overall, the results demonstrate that providing concentrate on its own during AMS training may not be motivating enough to improve adaptation and performance. However, exposing cows to the mechanics (e.g., the robotic arm and sounds of the AMS) before first milking may improve milk yield. Finally, cow personality may influence the performance of cows trained using less complicated training methods, such as only exposing them to the environment of the AMS.

Reducing life cycle environmental impacts of milk production through precision livestock farming

In recent decades, the livestock sector has significantly improved its efficiency, productivity, and environmental sustainability. Precision Livestock Farming (PLF) represents a driver in this direction, since it enables to monitor individual animals and herds, and supports the farmer in making better decisions. Although the benefits are clear on a livestock perspective, it is difficult to quantify the environmental benefit of having technology on farm, mostly due to the complexity of collecting data on the same farm before and after a certain solution.In this context, this paper focuses on the assessment of the environmental sustainability of a case-study Italian dairy cattle farm where different technologies were installed one by one: first a mechanical ventilation system (MV) and second an automatic milking system (AMS), without introducing other significant changes to the farm management and practices in the meantime. The environmental impact of milk production on the farm was quantified through the Life Cycle Assessment (LCA) method, and the initial farm configuration was compared with the two scenarios in which each technology was incorporated. Fat and protein corrected milk (FPCM) was used as Functional Unit, and a cradle to farm gate system boundary and biophysical allocation method were selected. This enabled to provide valuable insights for stakeholders about the effect on the environmental sustainability of the use of the two technologies. The results show that for all the evaluated impact categories there is an environmental benefit of the improved scenarios. The biggest benefit can be observed with the installation of mechanical ventilation, to which correspond benefits in terms of animal health, welfare and productivity. Then, also AMS entails sustainability improvements, mainly linked with increased efficiency and productivity. In conclusion, the use of technology on dairy farms improves not only the farm efficiency and the animal management, but also the environmental sustainability. Furthermore, the rapid technological advancements may further enhance this positive trend in reducing the contribution of livestock farming to the environmental impacts provided that farmers adopt them.

Comparing the Performance of Automatic Milking Systems through Dynamic Testing Also Helps to Identify Potential Risk Factors for Mastitis.

Automatic milking systems (AMSs) are revolutionizing the dairy industry by boosting herd efficiency, primarily through an increased milk yield per cow and reduced labor costs. The performance of milking machines, whether traditional or automated, can be evaluated using advanced vacuum meters through dynamic testing. This process involves scrutinizing the system and milking routine to identify critical points, utilizing the VaDia™ logger (BioControl AS, Rakkestad, Norway). Vacuum recordings were downloaded and analyzed using the VaDia Suite™ software under the guidance of a milking specialist. Access to data from AMSs across various manufacturers and herds facilitated a retrospective study aimed at describing and comparing key milk emission parameters for different AMS brands while identifying potential mastitis risk factors. Using the proper statistical procedures of SPSS 29.1 (IBM Corp., Armonk, NY, USA), researchers analyzed data from 4878 individual quarter milkings from cows in 48 dairy herds. Results indicated a significant variability in milking parameters associated with quarter milk yield and AMS brand. Notably, despite AMSs standardizing teat preparation and stimulation, this study revealed a surprisingly high frequency of two major mastitis risk factors-bimodality and irregular vacuum fluctuations-occurring more frequently than in conventional milking systems. This study, one of the few comparing different AMS brands and their performance, highlights the crucial role of dynamic testing in evaluating AMS performance under real-world conditions.

Association between automatic milking system parameters and intramammary infections in dairy cows at dry-off

IntroductionThe current global concern over increasing antimicrobial resistance among animal and human pathogens has motivated efforts to reduce antimicrobial drug use in food animals and its impact on antimicrobial resistance. One such strategy is to use selective dry cow therapy (SDCT) in dairy cows, which involves treating only cows with intramammary infection (IMI) at dry-off. However, efficient methods are needed to identify cows with IMI at dry-off to implement SDCT. Automatic Milking Systems (AMS) data may help farmers identify cows with IMI when individual Somatic Cell Count (SCC) is not routinely tested. This study assessed the correlation between cow-level and quarter-level AMS parameters and IMI at dry-off.Methods & ResultsA total of 733 udder quarters (comprising both Primiparous [PRIM] and Multiparous [MULT] cows) were sampled and categorized for IMI based on bacterial growth and SCC. Data were aggregated both daily and into 7-day and 15-day intervals preceding dry-off. The quarter-level prevalence of bacterial growth at dry-off was 24.28% overall. When stratified by parity, logistic regression analysis at 15 days to dry-off revealed that the average difference in mastitis detection index (MDi) in PRIM, MDi, and standard deviation milk flow rate in MULT were associated with increased odds of IMI at dry-off. Similarly, data from 7 days to dry-off revealed that average peak milk flow rate in PRIM, and MDi in MULT were associated with increased odds of IMI at dry-off. However, an increase in average milk yield was associated with decreased odds of IMI.Discussion & ConclusionOur findings underscore the significance of MDi, milk flow rate, peak milk flow rate, and milk yield in predicting IMI at dry-off. Notably, stronger associations were observed with data collected 7 days preceding dry-off. Further research is warranted to refine and validate algorithms amalgamating these variables for precise IMI prediction in cows at dry-off.

A computer vision approach for the automatic detection of social interactions of dairy cows in automatic milking systems

The integration of digital technologies and Artificial Intelligence (DT&AI) in veterinary practice is one of the key topics to improve Herd Health Management (HHM). The HHM includes the prevention of diseases, the assessment of the welfare, and the sustainability production of farm animals. In dairy cattle farming, particular attention is paid to automatic cow detection and tracking, as such information is closely related to animal welfare and thus to possible health issues. Cows are highly social animals; therefore, a better comprehension of social context can help improve their management and welfare. In the field of Precision Livestock Farming, computer vision represents a suitable and non-invasive method for automatic cow detection and tracking. In this study, we developed and tested the reliability of a deep learning-based computer vision system for the automatic recognition of dairy cows in a barn equipped with Automatic Milking System. We aimed to build the social network of 240 dairy cows (primiparous and multiparous) to understand how social interactions can influence their welfare and productivity.

Different Types of Milk Flow Curves and Factors Affecting Milkability in Buffalo Species

Buffaloes are characterized by longer teats and teat canals and stronger muscular resistance of the teat wall than cattle; it is necessary to have a high vacuum level to open the teat canal and begin milk ejection. In buffalo milking management, milk yield, and flow profiles are essential parameters to record and evaluate. The milking machine is a critical point, and the characteristics of the milking vacuum and the pulsation rate are closely related to milk flow observations. In Italy, the most used vacuum levels are 44-46 kPa (range 40-53 kPa). The data on the milkability traits of the Mediterranean Italian breed made it possible to classify eight different types of milk flow curves due to anatomical, physiological, and management differences. This study aims to evaluate the main factors influencing milkability in dairy buffaloes. The results suggest the detachment of the milking cluster to reduce the decreasing and blind phases with the following advantages: reduction of the total milking time and consequently of the worker's time, improvement of the farmer's profitability and milk quality through decreasing the incidence of mastitis. Milk ability is influenced by physiological, sanitary, management, and genetic factors. In Mediterranean Italian buffaloes milked with the Automatic Milking System (AMS), a considerable variation in milk ejection and, consequently, in the milk flow curve was found compared to the conventional one, with better pre-stimulation, independent milk ejection for each teat, optimal milking of all quarters. In conclusion, continuous milkability monitoring will help optimize milking practices by reducing labor time and increasing farmers’ income through better milk quality. In addition, the identification of buffaloes with desirable types of milk flow curves could be helpful for buffalo breeders’ associations to address farmer management and to define potential new breeding objectives.

Influence of Preprocessing Methods of Automated Milking Systems Data on Prediction of Mastitis with Machine Learning Models

Missing data and class imbalance hinder the accurate prediction of rare events such as dairy mastitis. Resampling and imputation are employed to handle these problems. These methods are often used arbitrarily, despite their profound impact on prediction due to changes caused to the data structure. We hypothesize that their use affects the performance of ML models fitted to automated milking systems (AMSs) data for mastitis prediction. We compare three imputations—simple imputer (SI), multiple imputer (MICE) and linear interpolation (LI)—and three resampling techniques: Synthetic Minority Oversampling Technique (SMOTE), Support Vector Machine SMOTE (SVMSMOTE) and SMOTE with Edited Nearest Neighbors (SMOTEEN). The classifiers were logistic regression (LR), multilayer perceptron (MLP), decision tree (DT) and random forest (RF). We evaluated them with various metrics and compared models with the kappa score. A complete case analysis fitted the RF (0.78) better than other models, for which SI performed best. The DT, RF, and MLP performed better with SVMSMOTE. The RF, DT and MLP had the overall best performance, contributed by imputation or resampling (SMOTE and SVMSMOTE). We recommend carefully selecting resampling and imputation techniques and comparing them with complete cases before deciding on the preprocessing approach used to test AMS data with ML models.

PSXI-30 Economic impact of pre-training on dairy cattle automatic milking system acclimation

Abstract Pre-training in automatic milking systems (AMS) has the potential to increase milk production and milk quality. In a recent study, cows that experienced pre-training (TRT; i.e. intentional training access with an AMS prior to first AMS milking) had greater milk yield and fat percentages compared with no pre-training (38.4 vs. 37.6 ± 0.2 kg/d; 4.75 vs. 4.38 ± 0.06%; P < 0.01, and < 0.01 respectively). Similarly, cows without pre-training had greater somatic cell count (SCC; 298,860 vs. 188,220 ± 10,700 cells/mL; P < 0.001). The time required for pre-training could be a limiting factor (40 ± 10 h/wk), and the economic implications of labor versus long-term benefits must be examined. To that end, a stochastic simulation tool was developed to consider the increased costs of labor and the potential benefits of improved milk yield, milk fat percentage, and decreased somatic cell count. The GRKS distribution with minimum, mean, and maximum values was used to model increases in milk yield (0, 1.4, 1.8 kg), fat percentage (0, 3.5%, 4.5%), and labor cost ($0.0011, $0.0016, $0.0020 per h) and decreases in SCC (0, 120, 130 x 103 cells/mL) per hundredweight of milk produced. Baseline values for milk production ranged from 14.7 to 59.2 kg/cow/d in 4.4 kg increments with fat percentage of 3.5% and SCC of 312,000 cells/mL. The model assumed a minimum increase across milk yield, fat, and SCC of 0 (no change). The Simetar add-on in Microsoft Excel simulated 500 iterations across three herd size scenarios (60, 120, and 480 cows) and calculated the marginal return on investment across a 90-d period for all milk production ranges. Regardless of starting milk production level, pre-training had a positive economic impact across all levels (30 to 50 h) and herd sizes (Table 1). Financial impact per cow per d with input of 30, 40, and 50 h ranged from $0.58 to $0.73, $0.56 to $0.71, and $0.54 to $0.70. The majority of simulations returned a positive marginal impact for pre-training. If pre-training resulted in a loss, it ranged from $242 to $1,937, $323 to $2,585, $405 to $3,246, across 30, 40, and 50 hours, respectively. Based on these results, the investment in pre-training time was consistently beneficial for simulated herds.

87 Estimation of genetic parameters for activity levels in North American Holstein cattle

Abstract High-producing dairy cows face various challenges during their productive life, including metabolic and infectious diseases, heat stress, and intensive management practices. Therefore, dairy cattle breeding programs have begun to focus on novel traits related to the overall resilience of the cows. Resilience has been defined as the ability of an animal to be minimally affected or to recover quickly from environmental disturbances while maintaining a certain level of productivity. In dairy cattle, resilience can be evaluated using measurements of longitudinal indicator traits, such as activity level, which are repeatedly measured throughout the lifetime of the animal. Variability in activity (defined in this study as average steps per hour and daily steps taken) might be a key indicator of resilience, due to activity of contemporary group animals deviating from normal behavior in less resilient cattle. Before resilience indicators are defined based on variability in certain longitudinal traits, there is a need for evaluating the genetic background of the source variable. Therefore, the primary objective of this study was to estimate variance components and genetic parameters of activity traits in lactating Holstein cows. The data was collected from a large dairy farm located in Indiana, using milking systems. Records from 6,332 Holstein cows for the traits of average activity per hour and number of daily steps were used in the analyses. The models used for the estimation of variance components included the significant (P < 0.05) fixed effects of contemporary group defined based on the concatenation of calving year and season, parity number (1, 2, 3+), pregnancy group (0 mo, 1-3 mo, 4-6 mo, and 7-9 mo), and days in milk (2-wkclasses), and the random effects of direct additive genetic, permanent environment, and residual effects. Genetic parameters were estimated for average activity per hour and daily steps for all parities together. Heritability estimates were calculated based on single-trait repeatability models and the (AI) REML method implemented in the BLUPF90+ software. Daily steps taken had a heritability (± SE) of 0.05 (± 0.02) and a repeatability of 0.29 (± 0.02). Activity per hour had a heritability estimate of 0.12 (± 0.04) and a repeatability of 0.57 (± 0.01). These results indicate that activity level is heritable in North American Holstein cattle and can be added to selection indexes if proven to be a key auxiliary trait for improving dairy cattle sustainability. As a next step, we will investigate the genetic relationship of activity traits with other relevant traits and derive resilience indicators based on variability in activity level.

517 The effects of pellet starch concentration and allocation amount for Holstein cows in peak, mid, and late lactation in an automatic milking system

Abstract This study evaluated the effects of pellet starch concentration and amount of pellet delivered in an automated milking system (AMS) on AMS pellet and partial mixed ration (PMR) intake, milk and milk component yield, and milking and feeding behavior for Holstein cows at different stages of lactation. Twenty-four Holstein cows at peak [n = 8; 85 ± 25.7 days in milk (DIM)], mid (n = 8; 185 ± 35.1 DIM) or late (n = 8; 290 ± 69.5 DIM) lactation (3 squares/DIM category), housed in a free-stall barn with a feed-first guided traffic flow AMS, were used. Treatments included low (LS; 24% DM) or high (HS; 34% DM) starch pellets that were provided at low (LA; 2 kg/d DM) or high (HA; 6 kg/d DM) quantities within replicated 4 × 4 Latin square design. Each period lasted 21 d including 16 d of adaptation and 5 d of data and sample collection to evaluate feed intake and behavior, milking characteristics, milk and milk component yields. Pellet starch did not affect the amount of pellet consumed, but HA cows consumed more pellet than LA (4.3 vs. 1.8 kg/d; P < 0.01). Relative to LA, HA had greater pellet refused in the AMS (P < 0.01) and decreased PMR intake (P = 0.04). Total DMI was 1.3 kg/d greater for HA than LA cows (P = 0.05). Pellet starch and DIM did not affect PMR intake or DMI. Neither pellet starch nor allocation affected the number of PMR meals; however, LA increased PMR eating time by 20 min/d (P < 0.01) and PMR meal length by 2 min/meal (P = 0.03). Milking frequency was not affected by pellet starch or DIM, but HA tended to increase total milking frequency (2.7 vs. 2.6 no/d; P = 0.06) over LA, with greater voluntary milkings (2.5 vs 2.3 no/d; P < 0.01). Milk yield/visit and milking duration were not affected by pellet starch or allocation. Milk yield was not affected by pellet starch, or the amount allocated averaging 43.2, 41.3 and 43.2 kg/d for peak, mid, and late lactation cows (P ≥ 0.19). Compared with LS, HS decreased milk fat concentration (4.1 vs 3.9%; P < 0.01) and providing the HA reduced milk fat concentration (4.1 vs 3.96%; P < 0.01) when compared with LA; however, neither pellet starch nor allocation affected fat yield, averaging 1.67 kg/d (P ≥ 0.15). True protein yield was not affected. Cows fed the LA had greater milk urea nitrogen (14.8 mg/dL) relative to HA (14.3 mg/dL; P = 0.03). Increasing the amount of pellet allocated in the AMS reduced PMR intake, while increasing total DMI and resulted in greater amounts of pellet refusals by cows; however, greater amounts of pellet may increase attendance at the AMS without affecting milk or milk component yields. Starch concentration of the pellet had little effect on productivity.

Improving Lameness Detection in Cows: A Machine Learning Algorithm Application

The deployment of diverse data-generating technologies in livestock farming holds the promise of early disease detection and improved animal well-being. In this paper, we combine routinely collected dairy farm and herd data with weather and high frequency sensor data from 6 farms to predict new lameness events in various future periods, spanning from the following day to 3 weeks. A Random Forest classifier, using input features selected by the Boruta Algorithm, was used for the prediction task; effects of individual features were further assessed using partial dependence plots. We achieve precision scores of up to 93% when predicting lameness for the next 3 weeks and when using information from the last 3 weeks, combined with a balanced accuracy of 79%. Removing sensor data results have tendency to reduce the precision for predictions, especially when using information from the last one,2 or 3 weeks. Moving to a larger data set (without sensor data) of 44 farms keeps the similar balanced accuracy but reduces precision by more than 30%, revealing a substantial a trade-off in model quality between false positives (false lameness alerts) and false negatives (missed lameness events). Sensor data holds promise to further improve the precision of these models, but can be partially compensated by high resolution data from other systems, such as automated milking systems.

Impact of dairy cow personality traits and concentrate allowance on their response to training and adaptation to an automated milking system

The objectives of this study were to determine: 1) if dairy cow personality traits and concentrate allowance are associated with the behavior and performance of cows during training to use an automated milking system (AMS); and 2) if these factors were associated with the behavior and performance of cows after AMS training. Twenty-nine mid- to late-lactation Holstein cows (218 ± 49 DIM), who were milking on a rotary parlor and had never previously been milked in an AMS, were enrolled in this study. Cows were assigned to 1 of 2 dietary treatments, consisting of a basal partial mixed ration (PMR) common to both treatment groups, with a concentrate allowance (on dry matter basis) of: 1) 2.0 kg/d in the AMS (L-Tx); or 2) 6.0 kg/d in the AMS (H-Tx). Cows were trained to use the free-traffic AMS, with supervised milkings, over 72 h and were milked in this system for 63 d after training was complete. Variables relating to feeding behavior, milking activity, and production were measured from the start of AMS training until the end of the study. Between 42 and 63 d after AMS introduction, each cow was assessed for personality traits using a combined arena test consisting of exposure to a novel environment, novel object, and novel human. Principal components analysis of behaviors observed during the personality assessment revealed 2 factors (interpreted as boldness and activeness traits) that together explained 85% of the variance; each cow received a score for each trait. Associations between dietary treatment and personality traits with feeding behavior, milking activity, and production were analyzed using mixed-effect linear and logistic regression models. Cows with greater scores for the active trait produced less milk during the 3 d of AMS training compared with cows with lower scores. Within the H-Tx, more active cows had a 3.92 times greater risk of kicking off teat cups during AMS training than less active cows. However, during the 8 wk after training, more active cows had a 1.37 times lesser risk of teat cup kickoffs than those that were less active. Cows on the H-Tx produced 4.4 kg/d more energy-corrected milk compared with cows on the L-Tx in the 8 wk after training. During the 8 wk after AMS training the cows on the H-Tx consumed an average of 21.4 kg/d of PMR and were delivered 4.6 kg/d of AMS concentrate, while the L-Tx cows consumed 23.4 kg/d PMR and were delivered 2.0 kg/d of AMS concentrate. The results indicate that both dairy cow personality traits and AMS concentrate allocation influence their response to AMS training and subsequent feeding and milking behavior and production.

Early-Life Exposure to 4-Hydroxy-4'-Isopropoxydiphenylsulfone Induces Behavioral Deficits Associated with Autism Spectrum Disorders in Mice.

Exposure to bisphenol A (BPA) during gestation and lactation is considered to be a potential risk factor for autism spectrum disorder (ASD) in both humans and animals. As a novel alternative to BPA, 4-hydroxy-4'-isopropoxydiphenylsulfone (BPSIP) is frequently detected in breast milk and placental barrier systems, suggesting potential transmission from the mother to offspring and increased risk of exposure. Gestation and lactation are critical periods for central nervous system development, which are vulnerable to certain environmental pollutants. Herein, we investigated the behavioral impacts and neurobiological effects of early-life exposure to BPSIP (0.02, 0.1, and 0.5 mg/kg body weight/day) in mice offspring. Behavioral studies indicated that BPSIP exposure induced ASD-like behaviors, including elevated anxiety-related behavior and decreased spatial memory, in both male and female pups. A distinct pattern of reduced social novelty was observed only in female offspring, accompanied by significant alterations in antioxidant levels. Transcriptome analysis demonstrated that differentially expressed genes (DEGs) were mainly enriched in pathways related to behaviors and neurodevelopment, which were consistent with the observed phenotype. Besides, a decrease in the protein levels of complex IV (COX IV) across all tested populations suggests a profound impact on mitochondrial function, potentially leading to abnormal energy metabolism in individuals with autism. Additionally, changes in synaptic proteins, evidenced by alterations in synapsin 1 (SYN1) and postsynaptic density protein-95 (PSD95) levels in the cerebellum and hippocampus, support the notion of synaptic involvement. These findings suggest that BPSIP may induce sex-specific neurotoxic effects that involve oxidative stress, energy generation, and synaptic plasticity.

Effects of subclinical mastitis on automatic milking system data, hematological and biochemical parameters, and milk composition in Holstein cows.

Subclinical mastitis decreases milk production and quality, despite the normal appearance of the mammary glands and milk. Herein, we aimed to investigate changes in factors monitored via automatic milking systems (AMS) prior to subclinical mastitis onset and identify differences in hematological and biochemical parameters and milk composition at subclinical mastitis onset. Thirty-two Holstein cows were divided into two groups according to somatic cell counts (SCC) from AMS and milk composition analysis and the California mastitis test (CMT): healthy cows (controls [CON], n=16, SCC <500×103 cells/ml and negative for CMT) and cows with subclinical mastitis (SCM, n=16, SCC ≥500×103 cells/ml and positive for CMT). Eventually, 121 milk samples from the CON ([mCON], n=60) and SCM ([mSCM], n=61) groups were obtained; SCM samples were categorized as those from non-inflamed (mNQ) or subclinically-inflamed (mIQ) quarters. We evaluated AMS factors; hematological, biochemical, and milk composition parameters; and bacterial isolation. In cows with SCM, milk yield decreased and electrical conductivity (EC) changed before disease onset. Milk EC decreased in mNQ although increased in mIQ (p<0.05). The SCM group had higher globulin levels and lower basophil counts; albumin-to-globulin ratio; and total cholesterol, albumin, and blood urea nitrogen levels than the CON group (p<0.05). The mIQ group had higher SCC but lower levels of lactose and milk solids-not-fat than those in the mCON and mNQ groups (p<0.05). The mCON group had higher levels of milk non-protein nitrogen than the mNQ group (p<0.05). Opportunistic mastitis pathogens were isolated in the mIQ group. Changes in milk yield and EC measured using AMS occurred prior to subclinical mastitis, which may be associated with variation in basophil counts; albumin-to-globulin ratio; and total cholesterol, albumin, BUN, globulin, SCC, milk lactose, and milk solids-not-fat levels at disease onset. These findings provide new insights into early-stage subclinical mastitis.

Цифровая маркировка молока и молочной продукции как правовой механизм обеспечения продовольственной безопасности России

The article examines the features of the functioning of the new established digital labeling system for milk and dairy products as an object of ensuring food security in the Russian Federation. As part of the analysis, a number of methods of scientific knowledge were used, which made it possible to determine the relevance of studying this issue in the context of digitalization of Russian society. The study of this object of research is based on consideration of the regulatory framework in this area. The results of the study were the identification of a set of problems in organizing the implementation of activities by employees of economic security and anti-corruption departments to identify and solve crimes in the sphere of circulation of milk and dairy products.

Effects of Early Lactation Milking Frequency in an Automated Milking System on Cow Performance.

Automated milking systems (AMS) are increasingly adopted for dairy cow production, promoting individualized cow management dependent on factors like lactation stage, age, and productivity. The study objective was to investigate the effects of early lactation milking frequency on cows milked via AMS. Multiparous Holstein cows blocked by parity and due date were randomly assigned to treatments (n = 8 per treatment): three (3X) or six (6X) milkings per day (MPD). The experimental phase (EXP) was defined as 4 to 29 days in milk (DIM). The AMS settings were programed so 3X cows were limited to three MPD while 6X cows were allowed six MPD. Afterwards was the carry over phase (CO) ranging from 30 to 90 DIM; all cows were allowed up to six MPD. Measurements by the AMS included bodyweight, milk yield (MY), and pellet intake. Weekly composite milk samples were analyzed for macronutrient composition and fatty acid (FA) profile. Coccygeal blood was sampled at 3, 8 ± 1, and 13 ± 1 DIM; concentrations of blood plasma analytes were quantified. Greater MPD was achieved for 6X cows versus 3X cows during EXP, but similar during the CO. Daily MY was non-separable during the EXP while 6X cows in their third or greater lactation group (3 + LG) had greater MY than 3X cows of the same LG during the CO. Milk fat content and 4% fat-corrected MY were both greater for 6X, 3 + LG cows during the EXP compared to 3X, 3 + LG cows. Milk FA methyl esters (FAME) proportions were different between MPD groups, with 6X, 3 + LG cows having the lowest short, even-chain FA from de novo or post-absorptive origin. Differences in analytes indicated that 6X, 3 + LG cows experienced metabolic stress and incorporated greater FA from adipose tissue. Greater early lactation MPD in AMS may shift cow nutrient partitioning to support greater production in 3+ parity cows.

On Developing a Machine Learning-Based Approach for the Automatic Characterization of Behavioral Phenotypes for Dairy Cows Relevant to Thermotolerance

The United States is predicted to experience an annual decline in milk production due to heat stress of 1.4 and 1.9 kg/day by the 2050s and 2080s, with economic losses of USD 1.7 billion and USD 2.2 billion, respectively, despite current cooling efforts implemented by the dairy industry. The ability of cattle to withstand heat (i.e., thermotolerance) can be influenced by physiological and behavioral factors, even though the factors contributing to thermoregulation are heritable, and cows vary in their behavioral repertoire. The current methods to gauge cow behaviors are lacking in precision and scalability. This paper presents an approach leveraging various machine learning (ML) (e.g., CNN and YOLOv8) and computer vision (e.g., Video Processing and Annotation) techniques aimed at quantifying key behavioral indicators, specifically drinking frequency and brush use- behaviors. These behaviors, while challenging to quantify using traditional methods, offer profound insights into the autonomic nervous system function and an individual cow’s coping mechanisms under heat stress. The developed approach provides an opportunity to quantify these difficult-to-measure drinking and brush use behaviors of dairy cows milked in a robotic milking system. This approach will open up a better opportunity for ranchers to make informed decisions that could mitigate the adverse effects of heat stress. It will also expedite data collection regarding dairy cow behavioral phenotypes. Finally, the developed system is evaluated using different performance metrics, including classification accuracy. It is found that the YoloV8 and CNN models achieved a classification accuracy of 93% and 96% for object detection and classification, respectively.

Opportunities to integrate Ecosystem Services into Life Cycle Assessment (LCA): a case study of milk production in Brazil

World dairy production is growing rapidly having increased by 339 million tons over the last twenty years. However, it remains unclear how anthropic activities in the milk sector can impact the Ecosystem Services (ES) supply to society. The aim of this study was to propose and determine the Net Environmental Performance (NEP) of different milk production systems. For this purpose, a case study on a confined compost barn farm, located in southeastern Brazil was selected as reference scenario and compared with three other systems. The mapping of ES benefits was carried out using the Common International Classification of Ecosystem Services, while environmental impacts were calculated using Life Cycle Assessment (LCA). The LCA results and ecosystem benefits were combined and converted into monetary units to calculate the NEP per 1 kg of milk. The results indicated that semi-confined systems had the worst environmental performance (90 % more impacts) compared to the compost barn milk system. On the other hand, confined systems generate few ES benefits, but their environmental impacts were lower for most LCA impact categories (up to 87 % minimized impacts) compared to semi-confined systems. Finally, we concluded the confined systems in SP and PR showed the best NEP (1.07 and 1.48) aiming for both environmental impacts and ES benefits to fit the win–win situation.

The Short-Term Effects of Altering Milking Intervals on Milk Production and Behavior of Holsteins Milked in an Automated Milking System

The Short-Term Effects of Altering Milking Intervals on Milk Production and Behavior of Holsteins Milked in an Automated Milking System