Unlocking insights: text mining analysis on the health, welfare, and behavior of cows in automated milking systems.

Automated Milking Systems (AMS) have undergone significant evolution over the past 30 yr, and their adoption continues to increase, as evidenced by the growing scientific literature. These systems offer advantages such as a reduced milking workload and increased milk yield per cow. However, given concerns about the welfare of farmed animals, studying the effects of AMS on the health and welfare of animals becomes crucial for the overall sustainability of the dairy sector. In the last few years, some analysis conducted through text mining (TM) and topic analysis (TA) approaches have become increasingly widespread in the livestock sector. The aim of the study was to analyze the scientific literature on the impact of AMS on dairy cow health, welfare, and behavior: the paper aimed to produce a comprehensive analysis on this topic using TM and TA approaches. After a preprocessing phase, a dataset of 427 documents was analyzed. The abstracts of the selected papers were analyzed by TM and a TA using Software R 4.3.1. A Term Frequency-Inverse Document Frequency (TFIDF) technique was used to assign a relative weight to each term. According to the results of the TM, the ten most important terms, both words and roots, were feed, farm, teat, concentr, mastiti, group, SCC (somatic cell count), herd, lame and pasture. The 10 most important terms showed TFIDF values greater than 3.5, with feed showing a value of TFIDF of 5.43 and pasture of 3.66. Eight topics were selected with TA, namely: 1) Cow traffic and time budget, 2) Farm management, 3) Udder health, 4) Comparison with conventional milking, 5) Milk production, 6) Analysis of AMS data, 7) Disease detection, 8) Feeding management. Over the years, the focus of documents has shifted from cow traffic, udder health and cow feeding to the analysis of data recorded by the robot to monitor animal conditions and welfare and promptly identify the onset of stress or diseases. The analysis reveals the complex nature of the relationship between AMS and animal welfare, health, and behavior: on one hand, the robot offers interesting opportunities to safeguard animal welfare and health, especially for the possibility of early identification of anomalous conditions using sensors and data; on the other hand, it poses potential risks, which requires further investigations. TM offers an alternative approach to information retrieval in livestock science, especially when dealing with a substantial volume of documents.

Milking robots have revolutionized the cow milking, reducing dependence on human labor and increasing milk yield per cow. However, addressing concerns about farmed animal welfare and overall sustainability is crucial. This paper presents a text-mining analysis of the scientific literature to explore the effects of robotic milking on cow health, welfare, and behavior. The analysis revealed a growing body of research studies on these subjects, highlighting the complex nature of the relationship between automated milking, welfare, health, and cow behavior. Robotic milking has the potential to enhance animal health and living conditions, but the associated risks require further investigation.

Air Quality, Management Practices and Calf Health in Italian Dairy Cattle Farms.

Among factors that can affect calf health, microbial quality of the pen air is poorly studied. In 25 Italian dairy farms, data concerning air quality in the calf pens, hygiene of pens and equipment, microclimatic conditions, calf health and management were collected during the winter season (January-March 2020 and December-March 2021). The average air Standard Plate Count (SPC) of 85 pens was 4.51 (SD = 0.52) log10 cfu/m3 whereas the average air ammonia concentration was 0.66 (SD = 0.53) ppm. Positive correlations were found between average Temperature Humidity Index (THI) in the pen and air SPC, night maximum THI and air SPC and between SPC and yeast, mould and ammonia concentration in the pen air. The concentrations of E. coli, Enterobacteriaceae and yeasts in the pen air were higher and calf cough increased as the renewal interval of bedding material became longer. High bedding dry matter and low THI were associated with low air SPC, good calf health scores and low mortality. Maintaining low bedding humidity and controlling microclimatic conditions can contribute to enhancing air microbiological quality in the pen and reduce calf diseases and mortality.

Association between Udder and Quarter Level Indicators and Milk Somatic Cell Count in Automatic Milking Systems.

Automatic Milking Systems (AMS) record a lot of information, at udder and quarter level, which can be useful for improving the early detection of altered udder health conditions. A total of 752,000 records from 1003 lactating cows milked with two types of AMS in four farms were processed with the aim of identifying new indicators, starting from the variables provided by the AMS, useful to predict the risk of high milk somatic cell count (SCC). Considering the temporal pattern, the quarter vs. udder percentage difference in milk electrical conductivity showed an increase in the fourteen days preceding an official milk control higher than 300,000 SCC/mL. Similarly, deviations over time in quarter vs. udder milk yield, average milk flow, and milking time emerged as potential indicators for high SCC. The Logistic Analysis showed that Milk Production Rate (kg/h) and the within-cow within-milking percentage variations of single quarter vs. udder milk electrical conductivity, milk yield, and average milk flow are all risk factors for high milk SCC. The result suggests that these variables, alone or in combination, and their progression over time could be used to improve the early prediction of risk situations for udder health in AMS milked herds.

Effect of Different Farming Practices on Lactic Acid Bacteria Content in Cow Milk.

The natural load of lactic acid bacteria (LAB) in milk is the basis of the production of raw milk cheeses, such as Grana Padano PDO. In the last decades, improvements in livestock hygiene management resulted in bulk cow milk with less than 20,000 colony forming units (CFU) of bacterial count, unable to ensure a sufficient supply of LAB, with a negative impact on cheese quality. This study investigated the relations between farm management practices and prevalence of different groups of bacteria in cow milk. Sixty-two intensive dairy farms located in Lombardy (Italy) where involved, most of them destined as milk for the production of Grana Padano. Season had no significant effect on the content of most of the bacterial groups, except for coliforms. A strong relation among standard plate count (SPC) and other bacterial groups was evidenced. Cluster analysis showed that the most productive farms applied a complete milking routine and produced milk with the lowest value of SPC, the lowest count of the other bacteria, including LAB, but the highest LAB/SPC. The study suggests that complexity of farming practices can affect the microbial population of milk.

Relating Lying Behavior With Climate, Body Condition Score, and Milk Production in Dairy Cows.

Attention on animal behavior and welfare has been increasing. Scientific knowledge about the effect of behavior and welfare on animals' production augmented and made clear the need of improving their living conditions. Among the variables to monitor in dairy cattle farming, lying time represents a signal for health and welfare status as well as for milk production. The aim of this study is to identify the relationship among the lying behavior of dairy cows and milk production, body condition score (BCS), weather variables, and the temperature-humidity index (THI) in the barn from a dairy farm located in Northern Italy. One-year data were collected on this farm with sensors that allowed monitoring of the environmental conditions in the barn and the activity of primiparous lactating cows. Principal components analysis (PCA), factor analysis (FA), generalized linear model select (GLMSelect), and logistic analysis (LA) were carried out to get the relationships among variables. Among the main results, it emerges that the effect of weather parameters is quite restrained, except for THI > 70, which negatively affects the lying time. In addition, the most productive cows are found to lie down more than the less productive ones, and the parameters of milk production, lying time, and BCS are found to be linked by a similar trend.

Rearing of Hermetia Illucens on Different Organic By-Products: Influence on Growth, Waste Reduction, and Environmental Impact.

The aim of the study was to evaluate the use of three by-products as growing substrates for Hermetia illucens (Black Soldier Fly (BSF)) larvae: okara, maize distiller, brewer's grains, and a control hen diet. The study focused on larval growth and bioconversion performance, production of methane by larvae and environmental burden of larvae production, using Life Cycle Assessment (LCA) on a lab scale. Chemical composition of substrates differed: okara had the highest crude protein and ether extract contents, while brewer's grains showed the highest fiber content. Larvae fed on a hen diet and maize distiller exhibited the highest final weights (2.29 and 1.97 g, respectively). Larvae grown on okara showed the highest indexes for waste reduction and efficiency of conversion of the ingested feed. The BSF larvae did not produce any detectable traces of CH4. LCA evaluation showed that larvae production on a hen diet resulted in the most impact for most of environmental categories, for the inclusion of soybean meal in the diet (for climate change, 5.79 kg CO2 eq/kg dry larvae). Feed production activities resulted in the main contributions to environmental impact. In order to compare the larvae production obtained on all substrates, an environmental impact was attributed to okara and brewer's grain through a substitution method, and, by this approach, the best sustainable product resulted from the larvae grown on the maize distiller.

Milk production Life Cycle Assessment: A comparison between estimated and measured emission inventory for manure handling.

Measuring emissions from manure management operations (from the barns to the land) is a challenging task, subject to different uncertainties related to the spatial-temporal variability in the process leading to gaseous release. At the same time, emissions inventory is a prerequisite of Life Cycle Assessment (LCA) studies. Manure management emissions are usually estimated using equations developed by Intergovernmental Panel on Climate Change (IPCC, in the case of greenhouse gases emissions) and European Environmental Agency (EEA) for Nitrogen-related emissions. In the present study, the environmental impacts associated to three Italian dairy farms were calculated through a comparative LCA using two different approaches for complying the emission inventory. In the "estimated" approach (E) the commonly adopted IPCC and EEA equations were used, while in the "measured" approach (M) emissions actually measured were taken as input data to quantify the emissions associated to manure management. The results showed that the IPCC equation underestimates the manure management emissions, leading to a 10-42% lower global warming potential comparing E to M approach. On the other hand, ammonia related impact categories showed higher values if they were calculated using the estimated approach, underling that a safer level of estimation is maintained.

Efficient milking hygiene reduces bacterial spore contamination in milk.

Clostridia in the milk can lead to late blowing, a cheese defect. Clostridia are ubiquitous, deriving from both the farm environment and the feed ingested by the cows, and are transferred into the milk through faecal contamination. Our aim was to investigate the effect of different in-parlour practices on the content of anaerobic spore-forming bacteria in milk, and to monitor the variation in spore content in the feed and environment. The experiment, conducted in an experimental dairy during autumn, was repeated in exactly the same way for two consecutive years. The experimental design applied three different milking routines in three consecutive 7-d periods: forestripping alone (F); forestripping and post-dipping (F+Post); pre-dipping, wiping, forestripping and post-dipping (Pre+F+Post). Teat skin swabs and samples of feed, faeces, bedding materials and milk were collected for microbiological analyses. The dietary forage of the lactating cows included maize silage, which, in both years, was found to have the highest level of clostridial spore contamination. Pre-dipping with a detergent/emollient solution, and drying with a disposable paper towel, proved much more efficient in reducing spore contamination than forestripping alone, both on the teats (1·30 vs. 2·20 log10 MPN/swab; P < 0·001) and in the milk (1·82 vs. 2·47 log10 MPN/L, P < 0·02), while post-dipping had little influence on spore count. The standard plate count in milk was significantly lower with Pre+F+Post treatment than with F (3·80 vs. 4·51 log10 CFU/mL, P < 0·01). The teat preparation procedure did not influence the lactic acid bacterial levels in the milk, which is very positive in that decreased lactic acid bacterial content can lessen raw milk cheese quality.

Anaerobic digestion and milking frequency as mitigation strategies of the environmental burden in the milk production system.

The aim of the study was to assess, through a cradle to farm gate Life Cycle Assessment, different mitigation strategies of the potential environmental impacts of milk production at farm level. The environmental performances of a conventional intensive dairy farm in Northern Italy (baseline scenario) were compared with the results obtained: from the introduction of the third daily milking and from the adoption of anaerobic digestion (AD) of animal slurry in a consortium AD plant. The AD plant, fed only with animal slurries coming also from nearby farms. Key parameters concerning on-farm activities (forage production, energy consumptions, agricultural machines maintenance, manure and livestock management), off-farm activities (production of fertilizers, pesticides, bedding materials, purchased forages, purchased concentrate feed, replacement animals, agricultural machines manufacturing, electricity, fuel) and transportation were considered. The functional unit was 1kg fat and protein corrected milk (FPCM) leaving the farm gate. The selected environmental impact categories were: global warming potential, acidification, eutrophication, photochemical oxidation and non-renewable energy use. The production of 1kg of FPCM caused, in the baseline scenario, the following environmental impact potentials: global warming potential 1.12kg CO2 eq; acidification 15.5g SO2 eq; eutrophication 5.62g PO4(3-) eq; photochemical oxidation 0.87g C2H4 eq/kg FPCM; energy use 4.66MJeq. The increase of milking frequency improved environmental performances for all impact categories in comparison with the baseline scenario; in particular acidification and eutrophication potentials showed the largest reductions (-11 and -12%, respectively). In anaerobic digestion scenario, compared to the baseline one, most of the impact potentials were strongly reduced. In particular the most important advantages were in terms of acidification (-29%), global warming (-22%) and eutrophication potential (-18%). The AD of cow slurry is confirmed as an effective strategy to mitigate the environmental impact of milk production at farm level.

Management practices and forage quality affecting the contamination of milk with anaerobic spore-forming bacteria.

BACKGROUND: Anaerobic spore-forming bacteria (ASFB) in milk derive from the farm environment, and the use of silages and management practices are the main responsible of milk ASFB contamination. The aim of this study was to evaluate the relationships between feeding, milking routine and cow hygiene and milk and Grana Padano cheese (produced with and without lysozyme) ASFB contamination. RESULTS: The study involved 23 dairy farms. ASFB in corn silage were on average 2.34 ± 0.87 log10 MPN g(-1). For grass, Italian ryegrass and alfalfa, ASFB (log10 MPN g(-1)) were numerically higher for silages (3.22) than hays (2.85). The use of corn silages of high quality (high lactic and acetic acids concentrations) decreased the milk ASFB contamination, whilst the use of herbage silages did not affect it. The presence (>40%) of cows with dirty udders increased the ASFB contamination of milk, while forestripping had a positive effect (-9% ASFB). Ripened Grana Padano had an ASFB count below the analytical limit; Clostridium tyrobutyricum DNA was found only in wheels produced without lysozyme, which also showed late blowing. CONCLUSION: The factors increasing milk spore contamination were corn silage quality, cow udder hygiene and inadequate milking routine. Late blowing was present only in cheeses without lysozyme.

Effect of farming strategies on environmental impact of intensive dairy farms in Italy.

Agriculture and animal husbandry are important contributors to global emissions of greenhouse (GHG) and acidifying gases. Moreover, they contribute to water pollution and to consumption of non-renewable natural resources such as land and energy. The Life Cycle Assessment (LCA) methodology allows evaluation of the environmental impact of a process from the production of inputs to the final product and to assess simultaneously several environmental impact categories among which GHG emissions, acidification, eutrophication, land use and energy use. The main purpose of this study was to evaluate, using the LCA methodology, the environmental impact of milk production in a sample of 41 intensive Italian dairy farms and to identify, among different farming strategies, those associated with the best environmental performances. The functional unit was 1 kg Fat and Protein Corrected Milk (FPCM). Farms showed characteristics of high production intensity: FPCM, expressed as tonnes per hectare, was 30·8±15·1. Total GHG emission per kg FPCM at farm gate was 1·30±0·19 kg CO2 eq. The main contributors to climate change potential were emissions from barns and manure storage (50·1%) and emissions for production and transportation of purchased feeds (21·2%). Average emission of gases causing acidification to produce 1 kg FPCM was 19·7±3·6 g of SO2 eq. Eutrophication potential was 9·01±1·78 ${\rm PO}_{\rm 4}^{{\rm 3} -} {\rm eq}.$ per kg FPCM on average. Farms from this study needed on average 5·97±1·32 MJ per kg FPCM from non-renewable energy sources. Energy consumption was mainly due to off-farm activities (58%) associated with purchased factors. Land use was 1·51±0·25 m2 per kg FPCM. The farming strategy based on high conversion efficiency at animal level was identified as the most effective to mitigate the environmental impact per kg milk at farm gate, especially in terms of GHG production and non-renewable energy use per kg FPCM.

Effects of season, milking routine and cow cleanliness on bacterial and somatic cell counts of bulk tank milk.

The aim of the study was to investigate the effects of season, cow cleanliness and milking routine on bacterial and somatic cell counts of bulk tank milk. A total of 22 dairy farms in Lombardy (Italy) were visited three times in a year in different seasons. During each visit, samples of bulk tank milk were taken for bacterial and somatic cell counts; swabs from the teat surface of a group of cows were collected after teat cleaning and before milking. Cow cleanliness was assessed by scoring udder, flanks and legs of all milking cows using a 4-point scale system. Season affected cow cleanliness with a significantly higher percentage of non-clean (NC) cows during Cold compared with Mild season. Standard plate count (SPC), laboratory pasteurization count (LPC), coliform count (CC) and somatic cell count, expressed as linear score (LS), in milk significantly increased in Hot compared with Cold season. Coagulase-positive staphylococci on teat swabs showed higher counts in Cold season in comparison with the other ones. The effect of cow cleanliness was significant for SPC, psychrotrophic bacterial count (PBC), CC and Escherichia coli in bulk tank milk. Somatic cell count showed a relationship with udder hygiene score. Milking operation routine strongly affected bacterial counts and LS of bulk tank milk: farms that accomplished a comprehensive milking scheme including two or more operations among forestripping, pre-dipping and post-dipping had lower teat contamination and lower milk SPC, PBC, LPC, CC and LS than farms that did not carry out any operation.

Effect of cleaning procedure and hygienic condition of milking equipment on bacterial count of bulk tank milk.

The aim of the study was to describe the characteristics of cleaning procedures for milking equipment applied in intensive dairy farms in Lombardy (Italy) and to study their relationships with bacterial count of bulk milk and hygienic condition of milking machine components. A group of 22 dairy farms was visited twice (winter and summer) in order to collect bulk tank milk and post-rinse water samples and swabs from liners and milk receiver. Samples were analysed to determine: standard plate count (SPC), laboratory pasteurization count (LPC), psychrotrophic bacteria count (PBC), coliform count (CC) and Escherichia coli. Cleaning procedures were monitored using electronic milk flow meters with specific software for the measurement of the duration of each cleaning phase, circulating solution temperature and electrical conductivity, turbulence and water filling percentage of pipelines. The results showed that farms classified as high and low milk total bacteria count significantly differed both in terms of liners and receiver bacterial contamination and in terms of water temperature reached during the detergent phase of cleaning milking equipment. Significant positive correlations were found among total bacteria count in milk and bacterial contamination of the liners. Maximum water temperature reached during the cleaning cycle of milking equipment was very low (34.4±8.9°C on average); most of the observations (88.6%) corresponded to water temperatures <45°C. Cleaning temperature was related to psychrotrophic bacteria count of milk and post-rinse water and coliform count in liners. Routine check and regulation of water temperature during the washing phase of the milking machine can be a simple and effective way to control one of the main risk factors for bacteriological quality of bulk tank milk.

Milk emission and udder health status in primiparous dairy cows during lactation.

To investigate the relationships between milk flow traits and udder health status in primiparous cows, 74 primiparous Holstein cows were randomly selected in 5 herds and monitored monthly throughout the whole lactation. A total of 2902 quarter milk samples were collected for bacteriological analyses and the determination of lysozyme, N-acetyl-beta-glucosaminidase (NAGase) and somatic cell count (SCC). Milk flow curves of the whole udder of each cow were registered with continuous electronic milk flow meters. Teat conditions and teat thickness changes during milking were assessed monthly. Quarters, udders and cows were classified as healthy, latent, inflamed and subclinical depending on SCC and the results of bacteriological analyses. Lysozyme in milk, teat apex score and teat thickness change did not vary with udder health status while NAGase in milk significantly increased as udder health status worsened (P<0.001). Milk production (P<0.001) and time of plateau phase (P<0.05) were significantly lower in subclinical cows in comparison with the others. Animals with a high frequency of bimodal curves in the first 100 days in milk showed the worst udder health status during the whole lactation (P<0.01). Moreover, cows classified as subclinical in the first 3 months of lactation had higher peak milk flow than healthy cows (3.81 v. 3.48 kg/min; P<0.05) and shorter duration of plateau phase, expressed both as minutes and as percentage of time of milk flow (pTPL; P<0.001). Multivariate logistic analysis showed udder health status to be associated with duration of plateau phase, time of milk flow, bimodality and duration of overmilking phase. With short time of plateau phase (pTPL <25%), short time of milk flow (<5 min), presence of bimodality and long overmilking phase (>0.8 min) there was an increased risk of poor udder health status. These milk flow traits can be predictive indicators of udder health status; time of plateau phase, expressed as percentage of time of milk flow, can also be a useful parameter for animal selection.