Revolutionizing India’s Dairy Industry: The Role of Artificial Intelligence in Sustainable and Scalable Milk Production

Since most dairy production in developing countries comes from small farms, there is scope to reduce their contribution to greenhouse gas (GHG) emissions. In the highlands of Mexico, the limitations in these systems are high feeding costs. This paper assessed the production, economics and estimated methane emissions from traditional feeding strategies (TFS) in 22 small-scale dairy farms compared to optimised feeding strategies (OFS) evaluated through on-farm research in eight participating farms in the dry (DS) and in the rainy (RS) seasons. Results were analysed with a completely randomized design. There were no differences (P>0.05) in milk fat, body condition score (BCS) or live weight between TFS and OFS, but there was higher (P<0.05) milk yield (17.99 vs 14.01 kg/cow/d), energy corrected milk (ECM) (16.77 vs 12.93 kg/cow/d) and milk protein (32.1 vs 30.9 g/kg milk) in OFS than TFS. Profit margin/cow/day was higher (P<0.05) (US$4.42 vs US$2.74) with a lower (P<0.05) feeding cost (US$0.18 vs US$0.22/kg) in OFS than TFS. Environmentally, the calculated enteric CH4 emission intensities were lower (P<0.05) in OFS (19.8 g CH4/kg milk) than TFS (25.3 g CH4/kg milk). Optimized feeding strategies in small-scale dairy farms increase milk yields, reduce feeding costs, increase incomes, and reduce enteric CH4 emission/kg of milk.

According to the agricultural Census data, dairy farms with less than 20 cows (small-scale dairy farms) have the biggest share of dairy farms structure in Lithuania, Latvia, Estonia and Poland. It leads to the importance of entrepreneurship ability evaluation in small-scale farms among these countries. However, there are no researches about comparison of entrepreneurship ability of small-scale farms among mentioned countries. The article investigates a comparison of the farmers’ entrepreneurship ability in small-scale dairy farms in mentioned countries by using distribution terms. The aim of the article is to perform calculations of small-scale dairy farms’ entrepreneurship ability for each country, give comparison analysis of the data among countries and estimate fitted distributions of entrepreneurship ability for further modelling purposes. The entrepreneurship ability and fitted distributions are evaluated by using optimization methods. The complex comparison method is also provided to show the general situation of the dairy farms in the selected countries. The results of the investigation show that Poland takes relatively the best position in the dairy farms’ economy. Latvia and Estonia take up relatively weaker positions. The calculation of the entrepreneurship indicators for each country shows that Estonian farmers have the highest entrepreneurship ability level. Two third of Estonian small-scale dairy farms’ correspond the entrepreneurship of 0.8 and a higher level. Latvian, Lithuanian and Polish dairy farms’ owners have similar average entrepreneurship ability (0.6–0.7) with different standard deviations. The best fitted distributions for all countries are normal and truncated normal distributions.

Cow hair allergen concentrations in dairy farms with automatic and conventional milking systems: From stable to bedroom.

During the last several decades, new milking management systems have been introduced, of which development of automatic milking (AM) systems is a significant step forward. In Europe, AM has become an established management system and has shown to be much more than milking management. Factors such as milking, milk quality, feeding, cow traffic, grazing, and animal behavior are essential elements of AM. This system offers possibilities for more frequent milking and can be adapted to lactational stage. Increased milk yield with AM has been observed, but lack of increased production has also been reported from the field, probably due to less attention paid to the total management system. The AM system provides consistent milking routines, with those for teat stimulation and feeding during milking giving an adequate oxytocin release and milk ejection. Initially, reduced milk quality, such as increased FFA, total bacteria count, and somatic cell count (SCC), was observed. Increased FFA could be due to increased milking frequency or handling of the milk, although this has not yet been determined. The elevated total bacteria count was probably due to mismanagement because later studies indicated that teat cleaning in AM is sufficient to reduce spores and dirt on the teats. Significant positive effects on udder health and teat treatment were observed in some studies, possibly as an effect of quarter milking, a procedure whereby an individual teat cup is detached when milk flow is below the preset level for detachment. Well-functioning cow traffic is a prerequisite for successful AM system performance to obtain an optimal number of visits to the feeding area and the milking parlor for all cows. Technical stoppages in the AM system (i.e., the milking unit) increased milk SCC, and the variation and length of the milking interval seem to contribute to elevated SCC. Grazing is a common management routine in many countries. Different ways to motivate the cows to visit the milking parlor, such as shorter distance between barn and pasture, supplement feeding, access to water, and use of acoustic signals, have been tested. It was concluded that use of AM and grazing systems together is possible as long as the distance from the milking parlor to pasture is short. With proper management routines, it is possible to achieve a production level and animal well-being in AM systems that are at least as good as in conventional milking systems.

Subject area Entrepreneurship, Small Business, Small-scale Dairy Farmers Study level/applicability This case is appropriate for undergraduate final year/senior as well as graduate-level programme students. Case overview This case explores the life of Saravanan, a small-scale dairy farmer in Malaysia. He inherited the business from his father. Small-scale farmers in Malaysia own farms with 30 (or fewer) milking cows. Over the years, milk consumption had been on the rise, but production was less than promising. Besides low-quality milk, Saravanan often experienced issues of low milk yield. Selling fresh milk as his only source of income and the milk collection centre as his sole marketing channel, Saravanan was caught in a financially tight situation when product diversification and marketing initiatives were limited. Saravanan’s problems began with rejected fresh milk, which landed him with zero income for the day. This issue was detected when the authorities identified a few contaminated batches of milk during a site visit. The problem compounded when Saravanan had to settle three months’ debt with the feed supplier on the same day. Saravanan’s predicament echoed the plight faced by small-scale farmers in Malaysia. After managing the farm for more than 30 years, Saravanan had plans to pass it to his son, Mugunthan. However, doubts about the sustainability of the business remained. Would Mugunthan suffer the same dire fate? Would he be able to find a way out? Based on the problem-solving framework, the case attempts to identify and assess the problems faced by small-scale dairy farmers in Malaysia, and at the same time, to suggest solutions that will ensure the sustainability of their business. Expected learning outcomes After attempting the case, students should learn to empathise with the hardship small-scale dairy farmers endure in the pursuit of their businesses, analyse issues and determine the root causes of the problems faced by small-scale dairy farmers in Malaysia based on the problem-solving framework, generate and justify sustainable solutions to solve the problems faced by these dairy farmers and present the case, discuss and work in teams, and critically offer sustainable solutions based on framework and theories. Supplementary materials Teaching notes are available for educators only. Subject code CSS 3: Entrepreneurship.

The overall goal of this thesis therefore was to explore the potential use and benefit of using frequently measured data to optimize on-farm decision making in udder health management in herds using an automatic milking system (AMS). In chapter 2, the risk factors for bovine mastitis in Dutch AMS herds were ... read more described. The results indicated that mastitis control measurements as advised in CMS herds generally are also applicable in AMS herds, while specifically in larger herds, extra attention should be given to hygiene of cows and of the AMS. In chapter 3, we compared the results of an online automated California Mastitis Test sensor (O-CMT) to estimate the SCC, with the SCC as measured in a milk quality laboratory (L-SCC). The overall concordance correlation coefficient between O-CMT and L-SCC was 0.53, with substantial variation between farms. The optimal time window for aggregating multiple O-CMT measurements was found to be 24h. We also found that the agreement between O-CMT and L-SCC was positively associated with herd SCC. In chapter 4, we described the SCC pattern based on O-CMT in 1,000 cows from 55 dairy herds using AMS in 6 different countries. We identified the rfSCC pattern in 4.7% (95% CI: 3.5%-6.2%) of these episodes. The rfSCC episodes had a median SCC of 701 (2.5%-97.5% quantile: 539-1,162) × 1,000 cells/mL, a median amplitude of 552 (2.5%-97.5% quantile: 409-886) × 1,000 cells/mL and a median cycle length of 4.1 (2.5%-97.5% quantile: 3.7-4.9) days. No clear association between pathogen species and the rfSCC pattern was found. In chapter 5, the transmission rates, duration of intramammary infections (IMI) and the basic reproduction number of Staphylococcus aureus and Streptococcus agalactiae in a Dutch AMS herd were estimated and compared with those of CMS farms. The transmission rate for Staph. aureus was estimated to be within the range of 0.002 (95% CI: 0-0.005) quarter-day-1 to 0.019 (95% CI: 0.010-0.032) quarter-day-1, and for Strep. agalactiae of 0.007 (95% CI: 0.005-0.010) quarter-day-1 to 0.019 (95% CI: 0.011-0.032) quarter-day-1. The median duration of chronic IMI was estimated at 95 (95% CI: 72-125) days for Staph. aureus and at 86 (95% CI: 67-111) days for Strep. agalactiae, and the R0 between 0.16 (95% CI: 0.05-0.27) and 0.34 (95% CI: 0.20-0.48) for Staph. aureus, and between 0.64 (95% CI: 0.41-0.87) and 0.68 (95% CI: 0.48-0.88) for Strep. agalactiae. In chapter 6, we compared the antimicrobial usage (AMU) and the distribution of bovine mastitis causing pathogens between AMS and CMS farms. The total antimicrobial usage and antimicrobial usage for dry cow therapy were comparable between AMS and CMS farms, whereas antimicrobial usage for intramammary infection tended to be lower and antimicrobial usage for injection was higher on AMS farms than on CMS farms. These results suggest AMU is comparable between AMS and CMS farms, but AMS farms tend to use more injectables and less intramammary treatments during lactation. Farmers’ attitudes toward udder health and toward mastitis treatment were associated with AMU in both AMS and CMS herds. Based on the findings in this thesis, we conclude that the frequently measured data in AMS herds holds great potential to support data-driven mastitis management decision making. This can be done for instance by monitoring individual cow udder health, identifying herd specific risk factors automatically, capturing patterns of IMI dynamics and quantifying the transmission process of infectious mastitis pathogens. Concerns that now limit the implementation of sensor technologies must be addressed. Further research to integrate the data from different sources, and algorithms to turn the data into interpretable information that can be used by the farmer and his advisor are needed. show less

Sustainability evaluation of automatic and conventional milking systems on organic dairy farms in Denmark

Afghanistan is an agricultural country, where more than 80% of the population depends on agriculture for their livelihoods. The livestock sector contributes perhaps half of the licit agriculture’s contribution to the national GDP. Small-scale dairy farming is an important component of Afghanistan’s rural economy. Milk and dairy products are crucial for the daily food security and income generation of most Afghan households. Rural women play a significant role in agriculture production, but their contribution remains un-recognized by researchers and policymakers. This study intends to examine the role and extent of the participation of rural women in small-scale dairy farming. There are no data available for an objective understanding of the role played by women in the rural economy of Afghanistan. The data was obtained from a sample of 180 rural women using a random sampling technique through a dairy farm survey in the Mousahi district of Kabul, Afghanistan during August and September 2021. Descriptive statistical tools like frequency, average, and percentage were used for the analysis. The study concluded that rural women’s contribution is one of the most significant elements of the operation of small-scale dairy farming, and most dairy farming work, from fodder collection to feeding, watering, animal management, and health care, is conducted by women.

This paper highlights the factors likely to influence the economic efficiency of small-scale dairy farms in Mukurweini, Nyeri County, Kenya. A total of 91 small-scale dairy farms previously involved in a nutritional training in 2013 were administered with semi-structured questionnaires. Data collected were entered into SPSS and FRONTIER 4.1 was used to compute the technical, allocative and economic efficiency scores for each farm. The scores were then regressed against a set of variables using the Tobit model in STATA to determine the factors associated with the scores. The average age of the household members involved in dairy farming, household size, labour, cost of concentrates and size of land owned had a negative significant influence on economic efficiency. It was concluded that lowering costs, proper utilization of hired labour and intensive use of the available land for dairy farming would lead to an increase in economic efficiency. The study recommends subsidized prices for concentrates, intensive dairy farming, minimization of hired labour and organization of dairy training and workshops in order to increase the efficiency of milk production in small-scale farms in the study area and other parts of Kenya with similar agro-ecological and cultural conditions.

The objective of this study was to evaluate the adaptation of mid-lactating Holstein cows regarding their introduction at the automatic milking system (AMS) and its effect on behaviour and milk performance. From a herd of 400 milking cows, a group of twenty-eight mid-lactating Holstein cows were monitored in the transition from the conventional milking system (twice daily) to the free-traffic automatic milking system. After 37 days from the full transition to the AMS, cows were retrospectively divided into two groups according to the average number of milking visits during the first week of AMS: 1) milking visits &lt; 2 (MV-LOW) and 2) milking visits &lt; 2 (MV-HIGH). Number of milking visits, milk yield, milk quality and rumination and eating time were recorded. In the first week, MV-HIGH cows had an average of milking visits higher compared to the MV-LOW cows (2.44 vs. 1.67 ± 0.06 n°/d, respectively). Starting from the similar milk production in the pre-AMS period, milk yield after the introduction of AMS (from 0 to 37 days) was higher in the MV-HIGH than in the MV-LOW cows (36.91 vs. 30.94 ± 2.11 kg/d, respectively), but with lower fat, protein and lactose percentage. The first week of AMS was characterized by a marked increase in milk yield in the MV-HIGH cows (+30.98 %) and a decrease in the MV-LOW cows (-11.60 %) compared to the pre-AMS. The time spent for eating was also greater in the MV-HIGH compared to the MV-LOW cows. Even though MV-LOW cows increased the milk production over the first week of AMS, these cows had always a lower increase in milk yield compared with the MV-HIGH cows until 37 days of AMS. These results suggest that the adaptability of the cows to the automatic milking system may also depend on the individual behaviour of cows and not only on the environment around them. Therefore, it is necessary to apply new livestock management strategies, when AMS (as a free-traffic system) is going to displace the milking parlour in order to better fine-tune the adaptation of cows (especially for heifers) and also to select cows that respond best to the robotic milking system.

This study addresses a critical gap in understanding Artificial Intelligence (AI)'s role in education by empirically investigating and comparing the distinct perceptions of teachers and students regarding AI's role in a comprehensive range of social development aspects in both online and physical classroom settings. In particular, we evaluated how teachers utilize AI in their teaching methods, namely, Communicative Language Teaching (CLT), the Direct Method (DL), Task-Based Language Teaching (TBLT), Content and Language Integrated Learning (CLIL), and Community Language Learning (CLL), and students in their learning methods, namely, Communicative Learning (CL), Immersive Learning (IL), Task-Based Collaborative Learning (TBCL), Content Integrated Learning (CIL), and Community-Based Reflective Learning (CBRL), to configure their social development. We interviewed 20 teachers (10 from online and 10 from physical classes) and 40 students (20 from online and 20 from physical classes) and evaluated their perceptions regarding AI usage in teaching and learning methods towards social development. The results of our study are convincing enough to suggest that both teachers and students perceive AI usage helpful in teaching models; however, variation in their perception is observed. Notably, the divergence in the perception of teachers and students with regard to AI's role is a key observation of this study. For instance, the teachers perceived AI as a highly effective tool in fostering community building during online sessions; in contrast, the students viewed its role as being moderately effective. Likewise, the teachers perceived AI's role as a critical tool in traditional classrooms rather than in virtual ones, whereas the students associated AI with online learning-in terms of digital tools, learning opportunities, and critical discussion-by rating its impact on social confidence and verbal-nonverbal communications significantly more strongly in physical settings. On the contrary, the teachers emphasized AI's relevance to their self-confidence, emotional intelligence, and community engagement in online teaching platforms; yet, the ratings dropped to moderate in physical contexts. The students' perceptions in this regard matched those of the teachers, as they also emphasized the importance of social confidence and overall well-being in physical classrooms, where the teachers' assessment was comparatively low. These patterns provide analytical insights that are decisively valuable for designing AI-integrated pedagogical models that support social development within the educational environments.

Increasing milk yield per cow is considered a promising climate change mitigation strategy for small-scale dairy farms in developing countries. As it can be difficult to increase cow productivity, mitigation options beyond this production strategy need to be identified. The aim of this study was to identify entry points for mitigation of GHG emissions in small-scale dairy farms in Lembang Sub-district, West Java, Indonesia. Data on herd composition, productivity, feeding and manure management were collected in a survey of 300 randomly selected dairy farms. Characteristics of farms with the 25% lowest (<3291 kg milk/cow/y), medium 50% (3291-4975 kg milk/cow/y), and 25% highest milk yields (≥4976 kg milk/cow/y) were compared. Life cycle assessment was then performed to estimate the cradle-to-farm gate GHG emission intensity (EI) of farms. The relationship between EI and milk yield per cow for all farms was modeled and farms with an EI below and above their predicted EI were compared (‘low’ and ‘high’ EI farms). Results showed that milk yield explained 57% of the variance in EI among farms. Farms with medium and high milk yields were more often specialized farms, fed more tofu waste and compound feed, and had higher feed costs than farms with low milk yields (P<0.05). Farms with high milk yields also applied less manure on farm land than farms with low milk yields (P<0.05). Low EI farms had fewer cows, and fed less rice straw, more cassava waste, and more compound concentrate feed (particularly the type of concentrates consisting largely of by-products from milling industries) than high EI farms (P<0.05). In addition, low EI farms discharged more manure, stored less solid manure, used less manure for anaerobic digestion followed by daily spreading, and applied less manure N on farmland than high EI farms (P<0.05). Some associations were affected by confounding factors. Farm management factors associated with milk yield and the residual variation in EI were considered potential entry points for GHG mitigation. Feeding less rice straw and discharging manure, however, were considered unsuitable mitigation strategies because of expected trade-offs with other environmental issues or negative impacts on food-feed competition.

Artificial intelligence (AI) is increasingly applied in clinical diagnostics, particularly in radiology, where it can assist with imaging triaging and anomaly detection. However, the integration of AI into medical education remains under researched. This study investigates the impact of an AI-focused panel discussion on medical students' perceptions, knowledge, attitudes and concerns about AI in radiology. A paired pre-post design questionnaire comprising of 13 five-point Likert scale questions was administered to 40 medical students to complete before and after an AI-focused educational panel session at the International Radiology Undergraduate Symposium in London, United Kingdom on 24th November 2024. The questionnaire assessed four domains: 'Understanding of AI,' 'Attitudes Toward AI in Radiology,' 'AI Education in Medical School,' and 'Concerns About AI in the Future.' The primary outcome was to assess the change in students' perceptions of AI's role in radiology. Differences between pre- and post-session responses were analysed using the Wilcoxon signed-rank test. The Hodges-Lehmann median difference, the effect size, r, and their corresponding 95% confidence intervals were calculated, and p-values were adjusted using the Holm-Bonferroni method. Of the 81 eligible attendees, 40 (49.4%) completed the questionnaire (39 pre-session, 40 post-session). Students demonstrated significant improvements in their understanding of AI's potential role in radiology (Z = 3.04, p = 0.002; Holm-Bonferroni = 0.029; median paired difference = 0.5, 95% CI 0.0-0.5; r = 0.49, 95% CI 0.25-0.68) and in their awareness of AI's broader clinical applications (Z = 3.65, p < 0.001; Holm-Bonferroni = 0.0035; median paired difference = 0.5, 95% CI 0.5-1.0; r = 0.60, 95% CI 0.38-0.75). Participants expressed a more positive view of AI in healthcare overall, although concerns about AI replacing radiologists and insufficient AI education persisted. Educational interventions have the potential to improve medical students' understanding and attitudes toward AI in radiology. Integrating structured AI education into undergraduate curricula may enhance AI literacy and better prepare future clinicians for an AI-enabled healthcare environment.

Conventional pipeline and parlor milking expose dairy farmers and workers to adverse health outcomes. In recent years, automatic milking systems (AMS) have gained much popularity in Finland, but the changes in working conditions when changing to AMS are not well known. The aim of this study was to investigate the occupational health and safety risks in using AMS, compared to conventional milking systems (CMS). An anonymous online survey was sent to each Finnish dairy farm with an AMS in 2014. Only those dairy farmers with prior work experience in CMS were included in the final analysis consisting of frequency distributions and descriptive statistics. We received 228 usable responses (131 male and 97 female; 25.2% response rate). The majority of the participants found that AMS had brought flexibility to the organization of farm work, and it had increased leisure time, quality of life, productivity of dairy work, and the attractiveness of dairy farming among the younger generation. In addition, AMS reduced the perceived physical strain on the musculoskeletal system as well as the risk of occupational injuries and diseases, compared to CMS. However, working in close proximity to the cattle, particularly training of heifers to use the AMS, was regarded as a high-risk work task. In addition, the daily cleaning of the AMS and manual handling of rejected milk were regarded as physically demanding. The majority of the participants stated that mental stress caused by the monotonous, repetitive, paced, and hurried work had declined after changing to AMS. However, many indicated increased mental stress because of the demanding management of the AMS. Nightly alarms caused by the AMS, lack of adequately skilled hired labor or farm relief workers, and the 24/7 standby for the AMS were issues that also caused mental stress. Based on this study, AMS may have significant potential in the prevention of adverse health outcomes in milking of dairy cows. In addition, AMS may improve the productivity of dairy work and sustainability of dairy production. However, certain characteristics of the AMS require further attention with regard to occupational health and safety risks.

The aim of the study was to investigate the effect of feeding frequency on milk production, dry matter intake (DMI) and cow behaviour on two dairy farms with conventional and automatic milking systems (AMS) in different environmental conditions. Cows on two farms were monitored. On the first farm, 96 primiparous cows were milked in a herringbone parlor while on the second a group of nearly 50 cows were milked in two AMS with a forced traffic. On each farm, treatments consisted of two different frequencies of total mixed ration (TMR) delivery (2 vs 3 on the conventional farm; 1 vs 2 on the AMS farm) replicated in two different periods of the year with THI of 72.6 and 60.7, respectively. The behaviour of the cows was monitored by continuous video recording. Statistical analysis was performed separately for the two farms. Increasing the frequency of TMR deliveries did not result in any variation in DMI but significantly improved milk yield on both farms. The increase in feeding frequency at the bunk in the AMS farm mitigated the negative effect of hot conditions on production with a 7.6% increase in milk yield. Feeding frequency did not influence cow behaviour on either farm. Hot conditions showed a depressive effect on DMI (nearly 8% on both farms) compared with thermoneutral conditions but caused a reduction in milk yield (an average 17%) only on the farm with multiparous high-producing cows milked automatically. In the hot period, cows on both farms showed a reduction in daily lying time and an increase in daily standing time.