Smart dairy farming: Automation, artificial intelligence and precision livestock technologies: Current advances, challenges and future perspectives

Introduction

Increasing herd sizes and declining labour availability have encouraged the adoption of Precision Livestock Farming (PLF) technologies to reduce repetitive tasks and improve herd monitoring (Hostiou et al., 2017) [15] , while growing expectations for environmentally, economically, and socially sustainable dairy production have accelerated the integration of sensors, automation, and decision-support technologies (Lovarelli et al., 2020) [25] . PLF integrates engineering, sensor technologies, animal science, and information systems to continuously monitor individual animals and support data-driven management decisions (Wathes et al., 2008; Norton et al., 2019) [31] , emphasizing real-time assessment of physiological, behavioural, health, production, and welfare parameters (Berckmans, 2017) [7] . Smart dairy farming extends PLF through the integration of automation, Internet of Things (IoT), artificial intelligence (AI), robotics, cloud computing, and advanced data analytics (Akbar et al., 2020; Yousfi and M'Sadak, 2025) [1,43] , facilitating continuous data acquisition, transmission, and analysis for evidence-based decision-making (Taneja et al., 2019; Akbar et al., 2020) [1,38] . Wearable sensors, RFID, accelerometers, rumination collars, rumen boluses, thermal imaging, and computer vision generate highfrequency data for precision management (Rutten et al., 2013; Lamanna et al., 2025; Han et al., 2022) [13,21,36] , enabling early detection of diseases, reproductive disorders, metabolic disturbances, and behavioural abnormalities (Rutten et al., 2013; Han et al., 2022) [13,36] . AI-driven machine learning and deep learning are increasingly investigated for health prediction, reproductive monitoring, lameness detection, and milk production forecasting (Slob et al., 2021; Kaur et al., 2023a) [18] , while automated milking, feeding, and sensor-actuator systems can reduce labour requirements and support precision management (Jacobs and Siegford, 2012; Kaur et al., 2023a) [16] . However, expanding sensor networks generate large, heterogeneous datasets requiring advanced integration and analytics (Bahlo et al., 2019; Cockburn, 2020) [4,11] . Although these systems can improve monitoring of health, welfare, productivity, and resource use (Cockburn, 2020) [11] , widespread adoption remains constrained by investment costs, interoperability, data integration, management, and ownership issues (Bahlo et al., 2019) [4] . Furthermore, machine-learning models require larger integrated datasets and further validation to improve reliability and generalizability across commercial production systems (Cockburn, 2020) [11] .

Automation and robotics in smart dairy farming

Automation has emerged as an important component of the digital transformation of dairy farming, replacing or assisting repetitive manual operations through automated, sensorbased, and increasingly data-driven systems (Jacobs and Siegford, 2012; Kaur et al., 2023b) [16,19] . Beyond conventional mechanization of individual farm tasks, modern automated systems increasingly integrate sensors, communication technologies, data-processing tools, and decision-support systems to monitor animals and farm processes and support management decisions based on continuously generated data (Kaur et al., 2023b) [19] . This transition has contributed to a shift from labour-intensive operations toward precision management, with opportunities to improve labour efficiency, production management, animal monitoring, and resource utilization (Jacobs and Siegford, 2012; Romano et al., 2023) [16] . Recent technological developments have extended automation across multiple dairy operations, including automatic milking and feeding, while sensor-based technologies increasingly support health, behavioural, and reproductive monitoring, contributing to the development of more integrated precision dairy farming systems (Mottram, 2016; Kaur et al., 2023b) [19,29] .

Automatic milking systems (AMS)

Automatic Milking Systems (AMS) are among the most important automation technologies adopted in modern dairy farming, allowing cows voluntary access to milking while generating individual-level data on milk production, milking frequency, and other parameters useful for herd management (Jacobs and Siegford, 2012; Løvendahl and Chagunda, 2011) [16, 26] . Beyond reducing milking-related labour, data routinely collected by AMS and associated sensor technologies can support the detection and management of health disorders through changes in milk production, milking behaviour, and animal activity (King et al., 2018; Tse et al., 2018). Although AMS can reduce labour requirements and provide greater flexibility in milking management, their economic performance depends on factors such as system utilization, herd size, milk production, investment costs, and farm management (Rotz et al., 2003; Bijl et al., 2007; Jacobs and Siegford, 2012) [8,16,34] .

1.2 Automated feeding systems Automated feeding technologies improve feeding precision, reduce labour requirements, and enable consistent ration delivery, thereby supporting feed efficiency and animal performance (Monteiro et al., 2021; Tangorra et al., 2024) [28,39] . Integration of automated feeding with sensors and datadriven technologies further enables precision nutrition through individualized feed allocation based on animal requirements and performance (Dell 'Unto et al., 2025)

Automated manure management

Autonomous manure-scraping robots improve barn hygiene, reduce labour demand, and minimize exposure to pathogens associated with hoof and udder diseases (Benni et al., 2021) [6] . Efficient manure management can further support nutrient recovery and renewable energy production through anaerobic digestion, contributing to more sustainable dairy production systems (Atandi and Rahman, 2012) [3] .

Automated environmental control

Sensor-based ventilation and cooling systems facilitate automated regulation of the barn microclimate, including temperature and humidity, helping to mitigate heat stress and its adverse effects on milk production and reproductive performance (Polsky and von Keyserlingk, 2017; Fournel et al., 2017) [32] . Such environmental control strategies are particularly important in hot climatic conditions, where heat stress represents a major constraint to dairy cattle productivity (Becker et al., 2020) [5] .

Advantages and limitations

Automation enhances labour efficiency, production consistency, disease surveillance, and precision management through continuous data acquisition (Jacobs and Siegford, 2012) [16] . However, high capital investment, maintenance costs, interoperability issues, and limited adoption by smallholder farmers remain major barriers to widespread implementation (Benni et al., 2021) [6] .

Artificial intelligence and machine learning in smart dairy farming

Artificial Intelligence (AI) and Machine Learning (ML) enable automated analysis of large, complex datasets generated by sensors and farm-management systems, supporting predictive decision-making and individual-animal precision management. By identifying complex relationships among behavioural, physiological, environmental, and production variables, AI-based approaches are increasingly applied to dairy cattle health monitoring, reproduction, feeding, and welfare assessment (Cockburn, 2020; Slob et al., 2021; Kaur et al., 2023a) [11,18] .

Machine learning algorithms in dairy farming

Supervised machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and gradient-boosting methods, are increasingly applied to multidimensional agricultural and dairy datasets for prediction and classification tasks (Liakos et al., 2018; Cockburn, 2020) [11,22] . In dairy farming, these approaches have been investigated for predicting milk production, animal health, and other management-related outcomes. RF models offer robust ensemble-based classification and regression, while SVMs are effective for high-dimensional classification problems and ANNs are particularly suited to modelling complex nonlinear relationships. However, model performance is applicationand dataset-dependent, and no single algorithm is universally superior (Cockburn, 2020) [11] [2] .

AI-based health monitoring

Artificial Intelligence (AI) and machine-learning approaches enable integration of sensor and farm-management data for earlier identification of health abnormalities in dairy cattle. Predictive models using milk, behavioural, activity, and other sensor-derived data have shown potential for detecting conditions such as mastitis and lameness, supporting earlier intervention and improved health management (Post et al., 2020; Shahinfar et al., 2021) [33,37] . Emerging ML-based approaches also show promise for identifying physiological responses to heat stress by integrating environmental, behavioural, and physiological indicators (Džermeikaitė et al., 2025). [27] . Similarly, sensor-based and machine-learning systems analyse activity and behavioural changes to support automated estrus detection and reproductive monitoring, reducing reliance on visual observation (Liu et al., 2023) [24] .

Emerging technologies

Digital twins are emerging as virtual representations of animals and farming systems that integrate real-time data with computational models to support monitoring, simulation, and predictive management (Neethirajan and Kemp, 2021) [30] . Emerging explainable AI (XAI), multimodal learning, and large language models (LLMs) may further enhance the interpretability, integration, and accessibility of AI-driven livestock management systems (Menezes et al., 2024). [4,11] .

Precision livestock farming (PLF) technologies and biosensors

Precision Livestock Farming (PLF) integrates sensors, automation, and data analytics for continuous, individualanimal monitoring and data-driven management. By assessing health, production, reproduction, behaviour, and welfare in real time, PLF enables earlier identification of deviations and supports timely management interventions (Berckmans, 2017; Norton et al., 2019) [7,31] . Unlike conventional herd-level management, PLF utilizes continuously generated animal and environmental data to improve decision-making, productivity, and precision management (Rutten et al., 2013; Kaur et al., 2023b) [36] .

Wearable sensor technologies

Wearable sensors, including neck collars, ear tags, pedometers, accelerometers, and rumination monitors, enable continuous monitoring of activity, feeding, rumination, and locomotor behaviour in dairy cattle, supporting precision health and reproductive management (Rutten et al., 2013; Mottram, 2016) [29,36] . Accelerometer-based systems can identify behavioural and activity changes associated with estrus, lameness, and health disturbances, facilitating earlier detection and reducing reliance on manual observation (Mottram, 2016; King et al., 2018) [29] .

Rumination and feeding monitoring

Rumination and feeding behaviours are valuable indicators of dairy cattle health and welfare. Automated sensors enable continuous monitoring of rumination, feeding duration, and feeding frequency, facilitating early identification of behavioural deviations associated with health disturbances (Borchers et al., 2016; Lamanna et al., 2025) [9,21] . Sensorbased monitoring of feeding behaviour and feed intake can further support precision feeding and individualized nutritional management, with potential benefits for feed efficiency and farm profitability (Kaur et al., 2023a) [18] .

Milk monitoring sensors

Automatic milking systems incorporate inline sensors that monitor parameters such as milk yield, flow rate, electrical conductivity, colour, and somatic cell count-related indicators, supporting automated surveillance of udder health and milk quality (Kamphuis et al., 2008; Rutten et al., 2013) [17] . Integration of milk sensor data with machine-learning algorithms can further improve mastitis prediction and facilitate earlier management interventions (Tian et al., 2024) [40] .

Identification and traceability technologies

Radio Frequency Identification (RFID) is widely used for automated individual-animal identification and provides a foundation for linking animal identity with production, health, feeding, reproductive, and movement records in precision livestock systems (Ruiz-Garcia and Lunadei, 2011; Caja et al., 2016) [10,35] . Integration of electronic identification with digital farm-management platforms can enhance livestock traceability and facilitate more efficient animal monitoring and record management throughout the production chain (Ruiz-Garcia and Lunadei, 2011) [35]

3.5Internet of things (IoT) in dairy farming

The Internet of Things (IoT) interconnects sensors, automated equipment, and digital management platforms through communication networks, enabling real-time data exchange and integrated monitoring in dairy farms (Akbar et al., 2020) [1] . IoT architectures incorporating cloud and fog computing facilitate remote monitoring of animal behaviour and health and support data-driven decision-making, improving the flexibility and efficiency of dairy management (Taneja et al., 2019) [38] .

Benefits and limitations of PLF technologies

Precision Livestock Farming (PLF) technologies enable continuous individual-animal monitoring, supporting improved health surveillance, reproductive management, labour efficiency, and welfare assessment (Rutten et al., 2013; Berckmans, 2017) [7] . However, wider adoption remains constrained by investment costs, technical complexity, data integration, and interoperability challenges (Bahlo et al., 2019; Kaur et al., 2023a) [4,18] . Future research should prioritize interoperable data standards, integration of heterogeneous data sources, and robust validation across commercial production environments to improve the reliability and scalability of PLF systems (Bahlo et al., 2019; Cockburn, 2020) [4,11] .

Challenges, research gaps and future perspectives 4.1 Technical challenges

The effectiveness of smart dairy farming depends on the accuracy, reliability, and completeness of sensor-generated data. Missing or erroneous data, sensor failures, and communication disruptions can compromise data quality and consequently reduce the reliability of automated monitoring and AI-based decision-support systems (Cockburn, 2020; Kaur et al., 2023b) [11,19] . Interoperability is another major challenge, as heterogeneous technologies and data formats often limit seamless data exchange and system integration. Development of standardized and interoperable data frameworks is therefore essential for effective integration of sensors, automated systems, and farm-management platforms (Bahlo et al., 2019) [4] .

Data management and cybersecurity

Smart dairy farming generates large volumes of heterogeneous animal, production, and environmental data, creating challenges related to data storage, processing, integration, and governance. Although cloud-based platforms facilitate data access and management, concerns regarding data privacy, ownership, security, and responsible data sharing remain important considerations in digital agriculture (Wiseman et al., 2019) [41] . Furthermore, limited interoperability and the lack of standardized data frameworks restrict seamless data exchange among digital technologies and management platforms (Bahlo et al., 2019) [4] .

Adoption by farmers

Adoption of precision dairy technologies remains uneven and is influenced by economic, technical, and farm-specific factors. High investment costs, uncertainty regarding economic returns, technological complexity, and farmers' skills and perceptions can constrain technology adoption (Drewry et al., 2019; Lima et al., 2020) [23] . These barriers may be particularly important for resource-constrained and smallholder production systems, where access to capital, digital infrastructure, and technical support is often limited.

Research gaps

Most AI models have been developed using datasets collected from a limited number of commercial farms, reducing their applicability across different breeds, management systems, and climatic regions. Greater emphasis should be placed on developing robust and externally validated algorithms capable of generalizing under diverse production environments (Liakos et al., 2018; Liu et al., 2023) [22] . Current research also focuses predominantly on disease detection and behavioural monitoring, whereas comparatively fewer studies have investigated long-term sustainability, economic performance, greenhouse gas mitigation, and integration of multiple technologies into unified management platforms (Liu et al., 2023) [24] .

Future perspectives

Future smart dairy systems are likely to increasingly integrate AI, IoT, robotics, advanced analytics, and digital twins to support predictive and individualized management, automation, and improved production efficiency (Neethirajan and Kemp, 2021; Hassoun et al., 2023) [14,30] . Emerging technologies may further enhance real-time data integration and intelligent decision support; however, their practical scalability, interoperability, and effectiveness under commercial dairy conditions require further validation.

Conclusion and future outlook

Smart dairy farming represents a shift from conventional herd management toward automated, data-driven, and individualanimal-focused production systems. The integration of precision livestock farming technologies, IoT, biosensors, robotics, automation, and artificial intelligence enables continuous monitoring and supports timely decisions related to animal health, reproduction, feeding, welfare, and production. Automated milking and feeding systems further reduce labour demands while generating high-frequency data for precision management. Advances in AI, machine learning, and computer vision are facilitating a transition from reactive toward predictive management through earlier identification of health and behavioural abnormalities. However, widespread implementation remains constrained by high investment costs, limited interoperability and data integration, concerns regarding data governance and security, and insufficient validation of AI models across diverse production environments. Future research should prioritize interoperable digital infrastructures, standardized data frameworks, robust model validation, explainable and multimodal AI, and affordable technologies adaptable to different farm scales. Emerging approaches such as digital twins may further strengthen predictive and individualized decision support, although their commercial applicability requires validation. Ultimately, the success of Dairy 4.0 will depend on developing reliable, economically viable, and farmer-oriented technologies that translate complex data into actionable decisions, supporting efficient, resilient, welfare-oriented, and environmentally sustainable dairy production.

References

1. Akbar MO, Khan S, Saad M, Ali A, Jamshaid M, Hussain A, et al. IoT for development of smart dairy farming. J Food Qual. 2020;2020:4242805. Doi:10.1155/2020/4242805.
2. Antognoli V, Presutti L, Bovo M, Torreggiani D, Tassinari P. Computer vision in dairy farm management: a literature review of current applications and future perspectives. Animals (Basel). 2025;15(17):2508. Doi:10.3390/ani15172508.
3. Atandi E, Rahman S. Prospect of anaerobic co-digestion of dairy manure: a review. Environ Technol. 2012;33(11):1221-1232. Doi:10.1080/09593330.2012.698654.
4. Bahlo C, Dahlhaus P, Thompson H, Trotter M. The role of interoperable data standards in precision livestock farming in extensive livestock systems: a review. Comput Electron Agric. 2019;156:459-466. Doi:10.1016/j.compag.2018.12.007.
5. Becker CA, Collier RJ, Stone AE. Invited review: physiological and behavioral effects of heat stress in dairy cows. J Dairy Sci. 2020;103(8):6751-6770. Doi:10.3168/jds.2019-17929.
6. Benni S, Tassinari P, Bonora F, Barbaresi A, Torreggiani D, Teye FK. Challenges and tendencies of automatic milking systems (AMS): a 20-years systematic review of literature and patents. Animals (Basel). 2021;11(2):356. Doi:10.3390/ani11020356.
7. Berckmans D. General introduction to precision livestock farming. Anim Front. 2017;7(1):6-11. Doi:10.2527/af.2017.0102.
8. Bijl R, Kooistra SR, Hogeveen H. The profitability of automatic milking on Dutch dairy farms. Dairy Sci. 2007;90(1):239-248. Doi:10.3168/jds.S00220302(07)72625-5.
9. Borchers MR, Chang YM, Tsai IC, Wadsworth BA, Bewley JM. A validation of technologies monitoring dairy cow feeding, ruminating, and lying behaviors. J Dairy Sci. 2016;99(9):7458-7466. Doi:10.3168/jds.201510843.
10. Caja G, Castro-Costa A, Knight CH. Engineering to support wellbeing of dairy animals. J Dairy Res. 2016;83(S1):136-147. Doi:10.1017/S0022029916000261.
11. Cockburn M. Review: application and prospective discussion of machine learning for the management of dairy farms. Animals (Basel). 2020;10(9):1690. Doi:10.3390/ani10091690.
12. Dell'Unto D, Selvaggi R, Pappalardo G, Cortignani R. Adoption of precision livestock farming devices in the dairy cattle sector: an assessment based on agroeconomic modelling. Sci Total Environ. 2025. Doi:10.1016/j.scitotenv.2025.180555.
13. Han CS, Kaur U, Bai H, Dos Reis BR, White RR, Nawrocki RA, et al. Invited review: sensor technologies for real-time monitoring of the rumen environment. J Dairy Sci. 2022;105(8):6379-6404.
14. Hassoun A, Garcia-Garcia G, Trollman H, Jagtap S, Parra-López C, Cropotova J, et al. Birth of Dairy 4.0: opportunities and challenges in adoption of fourth industrial revolution technologies in the production of milk and its derivatives. Curr Res Food Sci. 2023;7:100535. Doi:10.1016/j.crfs.2023.100535.
15. Hostiou N, Fagon J, Chauvat S, Turlot A, Kling-Eveillard F, Boivin X, et al. Impact of precision livestock farming on work and human-animal interactions on dairy farms: a review. Biotechnol Agron Soc Environ. 2017;21(4):268275. Doi:10.25518/1780-4507.13706.
16. Jacobs JA, Siegford JM. Invited review: The impact of automatic milking systems on dairy cow management, behavior, health, and welfare. J Dairy Sci. 2012;95(5):2227-2247. Doi:10.3168/jds.2011-4943.
17. Kamphuis C, Sherlock R, Jago J, Mein G, Hogeveen H. Automatic detection of clinical mastitis is improved by in-line monitoring of somatic cell count. J Dairy Sci. 2008;91(12):4560-4570. Doi:10.3168/jds.2008-1160.
18. Kaur U, Kaur B, Suri TM, Priya S, Singh A. Invited review: Integration of technologies and systems for precision animal agriculture-A case study on precision dairy farming. J Dairy Sci. 2023;106(8):5938-5962. Doi:10.3168/jds.2022-23004.
19. Kaur U, Malacco VM, Bai H, Price TP, Datta A, Xin L, Voyles RM. Invited review: Integration of technologies and systems for precision animal agriculture-A case study on precision dairy farming. J Anim Sci. 2023;101:skad206. Doi:10.1093/jas/skad206.
20. King MTM, LeBlanc SJ, Pajor EA, DeVries TJ. Cowlevel associations of lameness, behavior, and milk yield of cows milked in automated systems. J Dairy Sci. 2018;101(6):5326-5337. Doi:10.3168/jds.2017-13943.
21. Lamanna M, Bovo M, Cavallini D. Wearable collar technologies for dairy cows: A systematized review of the current applications and future innovations in precision livestock farming. Animals (Basel). 2025;15(3):458. Doi:10.3390/ani15030458.
22. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture: A review. Sensors (Basel). 2018;18(8):2674. Doi:10.3390/s18082674.
23. Lima E, Hopkins T, Gurney E, Shortall O, Lovatt F, Davies P, et al. Drivers for precision livestock technology adoption: A study of factors associated with adoption of electronic identification technology by commercial sheep farmers in England and Wales. PLoS One. 2020;15(1):e0220488. Doi:10.1371/journal.pone.0220488.
24. Liu N, Qi J, An X, Wang Y. A review on information technologies applicable to precision dairy farming: Focus on behavior, health monitoring, and the precise feeding of dairy cows. Agriculture. 2023;13(10):1858. Doi:10.3390/agriculture13101858.
25. Lovarelli D, Bacenetti J, Guarino M. A review on dairy cattle farming: Is precision livestock farming the compromise for an environmental, economic and social sustainable production? J Clean Prod. 2020;262:121409. Doi:10.1016/j.jclepro.2020.121409.
26. Løvendahl P, Chagunda MGG. Covariance among milking frequency, milk yield, and milk composition from automatically milked cows. J Dairy Sci. 2011;94(11):5381-5392. Doi:10.3168/jds.2010-3589.
27. Martin MJ, Dórea JRR, Borchers MR, Wallace RL, Bertics SJ, DeNise SK, et al. Comparison of methods to predict feed intake and residual feed intake using behavioral and metabolite data in addition to classical performance variables. J Dairy Sci. 2021;104(8):87658776. Doi:10.3168/jds.2020-20051.
28. Monteiro A, Santos S, Gonçalves P. Precision agriculture for crop and livestock farming-Brief review. Animals (Basel). 2021;11(8):2345. Doi:10.3390/ani11082345.
29. Mottram T. Animal Board invited review: Precision livestock farming for dairy cows with a focus on oestrus detection, mastitis and lameness detection. Animal. 2016;10(10):1575-1584. Doi:10.1017/S1751731115002518.
30. Neethirajan S, Kemp B. Digital twins in livestock farming. Animals (Basel). 2021;11(4):1008. Doi:10.3390/ani11041008.
31. Norton T, Chen C, Larsen MLV, Berckmans D. Review: Precision livestock farming: Building "digital representations" to bring the animals closer to the farmer. Animal. 2019;13(12):3009-3017.
32. Polsky L, von Keyserlingk MAG. Invited review: Effects of heat stress on dairy cattle welfare. J Dairy Sci. 2017;100(11):8645-8657. Doi:10.3168/jds.2017-12651.
33. Post C, Rietz C, Büscher W, Müller U. Using sensor data to detect lameness and mastitis treatment events in dairy cows: A comparison of classification models. Sensors (Basel). 2020;20(14):3863. Doi:10.3390/s20143863.
34. Rotz CA, Coiner CU, Soder KJ. Automatic milking systems, farm size, and milk production. J Dairy Sci. 2003;86(12):4167-4177. Doi:10.3168/jds.S00220302(03)74032-6.
35. Ruiz-Garcia L, Lunadei L. The role of RFID in agriculture: Applications, limitations and challenges. Comput Electron Agric. 2011;79(1):42-50. Doi:10.1016/j.compag.2011.08.010.
36. Rutten CJ, Velthuis AGJ, Steeneveld W, Hogeveen H. Invited review: Sensors to support health management on dairy farms. J Dairy Sci. 2013;96(4):1928-1952. Doi:10.3168/jds.2012-6107.
37. Shahinfar S, Khansefid M, Haile-Mariam M, Pryce JE. Machine learning approaches for the prediction of lameness in dairy cows. Animal. 2021;15(11):100391. Doi:10.1016/j.animal.2021.100391.
38. Taneja M, Jalodia N, Byabazaire J, Davy A, Olariu C. SmartHerd management: A microservices-based fog computing-assisted IoT platform towards data-driven smart dairy farming. Softw Pract Exp. 2019;49(7):10551078. Doi:10.1002/spe.2704.
39. Tangorra FM, Buoio E, Calcante A, Bassi A, Costa A. Internet of Things (IoT): Sensors application in dairy cattle farming. Animals (Basel). 2024;14(21):3071. Doi:10.3390/ani14213071.
40. Tian H, Zhou X, Wang H, Xu C, Zhao Z, Xu W, et al. The prediction of clinical mastitis in dairy cows based on milk yield, rumination time, and milk electrical conductivity using machine learning algorithms. Animals (Basel). 2024;14(3):427. Doi:10.3390/ani14030427.
41. Wiseman L, Sanderson J, Zhang A, Jakku E. Farmers and their data: An examination of farmers' reluctance to share their data through the lens of the laws impacting smart farming. NJAS Wageningen J Life Sci. 2019;9091:100301. Doi:10.1016/j.njas.2019.04.007.
42. Wolfert S, Ge L, Verdouw C, Bogaardt MJ. Big data in smart farming: A review. Agric Syst. 2017;153:69-80. Doi:10.1016/j.agsy.2017.01.023.
43. Yousfi M, M'Sadak Y. Smart dairy cattle farming: Current tools, technologies, and future (literature review). Afr Mediterr Agric J (Al Awamia). 2025;147:115-127. Doi:10.34874/IMIST.PRSM/afrimed-i147.54174.