1 Introduction

TPrecision dairy farming represents a transformative approach in the agricultural sector, leveraging advanced technologies to enhance the efficiency and productivity of dairy farms. This method integrates various data-driven tools and techniques to monitor and manage dairy cattle, aiming to optimize milk production, improve animal health, and reduce environmental impact. The advent of precision farming has been driven by the need to meet the growing demand for dairy products while ensuring sustainable farming practices (García et al., 2020; Slob et al., 2020; Sharma et al., 2021).

Modern dairy farming has seen a significant shift with the incorporation of technologies such as the Internet of Things (IoT), big data analytics, and machine learning (ML). These technologies enable real-time monitoring and data collection from various sensors placed on animals and farm equipment. For instance, IoT devices can track cow behavior, health parameters, and environmental conditions, providing valuable insights for farm management (Akhter and Sofi, 2021). Big data analytics further processes this information to identify patterns and trends, facilitating informed decision-making (García et al., 2020). The integration of these technologies has revolutionized dairy farming, making it more precise, efficient, and sustainable (Lokhorst et al., 2019; Slob et al., 2020).

Machine learning, a subset of artificial intelligence, involves the development of algorithms that can learn from and make predictions based on data. In the context of dairy farming, ML algorithms analyze vast amounts of data collected from various sources to predict outcomes such as milk yield, disease outbreaks, and optimal feeding times (Slob et al., 2020; Cockburn, 2020). These algorithms can handle complex and high-dimensional data, making them ideal for applications in precision dairy farming where multiple variables need to be considered simultaneously (Condran et al., 2022). The use of ML in dairy farming not only enhances productivity but also improves animal welfare by enabling early detection of health issues and optimizing resource use (Shine and Murphy, 2021).

This study provides a comprehensive review of current trends and future prospects of machine learning in precision dairy farming, exploring how ML techniques are utilized to address various challenges in dairy agriculture, such as disease detection, milk production optimization, and animal behavior monitoring. It also discusses the potential benefits and limitations of these technologies, offers insights into future research directions and practical applications, and aims to contribute to the expanding body of knowledge in this field, supporting the adoption of ML technologies in dairy farming practices.

2 Current Applications of Machine Learning in Precision Dairy Farming

2.1 Animal health monitoring

Machine learning (ML) has been extensively applied to the early detection of diseases in dairy farming. Various algorithms, including decision trees, artificial neural networks, and regression-based models, have been utilized to predict health issues such as mastitis, ketosis, lameness, and metritis. These models analyze data from sensors monitoring milk yield, physical activity, rumination time, and milk conductivity to identify cows at risk of developing health disorders (Halachmi and Guarino, 2016; Slob et al., 2020; Zhou et al., 2022). The integration of diverse data sources, such as housing, nutrition, and climate, further enhances the prediction accuracy, enabling timely interventions to prevent disease outbreaks (Lasser et al., 2021).

Predictive models leveraging ML algorithms are also used to forecast the health and longevity of dairy cows. These models utilize historical data on cow characteristics, lactation, and farm conditions to predict future health outcomes and longevity. The use of supervised learning techniques, particularly classification methods, has shown promising results in predicting health-related events and improving decision support systems for farmers (Lokhorst et al., 2019; Cockburn, 2020; Shine and Murphy, 2021). The integration of large datasets from multiple farms can further improve the reliability and accuracy of these predictive models (Cockburn, 2020).

2.2 Milk production optimization

ML algorithms are employed to optimize milk production by predicting milk yield based on various factors such as cow characteristics, lactation stage, and milking parameters. Decision tree-based algorithms and artificial neural networks are commonly used to analyze these variables and provide accurate predictions of milk yield (Cockburn et al., 2020; Slob et al., 2020; Sharma et al., 2021). The use of time-series data and supervised learning methods has been particularly effective in enhancing the precision of milk yield predictions (Lokhorst etal., 2019).

Optimizing feed efficiency and nutrient balance is another critical application of ML in dairy farming. By analyzing data from feeding lists, behavioral sensors, and health records, ML models can predict the optimal feed composition and quantity for individual cows, thereby improving feed efficiency and nutrient utilization (Halachmi and Guarino, 2016; Cockburn, 2020; Sharma et al., 2021). These models help in reducing feed costs and enhancing milk production while maintaining the health and well-being of the cows.

2.3 Reproduction and fertility management

ML-based heat detection systems have revolutionized reproduction management in dairy farming. These systems use data from behavioral sensors and activity monitors to accurately detect estrus in cows, enabling timely artificial insemination and improving reproductive efficiency (Halachmi and Guarino, 2016; Cockburn, 2020). The use of supervised learning algorithms, particularly classification methods, has been effective in identifying heat events with high accuracy (Lokhorst et al., 2019).

Artificial intelligence (AI) techniques, including ML algorithms, are also used to predict fertility outcomes in dairy cows. By analyzing data on cow characteristics, health records, and environmental conditions, these models can forecast the likelihood of successful conception and calving (Sharma et al., 2021; Cockburn, 2020). The integration of diverse data sources and advanced ML techniques, such as deep learning, further enhances the accuracy of fertility predictions (Yousefi et al., 2022).

2.4 Environmental monitoring and management

ML algorithms are employed to analyze real-time sensor data to monitor and manage barn conditions, such as temperature, humidity, and air quality. These models help in maintaining optimal environmental conditions for the cows, thereby improving their health and productivity (Halachmi and Guarino, 2016; Cockburn, 2020). The use of IoT-enabled sensors and ML techniques allows for continuous monitoring and timely adjustments to barn conditions (Sharma et al., 2021).

Optimizing the use of water and feed resources is another important application of ML in precision dairy farming. By analyzing data on water usage, feed intake, and environmental conditions, ML models can predict the optimal allocation of these resources, reducing waste and improving efficiency (Sharma et al., 2021). These models help in sustainable resource management and contribute to the overall profitability of dairy farms.

Machine learning has become an integral part of precision dairy farming, offering innovative solutions for animal health monitoring, milk production optimization, reproduction management, and environmental monitoring. The integration of diverse data sources and advanced ML techniques holds great promise for the future, enabling more accurate predictions and efficient farm management practices. As the technology continues to evolve, the potential for ML in precision dairy farming will only grow, driving further advancements in the industry.

3 Data Sources for Machine Learning in Dairy Farming

3.1 Sensor technology and IoT devices

Wearable sensors have become increasingly accessible and affordable, providing valuable data for monitoring cow behavior and health. These sensors can track various activities such as feeding, rumination, and movement, which are crucial for early disease detection and overall herd management. For instance, commercial acceleration measuring tags connected via Bluetooth Low Energy (BLE) have been used to classify feeding behavior with high accuracy using convolutional neural networks (CNNs) and transfer learning techniques (Bloch et al., 2023). Additionally, wearable precision dairy technologies (WPDT) can monitor time spent at the feed bunk, rumination time, eating time, lying time, standing time, walking time, activity, and transitions between lying and standing, providing comprehensive behavioral data (Eckelkamp, 2019).

Barn monitoring systems equipped with sensors and cameras generate large amounts of data that can be used for real-time monitoring and predictive analytics. These systems can capture data on environmental conditions, cow positioning, and interactions within the barn. For example, automated systems can measure feed intake and environmental parameters, which are essential for optimizing feeding strategies and improving animal welfare (Koltes et al., 2021). Integrating these data sources with machine learning models can enhance the prediction of disease risk and other critical parameters, thereby improving farm management practices (Lasser et al., 2021).

3.2 Genomic data and animal genetics

Genomic data provides a wealth of information that can be integrated into machine learning models to predict various traits and improve breeding programs. By combining genomic data with other data sources such as phenotypic and environmental data, more accurate and robust predictive models can be developed. This integration allows for the identification of genetic markers associated with desirable traits, thereby facilitating more informed breeding decisions (Cockburn, 2020). The use of high-throughput assays and omics data can further enhance the precision of these models, enabling the identification of complex trait relationships and underlying genetics (Koltes, 2021).

Predictive analytics can significantly improve breeding programs by identifying animals with the highest genetic potential for specific traits. Machine learning algorithms can analyze large datasets to predict outcomes such as milk yield, disease resistance, and reproductive performance. For example, integrating diverse data sources, including genomic, phenotypic, and environmental data, can improve the prediction of disease risk and other important traits, leading to more effective breeding strategies (Lasser et al., 2021). This approach not only enhances the genetic quality of the herd but also contributes to overall farm productivity and sustainability (Cockburn, 2020).

3.3 Behavioral and environmental data

Behavioral data, such as feeding, drinking, and social interactions, provide critical insights into the health and well-being of dairy cows. Machine learning models can analyze these behaviors to detect anomalies that may indicate health issues or changes in welfare. For instance, wearable sensors and barn monitoring systems can track feeding and drinking patterns, which are essential for early detection of diseases and optimizing feeding strategies (Figure 1) (Eckelkamp, 2019; Bloch et al., 2023). Additionally, social behaviors can be monitored to understand herd dynamics and identify potential stressors or welfare concerns (Sharma et al., 2021).

Figure 1 Component of the location and acceleration measuring system installed in a barn (Adopted from Bloch et al., 2023) Image caption: RuuviTag inside a protecting plastic box (a), tag on the cow collar (b) and receiving station installed on a barn structure (c) marked by red circles (Adopted from Bloch et al., 2023)

Environmental factors such as temperature, humidity, and air quality can significantly impact animal performance and health. Integrating these factors with behavioral and physiological data can provide a comprehensive understanding of how environmental conditions affect dairy cows. Machine learning models can analyze these integrated datasets to predict outcomes such as milk yield, disease risk, and overall animal performance (Cockburn, 2020; Lasser et al., 2021). This holistic approach enables farmers to make data-driven decisions to optimize the barn environment and improve animal welfare and productivity (Cabrera et al., 2019).

The integration of diverse data sources, including sensor technology, genomic data, and behavioral and environmental data, is revolutionizing precision dairy farming. Machine learning models leveraging these data sources can provide valuable insights for improving herd management, disease detection, and breeding programs. As technology continues to advance, the potential for more accurate and comprehensive predictive analytics in dairy farming will only grow, leading to more sustainable and efficient farming practices.

4 Machine Learning Models and Techniques Used

4.1 Supervised learning in dairy farming

Regression models are widely used in precision dairy farming to predict various continuous outcomes such as milk yield and quality. These models help in understanding the relationship between different farm parameters and the output variables. For instance, regression-based algorithms have been applied to predict milk production and quality by analyzing factors like milking parameters and milk properties (Slob et al., 2020). Additionally, regression methods are utilized to forecast yield by integrating agrarian factors, which include soil, climate, and water regime (Elavarasan et al., 2018; Yang, 2024).

Classification algorithms are extensively used to predict health-related issues and yield outcomes in dairy farming. Decision tree-based algorithms are the most commonly used, followed by artificial neural networks (Slob et al., 2020). These algorithms help in early disease detection, which is crucial for maintaining the health and productivity of dairy cows. For example, supervised ensemble classifiers have been employed to classify cattle behavior patterns, aiding in the early detection of health issues such as lameness (Dutta et al., 2015). Moreover, classification techniques are used to predict various health conditions and milk yield, enhancing the decision-making process for dairy farmers (Cockburn, 2020).

4.2 Unsupervised learning techniques

Clustering techniques are used to group animals based on their health and productivity metrics. These unsupervised learning methods help in identifying patterns and anomalies that are not apparent through traditional analysis. For instance, partitioning around medoids clustering has been used to model groups of farms based on production parameters and bulk tank milk antibody status of internal parasites (Oehm et al., 2022). This approach helps in understanding the complex relationships between parasitic infections and milk production, thereby aiding in better farm management.

Anomaly detection techniques are crucial for identifying unusual patterns in feed intake and animal behavior, which can indicate health issues or management problems. These techniques help in monitoring the well-being of dairy cows by detecting deviations from normal behavior. For example, unsupervised clustering frameworks have been developed to study the natural structure of sensor data, which can then be used to guide supervised learning for more accurate behavioral classification (Dutta et al., 2015). This approach ensures that any anomalies in feed intake or behavior are promptly identified and addressed.

4.3 Deep learning approaches

Deep learning, particularly neural networks, has shown great promise in image recognition tasks within precision dairy farming. Neural networks are used to analyze images and videos to detect conditions such as lameness in dairy cows. This method provides a non-invasive and efficient way to monitor animal health. For instance, neural network-based algorithms have been increasingly utilized for tasks like lameness detection, leveraging the power of deep learning to analyze complex visual data (Shine and Murphy, 2021). LSTM networks are a type of recurrent neural network (RNN) that are particularly effective for time-series predictions. In dairy farming, LSTM networks are used to predict future trends based on historical data, such as milk yield and cow health metrics. These networks can handle the temporal dependencies in the data, making them ideal for forecasting tasks. For example, time-series data, which is prevalent in animal-based farm data, is often analyzed using LSTM networks to predict future outcomes and improve farm management practices (Lokhorst et al., 2019).

Machine learning models and techniques are revolutionizing precision dairy farming by providing advanced tools for prediction, classification, and anomaly detection. Supervised learning methods, including regression and classification algorithms, are widely used for predicting health and yield outcomes. Unsupervised learning techniques, such as clustering and anomaly detection, help in understanding complex patterns in animal behavior and health. Deep learning approaches, particularly neural networks and LSTM networks, offer powerful solutions for image recognition and time-series predictions. As the field continues to evolve, the integration of multiple data sources and advanced machine learning techniques will further enhance the efficiency and productivity of dairy farming.

5 Challenges and Limitations in Applying Machine Learning

5.1 Data quality and availability

One of the primary challenges in applying machine learning (ML) in precision dairy farming is the inconsistency in data collection across different farms. Variability in data collection methods, sensor types, and data recording practices can lead to significant discrepancies in the datasets used for training ML models. This inconsistency can hinder the development of robust and generalizable models, as highlighted by the systematic literature review which identified data quality as a critical issue (Gengler et al., 2019; Slob et al., 2020). Additionally, the lack of standardized protocols for data collection exacerbates this problem, making it difficult to compare and integrate data from multiple sources (Cockburn, 2020; Shine and Murphy, 2021).

The proliferation of sensors and IoT devices in dairy farming generates vast amounts of data, which poses a significant challenge in terms of data management and analysis. The volume of data can overwhelm traditional data processing systems, necessitating the use of advanced big data analytics and real-time data integration techniques (Lokhorst et al., 2019; Cabrera et al., 2019). Effective data management strategies are essential to handle the high volume, velocity, and variety of data generated, as noted in studies focusing on big data in precision dairy farming (Kolipaka, 2020). Moreover, ensuring data quality and consistency across these large datasets remains a persistent challenge (Gengler, 2019; Liu et al., 2023).

5.2 Integration with traditional farming practices

Despite the potential benefits of ML, there is often resistance to adopting new technologies among farmers. This resistance can stem from a lack of understanding of the technology, perceived complexity, or concerns about the cost and reliability of ML systems (Cockburn, 2020; Shine and Murphy, 2021). The integration of ML into traditional farming practices requires not only technological advancements but also efforts to educate and train farmers on the use and benefits of these technologies (Cabrera et al., 2019; Sharma et al., 2021). Overcoming this resistance is crucial for the successful implementation of ML in precision dairy farming.

Another significant challenge is the gap between ML experts and farmers. Effective communication and collaboration between these two groups are essential to ensure that ML solutions are practical, user-friendly, and address the real needs of farmers (Cockburn, 2020). Bridging this gap involves developing tools and interfaces that are accessible to farmers, as well as fostering a mutual understanding of the challenges and opportunities in precision dairy farming (García et al., 2020). Collaborative projects that involve both ML experts and farmers can help in creating more effective and widely accepted solutions (Shine and Murphy, 2021).

5.3 Ethical and Privacy Concerns

The use of ML in precision dairy farming raises significant data privacy concerns. Farms generate sensitive data that, if mishandled, could lead to privacy breaches and misuse of information. Ensuring the privacy and security of farm data is paramount, and this requires robust data governance frameworks and compliance with data protection regulations (Gengler, 2019; Liu et al., 2023). The challenge lies in balancing the need for data sharing to improve ML models with the necessity of protecting farmers' privacy.

Ethical considerations also play a crucial role in the application of ML in dairy farming, particularly concerning the use of animal data. The collection and analysis of data related to animal health, behavior, and productivity must be conducted ethically, ensuring that the welfare of the animals is not compromised (Cockburn, 2020). Researchers and practitioners must adhere to ethical guidelines and standards to ensure that the use of ML contributes positively to animal welfare and does not lead to adverse outcomes (Slob et al., 2020). Addressing these ethical concerns is essential for the sustainable and responsible use of ML in precision dairy farming.

6 Case Study: Predictive Health Monitoring in a Large-Scale Dairy Farm

6.1 Farm overview and setup

The case study focuses on a large-scale dairy farm that has integrated advanced technological systems to enhance its operational efficiency and animal health management. The farm utilizes a combination of automated milking systems, behavioral sensors, and health monitoring devices to collect extensive data on each cow. This setup allows for continuous monitoring of various parameters such as milk yield, physical activity, rumination time, and electrical conductivity of milk, which are crucial for early disease detection and overall herd management (Cockburn, 2020; Slob et al., 2020; Zhou et al., 2022).

6.2 Use of machine learning for disease prediction

The farm employs multiple machine learning algorithms to predict common health disorders in dairy cows, including clinical mastitis, subclinical ketosis, lameness, and metritis. The selection of models is based on their ability to handle large datasets and provide accurate predictions. Decision tree-based algorithms, such as Rpart, and ensemble methods like eXtreme Gradient Boosting (XGBoost) and Adaboost, have been particularly effective. These models are trained using historical data collected from the farm, which includes variables such as milk yield, activity levels, rumination patterns, and milk conductivity (Zhou et al., 2022). The training process involves splitting the data into training and validation sets to ensure the models can generalize well to new, unseen data (Lasser et al., 2021).

The integration of machine learning models with the farm's Internet of Things (IoT) and sensor systems is a critical component of the predictive health monitoring setup. Sensors placed on cows and within the milking systems continuously collect data, which is then transmitted to a central database. This data is pre-processed and fed into the machine learning models in real-time, allowing for continuous health monitoring and early detection of potential issues. The use of IoT devices ensures that data is collected consistently and accurately, providing a robust foundation for the machine learning algorithms to operate effectively (Cabrera et al., 2019; Lokhorst et al., 2019; Lasser et al., 2021).

The implementation of predictive health monitoring using machine learning has led to significant improvements in both animal health and milk production on the farm. Early detection of diseases such as mastitis and ketosis has allowed for timely interventions, reducing the severity and duration of these conditions. This proactive approach has not only improved the overall well-being of the cows but also enhanced milk yield and quality. The farm has reported a reduction in disease incidence rates and an increase in milk production efficiency, demonstrating the effectiveness of integrating machine learning with precision dairy farming practices (Cabrera et al., 2019; Lasser et al., 2021).

7 Future Prospects of Machine Learning in Precision Dairy Farming

7.1 Advancements in ml algorithms and their potential in dairy

The future of machine learning (ML) in precision dairy farming is promising, with advancements in algorithms playing a crucial role. Decision tree-based algorithms and artificial neural networks have been widely used, but there is a growing interest in hybrid models that combine multiple techniques to enhance prediction accuracy and reliability (Slob et al., 2020; Cockburn, 2020). For instance, hybrid models like the K-medoids, random forest, and support vector regression (K-R-S) approach have shown significant improvements in predicting lactation curves, demonstrating the potential of advanced ML algorithms in dairy farming (Zhang et al., 2022). Additionally, the development of label-efficient learning methods, which require fewer labeled data for training, can address the challenges of data scarcity and high labeling costs, further enhancing the applicability of ML in dairy farming (Li et al., 2023).

7.2 Integration of ML with robotics and automated systems

The integration of ML with robotics and automated systems is set to revolutionize precision dairy farming. Robotic milking systems, automated feeding systems, and behavioral sensors generate vast amounts of data that can be analyzed using ML algorithms to optimize farm operations (Cockburn, 2020). For example, the Dairy Brain project aims to create a real-time, data-driven decision-making engine by integrating data from various sources, including sensors and robotic systems, to improve whole-farm management (Cabrera et al., 2019). This integration can lead to more efficient resource utilization, better animal health monitoring, and enhanced productivity, ultimately transforming dairy farming practices.

7.3 Role of cloud computing and big data analytics in enhancing dairy productivity

Cloud computing and big data analytics are essential for handling the large volumes of data generated in precision dairy farming. These technologies enable the storage, processing, and analysis of data from multiple sources, facilitating real-time decision-making and predictive analytics. The use of big data analytics can help identify patterns and trends in dairy farm data, leading to improved disease detection, milk production, and overall farm management. The integration of cloud computing with ML algorithms allows for scalable and efficient data processing, making it possible to leverage the full potential of big data in dairy farming (Lokhorst et al., 2019).

7.4 Policy and regulatory support for ml adoption in agriculture

The successful adoption of ML in precision dairy farming requires supportive policies and regulations. Governments and regulatory bodies need to create frameworks that encourage the use of advanced technologies in agriculture while ensuring data privacy and security. Policy support can include funding for research and development, incentives for technology adoption, and the establishment of standards for data interoperability and integration. By fostering a conducive environment for ML adoption, policymakers can help accelerate the transformation of dairy farming, leading to increased productivity, sustainability, and profitability (Sharma et al., 2020).

8 Concluding Remarks

The application of machine learning (ML) in precision dairy farming has seen significant advancements over recent years. A systematic review identified that more than half of the studies focused on disease detection, with other prominent areas being milk production and quality. The use of decision tree-based algorithms and artificial neural networks has been prevalent, with sensitivity, specificity, and RMSE being the most common evaluation metrics. Big Data analytics, particularly supervised learning methods, have also been extensively applied, with a notable focus on animal-based farm data. The integration of various data sources, such as sensors and herd management systems, has been crucial in developing predictive models for milk yield and animal health. Despite the progress, challenges such as data integration, feature selection, and handling unbalanced data remain.

One of the primary challenges in the application of ML in dairy farming is the integration of diverse data sources to improve the reliability and accuracy of predictive models. The need for larger, integrated datasets that cover longer periods is essential to enhance the performance of ML algorithms. Additionally, addressing issues such as class imbalance, data sparsity, and high dimensionality is crucial for the effective application of ML techniques in agriculture. There is also a growing need for the development of hybrid models that can diagnose and prescribe solutions for animal health issues, thereby providing a more comprehensive approach to precision livestock farming. The potential of Big Data in precision dairy farming is yet to be fully realized, and future research should focus on utilizing multiple Big Data characteristics and sources simultaneously to add value to decision-making processes.

Machine learning holds immense potential in promoting sustainable dairy farming by enhancing productivity and animal welfare while reducing resource exploitation and environmental impact. The use of ML algorithms in precision livestock farming can lead to more efficient feeding practices, better health monitoring, and improved management of dairy herds. By leveraging IoT and AI technologies, farmers can monitor animal behavior, health, and feed intake in near real-time, enabling timely interventions and better management practices. The integration of ML with other disruptive technologies such as cloud computing and blockchain can further enhance the sustainability of agricultural supply chains by providing real-time analytic insights for proactive decision-making. As the field continues to evolve, the adoption of ML in dairy farming is expected to play a crucial role in ensuring food security, ecological sustainability, and economic growth.

Acknowledgements

We would like to express our gratitude to reviewers for their suggested revisions to this study.

Conflict of Interest Disclosure

Authors affirm that this research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest.

References

Akhter R., and Sofi S., 2021, Precision agriculture using IoT data analytics and machine learning, J. King Saud Univ. Comput. Inf. Sci., 34: 5602-5618.

https://doi.org/10.1016/J.JKSUCI.2021.05.013

Bloch V., Frondelius L., Arcidiacono C., Mancino M., and Pastell M., 2023, Development and analysis of a CNN- and transfer-learning-based classification model for automated dairy cow feeding behavior recognition from accelerometer data, Sensors (Basel, Switzerland), 23(5): 2611.

https://doi.org/10.3390/s23052611

PMid:36904813 PMCid:PMC10006954

Cabrera V., Barrientos-Blanco J., Delgado H., and Fadul-Pacheco L., 2019, Symposium review: Real-time continuous decision making using big data on dairy farms, Journal of Dairy Science, 103(4): 3856-3866.

https://doi.org/10.3168/jds.2019-17145

PMid:31864744

Cockburn M., 2020, Review: application and prospective discussion of machine learning for the management of dairy farms, Animals : an Open Access Journal from MDPI, 10(9): 1690.

https://doi.org/10.3390/ani10091690

PMid:32962078 PMCid:PMC7552676

Condran S., Bewong M., Islam M., Maphosa L., and Zheng L., 2022, Machine learning in precision agriculture: a survey on trends, applications and evaluations over two decades, IEEE Access, 10: 73786-73803.

https://doi.org/10.1109/ACCESS.2022.3188649

Dutta R., Smith D., Rawnsley R., Bishop-Hurley G., Hills J., Timms G., and Henry D., 2015, Dynamic cattle behavioural classification using supervised ensemble classifiers, Comput. Electron. Agric., 111: 18-28.

https://doi.org/10.1016/j.compag.2014.12.002

Eckelkamp E., 2019, Invited review: current state of wearable precision dairy technologies in disease detection, Applied Animal Science, 35(2): 209-220.

https://doi.org/10.15232/AAS.2018-01801

Elavarasan D., Vincent D., Sharma V., Zomaya A., and Srinivasan K., 2018, Forecasting yield by integrating agrarian factors and machine learning models: a survey, Comput. Electron. Agric., 155: 257-282.

https://doi.org/10.1016/j.compag.2018.10.024

García R., Aguilar J., Aguilar J., Toro M., Pinto Á., and Rodríguez P., 2020, A systematic literature review on the use of machine learning in precision livestock farming, Comput. Electron. Agric., 179: 105826.

https://doi.org/10.1016/j.compag.2020.105826

Gengler N., 2019, Symposium review: Challenges and opportunities for evaluating and using the genetic potential of dairy cattle in the new era of sensor data from automation.. Journal of dairy science, 102(6): 5756-5763.

https://doi.org/10.3168/jds.2018-15711

PMid:30904300

Halachmi I., and Guarino M., 2016, Editorial: Precision livestock farming: a 'per animal' approach using advanced monitoring technologies, Animal : An International Journal of Animal Bioscience, 10(9) 1482-1483.

https://doi.org/10.1017/S1751731116001142

PMid:27534883

Kolipaka V., 2020, Predictive analytics using cross media features in precision farming, International Journal of Speech Technology, 23: 57-69.

https://doi.org/10.1007/s10772-020-09669-z

Koltes J., 2021, 51 opportunities to apply and learn from deep phenotyping in dairy cattle, Journal of Animal Science, 99(3): 30-31.

https://doi.org/10.1093/jas/skab235.051

Lasser J., Matzhold C., Egger-Danner C., Fuerst-Waltl B., Steininger F., Wittek T., and Klimek P., 2021, Integrating diverse data sources to predict disease risk in dairy cattle-a machine learning approach.. Journal of animal science, 99(11): 294.

https://doi.org/10.1093/jas/skab294

Li J., Chen D., Qi X., Li Z., Huang Y., Morris D., and Tan X., 2023, Label-efficient learning in agriculture: a comprehensive review, ArXiv, 215: 108412.

https://doi.org/10.48550/arXiv.2305.14691

Liu N., Qi J., An X., and Wang Y., 2023, A review on information technologies applicable to precision dairy farming: focus on behavior, health monitoring, and the precise feeding of dairy cows, Agriculture, 13(10): 1858.

https://doi.org/10.3390/agriculture13101858

Lokhorst C., Mol R., and Kamphuis C., 2019, Invited review: big data in precision dairy farming, Animal, 13: 1519-1528.

https://doi.org/10.1017/S1751731118003439

PMid:30630546 PMCid:PMC6581964

Oehm A., Springer A., Jordan D., Strube C., Knubben-Schweizer G., Jensen K., and Zablotski Y., 2022, A machine learning approach using partitioning around medoids clustering and random forest classification to model groups of farms in regard to production parameters and bulk tank milk antibody status of two major internal parasites in dairy cows, PLoS ONE, 17(7): e0271413.

https://doi.org/10.1371/journal.pone.0271413

PMid:35816512 PMCid:PMC9273072

Sharma A., Jain A., Gupta P., and Chowdary V., 2021, Machine learning applications for precision agriculture: a comprehensive review, IEEE Access, 9: 4843-4873.

https://doi.org/10.1109/ACCESS.2020.3048415

Sharma R., Kamble S., Gunasekaran A., Kumar V., and Kumar A., 2020, A systematic literature review on machine learning applications for sustainable agriculture supply chain performance, Comput. Oper. Res., 119: 104926.

https://doi.org/10.1016/j.cor.2020.104926

Shine P., and Murphy M., 2021, Over 20 years of machine learning applications on dairy farms: a comprehensive mapping study, Sensors (Basel, Switzerland), 22(1): 52.

https://doi.org/10.3390/s22010052

PMid:35009593 PMCid:PMC8747441

Slob N., Catal C., and Kassahun A., 2020, Application of machine learning to improve dairy farm management: A systematic literature review, Preventive Veterinary Medicine, 187: 105237.

https://doi.org/10.1016/j.prevetmed.2020.105237

PMid:33418514

Yang B., 2024, Enhancing dairy cow milk fat synthesis genes with CRISPR-Cas9 technology to increase dairy product yield, International Journal of Molecular Veterinary Research, 14(1): 9-16.

https://doi.org/10.5376/ijmvr.2024.14.0002

Yousefi D., Rafie A., Al-Haddad S., and Azrad S., 2022, A systematic literature review on the use of deep learning in precision livestock detection and localization using unmanned aerial vehicles, IEEE Access, 10: 80071-80091.

https://doi.org/10.1109/access.2022.3194507

Zhang F., Weigel K., and Cabrera V., 2022, 20 New insights on data integration and artificial intelligence to predict primiparous lactation curves capturing genotype-by-environment interactions, Journal of Animal Science, 100(3): 12.

https://doi.org/10.1093/jas/skac247.021

PMCid:PMC9494002

Zhou X., Xu C., Wang H., Xu W., Zhao Z., Chen M., Jia B., and Huang B., 2022, The early prediction of common disorders in dairy cows monitored by automatic systems with machine learning algorithms, Animals : an Open Access Journal from MDPI, 12(10): 1251.

https://doi.org/10.3390/ani12101251

PMid:35625096 PMCid:PMC9137925