Abstract
Globally, climate change, economic crises, and increased food demand pose significant challenges to the stability of agricultural production systems, underscoring the urgent need for more innovative approaches and tools to advance livestock production science. Machine Learning (ML) development supported the Digital Twin (DT), a digital replica of a real-world entity, as a game-changer in modern livestock science, enabling the prediction, optimisation, and simulation across various research environments. At the same time, it has been shown that synergism between ML and Digital Twin (DT) can mimic animals' physiological and physical state and behavior based on input data, leading to a better understanding of animal behavior, nutritional requirements, physiological status, or environmental stressors to investigate responses and suggest precise decisions. Moreover, such animal simulation models can offer deeper insights and predictive analytical tools that support animal welfare, forecast production efficiency, and sustainability. Although traditional simulation models are mainly snapshot-state models that indicate what should happen on average, ML-DT integration serves as a living mirror, dynamically predicting what is happening right now and what will happen to each animal under various changes. This integration can be a versatile tool for introducing solutions in the research domain; however, its augmentation remains complex and poses significant ethical, economic, and governance challenges. This review discusses recent ML-DT synergism applications in both barns and labs, highlighting their potential to reform both industry and research.
1 Introduction
Recently, Machine learning (ML) inclusion in animal science has grown significantly, supported by the development of remote monitoring technologies while facilitating more sustainable resource utilization by encompassing a range of tools and techniques, including in-field livestock monitoring, greenhouse gas emissions, body composition and physiology assessments, ground- or aerial-based livestock, automated in-field live weight measurement, on- and in-animal devices, and GPS (1, 2).
Additionally, ML models like random forest (RF), neural network (NN), deep learning (DL), Ensemble, support vector machine (SVM), k-nearest neighbors (KNN), and logistic regression (LR) showed promising results, predict outcomes, and uncover patterns crucial for enhancing animal health, productivity, and welfare (3–5). Also, these models can forecast economic returns without requiring extensive long-term individual observations (6), milk prices (7), and beef and lamb prices, offering robust support for managing these prices and facilitating higher income for producers (8).
These ML applications demonstrate the versatility in addressing complex problems not only in the production sector, but also in research fields such as artificial neural networks (ANN), which have been deployed in various biological sciences fields for data categorization into different classes, pattern recognition, future prediction, performance optimisation, and decision-making support (9) (Figure 1). Then, the next generation of ML models merged to introduce the digital twin (DT), which virtually constructs a digital replica that reflects the characteristics, state, and behavior of the corresponding physical entity and is updated in real-time as the physical entity changes (10–12). Furthermore, ML–DT integration has been applied to multiple domains, including nutrition, health, behavior, and product quality, such as predicting in vitro rumen VFA production (13), developing digital twin models for cattle care (14), and evaluating meat quality using computer vision (15). Additionally, such advancements led to the Precision Livestock Farming (PLF) approach, which incorporates Information and Communication Technologies (ICT) to enhance agricultural practices, reduce costs, and increase production, significantly contributing to the industrial revolution, referred to as Industry 4.0 and 5.0 (16–18).
Figure 1
Therefore, progressive advances in integrating ML-DT have opened up the scope for digital tools to solve industrial and scientific challenges that may transform livestock production and research, both in the present and the future.
2 Review methodology
2.1 Review design and scope
This review employs a narrative review methodology to critically synthesize recent research on machine learning (ML) and digital twin (DT) technologies and their augmentation in livestock production and research. With a focus on precision livestock farming, decision-support systems, and digital transformation, the scope includes methodological advancements, application domains, and integration issues across poultry, ruminant, pig, and multi-species livestock systems. The review investigates the applications and the potential for extending this contribution to the livestock research field.
2.2 Literature sources, search strategy, and selection process
The references were extracted from peer-reviewed articles indexed in major international scientific databases, including Google Scholar, Web of Science (SCI-Expanded), Scopus, ScienceDirect, SpringerLink, IEEE Xplore, PubMed, PMC, MDPI journals, and Frontiers journals.
“The review mainly focused on original research and review articles, complemented by selected studies for advanced methodological. While searches were in English, the keywords used for relevant articles, including but not limited to: “machine learning,” “deep learning,” “artificial intelligence,” “digital twin,” “precision livestock farming,” “smart farming,” “sensor- based monitoring,” “IoT,” “genomic prediction,” “animal health monitoring,” and “livestock decision support systems.” The initial selection focused on titles and abstracts to eliminate irrelevant records and duplicates. The final dataset comprised 195 references, representing a comprehensive, multi-species, and multidisciplinary set of articles (Tables 1, 2).”
Table 1
| Journal/Source | No. of articles |
|---|---|
| Animals (MDPI) | 34 |
| Sensors (MDPI) | 17 |
| Agriculture/Electronics/Applied Sciences (MDPI) | 14 |
| Journal of Animal Science | 12 |
| Computers and Electronics in Agriculture | 11 |
| Journal of Dairy Science | 9 |
| Poultry Science | 9 |
| Frontiers Journals (Vet Sci, Anim Sci, AI, Genomics) | 14 |
| Scientific Reports | 8 |
| Animal/Livestock Science/Meat Science | 14 |
| Genetics/Genomics Journals | 11 |
| AI/Data Science/Engineering Journals | 11 |
| Conference Proceedings (IEEE, IFAC, others) | 7 |
| Books/Book Chapters (Springer, Elsevier) | 4 |
| Other journals (single-occurrence sources) | 20 |
| The total | 195 |
The 195 references distribution by journal/source.
Table 2
| Category | Number of references |
|---|---|
| Poultry | 48 |
| Ruminants | 79 |
| Pig/multi-species | 68 |
| Total | 195 |
Overall summary by livestock category.
3 Mathematical model to machine learning: theory-driven vs. data-driven competition or integration?
Mathematical models (MMs) in livestock production have been utilized to simulate and forecast various aspects of behavior, health conditions, reproductive status, production performance, and environmental factors (19–21). Although MMs are difficult to reproduce, which exacerbates the challenge of automatically updating key input parameters (22, 23), MMs are still more transparent, Easier to audit, and safer from algorithmic bias than ML, which is expanding and competing with traditional mathematical restrictions (24–26). At the same time, working with larger datasets posed the main challenge for MMs' application, as addressing accuracy issues requires simplifying assumptions (27–29). However, ML models showed remarkable accuracy and potential in predicting production outcomes and health alerting models (30) (Table 3).
Table 3
| Comparison | ML | MM | References |
|---|---|---|---|
| Approach | Artificial intelligence subsets enable systems to involve training algorithms, identify patterns, and make decisions with minimal human intervention, using large datasets to improve their performance over time. | They are used to understand the relationships between variables and predict outcomes based on established mathematical principles and theory. | (75, 76) |
| Data processing | ML algorithms require substantial data processing capabilities, particularly those for deep learning. The need for large volumes of data and the iterative nature of training often require significant computational resources. | These models process data using predefined equations and relationships, which are less data-dependent and require less processing power. The data requirements are often specific and may not need to be as large as those for ML models. | (76) |
| Complexity and adaptability | By retraining, ML algorithms can handle complex, high-dimensional data and adapt to new data, which may be less computationally intensive than redesigning a mathematical model. | While complex, they often require a deep understanding of the underlying processes to be accurately formulated. | (76) |
| Development process | The development process involves data preprocessing, feature selection, model selection, training, and validation. | The process involves defining the problem, formulating equations based on theoretical knowledge, solving these equations, and validating the model against known data. | (77) |
| Real-time processing | Real-time ML processing can be more challenging, especially with large models, as it may require substantial computational power to process data and make predictions promptly. | Since mathematical models are often based on simple calculations, they can be processed in real time, making them suitable for applications requiring immediate responses. | (78) |
| Limitations | |||
| •ML models, especially deep learning models, can be considered “black boxes” because it's often difficult to understand how they arrive at their predictions. Compared to ML, MM models are generally more transparent and interpretable because their structure and variable relationships are explicitly defined. | •Scalability can be an issue if the model's complexity grows with the problem's size, leading to computational challenges. | (78–80) | |
| •MLs are heavily dependent on data. They require large amounts of data to train and improve their accuracy. | •Adapting them to new data or conditions may require a complete reevaluation and reformulation. | ||
| Wearable sensors, imaging systems, and automated monitoring platforms produce high-resolution data streams that require substantial computing resources, including reliable internet access and high-performance hardware. For livestock systems in low- and middle-income areas, where technological infrastructure and qualified workers may be limited, these criteria pose serious challenges. The ongoing maintenance and updates of ML models also drive long-term operational costs. | •While data can be used to parameterise these models, MM are not solely reliant on data. They are based on theoretical understanding and can be developed with or without empirical data. | ||
Conceptual, strengths, limitations, comparison of machine learning (ML), and mathematical models (MM) used in livestock research.
4 Data source and model initiation; the record-based, sensor-based, and the challenging integration
Before adopting a specific model, problem identification with parametric, scalable attributes to be evaluated is the critical first step for model building; then, the process proceeds to subsequent steps (Figure 2). Then ML processes large datasets, identifies intelligent patterns, and makes predictions based on learned experience (31, 32), depending on farm records such as milk yield, milk analysis, feed records, reproduction records, breeding records, and health records (33, 34).
Figure 2
However, researchers should incorporate extensive variability into their datasets and employ classifiers to mitigate overfitting, which can be controlled through cross-validation (31, 32) and regularization (35, 36), both of which are applied in livestock production and prediction studies (37, 38).
To track behavior, health, and production in real time, smart collars for dairy cows incorporate a range of wearable technologies, including accelerometers, GPS, RFID, and microphones (39). IoT-enabled neck collars with activity and temperature sensors lessen reliance on labor and enable early identification of health abnormalities (40). Furthermore, collar systems that integrate wireless communication, GPS, and vital-sign detection demonstrate how real-time livestock tracking and health monitoring can be implemented in practice (41).
Herein, the sensors serve as a significant data source for innovative farming models (42), including behavioral (43–47), physiological (48–52), and environmental (53–56), which raises integration challenges between record-based and sensor-based data (57).
Therefore, to tackle these challenges, some reports indicate that processes must be objective-driven and specifically tailored to the intended behaviors for specific farm applications (58) (Figure 3). So this challenge highlights the importance of model selection, in which analytical frameworks and algorithms must align with the targeted objective and the farm environment (59) (Table 4).
Figure 3
Table 4
| Data type | ML model | Modeling output | Species | ||
|---|---|---|---|---|---|
| Ruminants | Pigs | Poultry | |||
| Production records, feed intake, phenotypic traits. | regularizing models | Production and genomic performance prediction | (44–48, 81, 82) | (49–55) | (56, 83–87) |
| Sensor data, farm records, health, and management data | Tree-based models | Condition estimation and behavior classification, risk monitoring, and assessment | (88–91) | (92–97) | (98–102) |
| Accelerometer data, sample spectra, and imaging features. | Support Vector Machines (SVM) | Animal status, carcass, and body condition scoring | (103–108) | (49, 53, 55, 109–112) | (100, 113–116) |
| Production, metabolic, and environmental data. | Artificial Neural Networks (ANN) | Production and reproduction traits, and environmental impacts, Prediction | (117–126) | (54, 127–135) | (102, 136–140) |
| Visual/time-series and sensor data. | Deep learning models | Visual identification, status monitoring, and early detection. | (141–149) | (150–158) | (116, 159–165) |
| Multi-sensor data, omics datasets. | Unsupervised learning | Animal phenotyping, anomaly detection, | (166–171) | (154, 172–177) | (178–184) |
Application of different ML models through different data and species.
5 Machine learning-digital twin augmentation in livestock production and research
The relationship between ML and DT is jointly integrated, with ML, especially deep learning, providing digital twins with robust data analysis and pattern recognition capabilities, enabling more intelligent and adaptive applications (60–62). At the same time, DT can enhance predictive analytics, automate decision-making, and ensure secure data exchange among stakeholders when combined with cutting-edge AI/ML, blockchain, and reinforcement learning (12, 62).
For instance, ML-DT integration in comparative genomics can be advantageous for pinpointing virtual phenotypes of livestock traits important for genetic selection and responses under different conditions, thereby helping identify phenotypes linked to resilience and productivity (63, 64). This integration facilitates more effective breeding, nutrition, and sustainability studies by supporting enhanced phenotyping, forecasting production outcomes, and investigating host-environment interactions (62, 65, 66). Additionally, DTs offer a platform for in silico experimentation, allowing researchers to evaluate scenarios about resource utilization, disease transmission, and climate adaptation with lower ethical and financial risk (67, 68).
Support real-time monitoring and feedback: Digital twins can use machine learning algorithms to monitor and adjust the simulation of physical entities in real time (11, 69).
Predicting scalability and flexibility: Digital twins can be integrated with machine learning operations (MLOps) platforms in complex production environments to enable more intelligent and automated decision-making. DT can commence with basic configurations that can progressively be augmented with additional ML models to strengthen their intelligence and autonomy (60, 62).
Reduce costs and improve efficiency: Efficient Digital twins combined with ML algorithms can reduce research costs and improve resource utilization efficiency. This combination can achieve higher responsiveness, predictability, and adaptability by managing the full life cycles of different livestock species, biological processes, and farm practices. Then it can depict a research scene more richly, with more possible interactions and more extended indirect relations that can support a deeper, more precise evaluation of research outputs (70).
Cross-domain applications: The combination of digital twins and ML is not limited to farm production applications; it can also be applied across multiple fields. Simulation constitutes information fusion, as it amalgamates and enhances data from several heterogeneous sources. DT analyses physical twins from diverse viewpoints, using various data sources and evaluating the potential consequences of actions. Information fusion and the ongoing nature of operations illustrate the comprehensive status of past and present system conditions, facilitating the projection of future states (71).
Environmental control: Digital twins can simulate various research conditions and environments, and machine learning can adjust control parameters in the actual environment based on these simulations to improve animal comfort and production efficiency (72).
Also, there is promising potential for DT application in research by integrating physical research with a robust virtual model to extend research results and broaden the scope of physical research; while ML provides digital twins with intelligent analysis and prediction capabilities, digital twins afford ML with a highly detailed, up-to-date data environment. This DT fusion will bring more innovation and change to livestock research in the future (Table 5).
Table 5
| Animal species | Study | Studied variable | Marker | References | DT upgrading potential |
|---|---|---|---|---|---|
| Dairy cattle | Developing an artificial neural network for the early prediction of subclinical ketosis during lactation. | Subclinical Ketosis | 50,025 and 10,005 SNPs | (185) | Predict the effect on lactation performance and yield, and forecast culled animals. |
| Beef cattle (Nellore) | Utilizing machine learning to find small subsets of biologically significant genes for classifying animals into High Feed Efficiency and Low Feed Efficiency categories. | Feed efficiency | 16,423 genes | (186) | Rearranging this subset or investigating new gene subsets to predict their effect on the traits. |
| Goat | Efficiently oversee the health and welfare of their goats, thereby enhancing living circumstances and augmenting dairy output. | Animal behavior | Goat activity | (187) | Mimic population behavior changes and track their effect on herd performance. |
| Dairy cattle | Image processing algorithms and the YOLOv8 model facilitate the real-time, non-invasive monitoring of feeding periods. | Feed utilization efficiency | Feeding pattern | (188) | Simulate different feeding strategies and forecast productivity and economics. |
| Cattle and Buffalo | Forecasting lumpy skin disease infection | LSD occurrence | Meteorological and geological attributes | (189) | Stimulate assessment of infection virulence and its effects on productivity, and estimate potential economic losses in specific regions. |
| (Sheep) (Harnai) | Predicting live weight at the post-weaning period. | Growth performance | Body biometric parameters and sex factor. | (190) | Predicting the Economics of the Production |
| Pigs | Infection prediction in swine populations, both seven and 30 days in advance | Infection Outbreak | Nearby farm density, historical test rates, piglet inventory, feed consumption during gestation, and wind speed and direction. | (95) | Simulate the evaluation for disease prevention and mitigation strategies. |
| Cattle | 16S rRNA sequencing and machine learning methodologies identified a dozen species as taxonomic indicators for distinguishing infection. | The Mycobacterium avium disease state. | Fecal microbiota | (191) | Investigate the effects of microbial dysbiosis on pathogenic microbes. The Gut-host interaction |
| Chicken | Investigate antimicrobial resistance profiles across multiple chicken farms and abattoirs. | Antimicrobial resistance genes | E. coli | (192) | Forecast the intensity of ARGs under different environmental conditions and correlate ARGs with different microbiomes. |
| In-vitro fermentation | Prediction of Methane Production from in vitro Ruminal Fermentation | Methane | Volatile fatty acids | (193) | Introducing a cross-species Virtual rumen fermentation model |
| Water-Deer Water Buffalo Sheep Buffalo | Combined network analysis and interpretable machine learning reveal | Environmental adaptability | Microbial genomes | (194) | Predicting which pathogen species are most likely to emerge in the future |
| Wild-Livestock | ML demonstrates one approach to planning for and preventing disease emergence in livestock. | Pathogen-host associations at the wildlife–livestock interface | Bacterial association | (195) |
Examples of ML studies and the potential of digital twin to develop the results outcomes.
Herein, a meaningful question will be posed: How can ML-DT transform livestock science, and what can be introduced into the field of research?
For example, if a physical experiment investigating the maternal nutrition effect on reproductive physiology and hormonal regulation is piloted at this stage, the results will investigate a single research question. But what if we want to explore the further effects on offspring growth virtually? Can we deploy an ML-DT module to predict colostrum quality and offspring immune response using prior data linking hormonal effects to colostrum quality and offspring performance? Figure 4. The next stage can be developed by integrating multiple DT models to predict birth weight and, subsequently, mature body weight, average daily gain, and feed efficiency. In this hybrid research environment (physical-virtual), researchers can extend physical research findings using a virtual assistant, which we can call the virtual lab. Although model fitness for the virtual part will be challenging and critical, the model can produce more results with fewer physical resources, less time, and fewer specialized research environments. Moreover, the central role of this concept, “co-valorisation,” is to connect previous scientific work and data records with new golden opportunities to launch a contemporary era with powerful outputs and findings well positioned to reshape livestock production and research.
Challenges faced by ML-DT in augmentation and applications. To fully expand ML-DT integration through Smart Livestock Farming (SLF) across livestock species, a policy that encourages substantial equipment investment is critical. Also, data produced by SLF can be sensitive, necessitating robust legal measures to ensure information security and enhance trust in data sharing. Establishing an SLF big data recirculation center is essential, as individual farms often lack the capacity to process large volumes of data. Additionally, integrating public and farm data with AI and ML can leverage SLF big data to create digital twins, potentially increasing the economic value of the livestock industry through advanced simulations (73).
In addition to data accuracy, data synchronization, real-time analytics, computational load, and calibration issues, model suitability is a critical factor in building confidence in these models. Regarding farm-applicability constraints such as cost, scalability, hardware requirements, farm size, and on-farm feasibility, they clash with farmer acceptance and uncertainties, which may hinder wider deployment. Therefore, the transition from ML models to partially ML-DT-integrated and fully integrated models, adaptable across different research and farm environments, may be a key gateway to transforming livestock production and research (74).
However, despite the previous challenges and the limited number of proposed integrated models, most of which are at the conceptual stage, the gradual adoption and transition from physical to virtual, coupled with a multi-model approach, may be highly promising for avoiding future obstacles.
Figure 4
6 Conclusion
Integrating ML with DT into livestock production research, from predicting growth performance to understanding the relationships between health, behaviors, and different physiological statuses, to biological simulation models, can uncover hidden insights. Although ML-DT integration can completely transform the nature of outputs from production and research data, the integration models remain conceptual and limited due to data governance and resource utilization measures. There is an urgent need for more applications across both research and production plateaus, considering the variation in species, data types, and sources, and model selection and suitability. Such cross–domain models can reduce the time and resources required for more in-depth livestock research and production, enabling seamless transitions between physical/virtual and virtual/virtual environments. Although the early findings are promising and open the door to co-valorizing research data, these applications need to be comprehensively designed and integrated to solve sustainable livestock science and practices challenges.
Statements
Author contributions
MA: Conceptualization, Data curation, Formal analysis, Investigation, Supervision, Visualization, Writing – original draft, Writing – review & editing. SI: Investigation, Writing – review & editing. MEA: Data curation, Investigation, Methodology, Validation, Writing – review & editing. JA: Formal analysis, Investigation, Project administration, Resources, Writing – review & editing. FA: Data curation, Formal analysis, Funding acquisition, Investigation, Project administration, Resources, Writing – review & editing.
Funding
The author(s) declared that financial support was received for this work and/or its publication.
Acknowledgments
The authors would like to thank the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support (QU-APC-2026). Also, the authors acknowledge Professors Ahmed Ezzat Ahmed for his valuable and in-depth guidance and Professor Jiang Xunping for hosting the discussion of this work.
Conflict of interest
The author(s) declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Generative AI statement
The author(s) declared that generative AI was not used in the creation of this manuscript.
Any alternative text (alt text) provided alongside figures in this article has been generated by Frontiers with the support of artificial intelligence and reasonable efforts have been made to ensure accuracy, including review by the authors wherever possible. If you identify any issues, please contact us.
Correction note
A correction has been made to this article. Details can be found at: 10.3389/fvets.2026.1810873.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1.
DangCChoiTLeeSLeeSAlamMParkMet al. Machine learning-based live weight estimation for Hanwoo Cow. Sustainability. (2022) 14:12661. doi: 10.3390/su141912661
2.
GreenwoodPLKardailskyIBadgeryWBBishop-HurleyGJ. 381 Smart farming for extensive grazing ruminant production systems. J Anim Sci. (2020) 98:139–40. doi: 10.1093/jas/skaa278.257
3.
DŽermeikaiteKKrištolaityteJGrigeSGirdauskaiteAŠertvytyteGLembovičiuteGet al. Creation of machine learning models trained on multimodal physiological, behavioural, blood biochemical, and milk composition parameters for the identification of lameness in dairy cows. Biosensors. (2025) 15:722. doi: 10.3390/bios15110722
4.
YildizBI. Comparative performance of convolutional neural network models in wing morphometric classification of honey bee populations across Europe. Kafkas Üniv Vet Fak Derg. (2025) 31:653–9. doi: 10.9775/kvfd.2025.34544
5.
IssaSAliMEWangQAl-SaeedFAAbdelrahmanM. End-to-end deep SAE-DNN model for predicting Egyptian buffalo calf sex, weight, and daily milk yield. Trop Anim Health Prod. (2025) 57:512. doi: 10.1007/s11250-025-04752-6
6.
WełeszczukJKosińska-SelbiBCholewińskaP. Prediction of Polish Holstein's economical index and calving interval using machine learning. Livest Sci. (2022) 264:105039. doi: 10.1016/j.livsci.2022.105039
7.
KresovaSHessS. Identifying the determinants of regional raw milk prices in Russia using machine learning. Agriculture. (2022) 12:1006. doi: 10.3390/agriculture12071006
8.
YuanJHaoJLiuMWuDLiJ. A dynamic ensemble learning approach with spectral clustering for beef and lamb prices prediction. Procedia Comput Sci. (2022) 214:1190–7. doi: 10.1016/j.procs.2022.11.295
9.
RahmanMMandalAGayariIBidyalaxmiKSarkarDAlluTet al. Prospect and scope of artificial neural network in livestock farming: a review. Biol Rhythm Res. (2023) 54:249–62. doi: 10.1080/09291016.2022.2139389
10.
JeongD-YJoS-KLeeI-BShinHKimJ-G. Digital twin application: making a virtual pig house toward digital livestock farming. IEEE Access. (2023) 11:121592–602. doi: 10.1109/ACCESS.2023.3313618
11.
Escribà-GelonchMLiangSvan SchalkwykPFiskILongNVDHesselV. Digital twins in agriculture: orchestration and applications. J Agric Food Chem. (2024) 72:10737–52. doi: 10.1021/acs.jafc.4c01934
12.
Brown-BrandlTMTaoJ. ASAS-NANP Symposium: mathematical modeling in animal nutrition: harnessing real-time data and digital twins for precision livestock farming. J Anim Sci. (2025) 103:skaf138. doi: 10.1093/jas/skaf138
13.
DongRZhaoG. Predicting in vitro rumen VFA production using CNCPS carbohydrate fractions with multiple linear models and artificial neural networks. PLoS ONE. (2014) 9:e116290. doi: 10.1371/journal.pone.0116290
14.
HanXLinZClarkCVuceticBLomaxSAI. Based digital twin model for cattle caring. Sensors. (2022) 22:7118. doi: 10.3390/s22197118
15.
Taheri-GaravandAFatahiSOmidMMakinoY. Meat quality evaluation based on computer vision technique: a review. Meat Sci. (2019) 156:183–95. doi: 10.1016/j.meatsci.2019.06.002
16.
MajumdarKVermaAKKathpaliaKVSamajderPPrabhakarPK. Utilizing ndustry 5.0 technologies to improve food production and promote sustainability in agriculture. In:DuttaPKHamadAHaghiAKPrabhakarPK, editors. Sustainable Development Goals Series. Cham: Springer (2025). p. 143–53.
17.
GarcíaRAguilarJToroMPintoARodríguezP. A systematic literature review on the use of machine learning in precision livestock farming. Comput Electron Agric. (2020) 179:105826. doi: 10.1016/j.compag.2020.105826
18.
SarkerIH. AI-based modeling: techniques, applications and research issues towards automation, intelligent and smart systems. SN Comput Sci. (2022) 3:158. doi: 10.1007/s42979-022-01043-x
19.
RanzatoGAernoutsBLoraIAdriaensIBen AbdelkrimAGoteMJet al. Comparison of 3 mathematical models to estimate lactation performance in dairy cows. J Dairy Sci. (2024) 107:6888–901. doi: 10.3168/jds.2023-24224
20.
Canul-SolísJRPortillo-SalgadoRGarcía-HerreraRACastillo-GallegosECastillo-SanchezLECamacho-PérezEet al. Comparison of mathematical models to estimate live weight through heart girth in growing Pelibuey sheep. Rev Colomb Ciencias Pecu. (2022) 36:89–97. doi: 10.17533/udea.rccp.v36n2a4
21.
MenendezHMBrennanJRGaillardCEhlertKQuintanaJNeethirajanSet al. ASAS-NANP symposium: mathematical modeling in animal nutrition: opportunities and challenges of confined and extensive precision livestock production. J Anim Sci. (2022) 100:skac160. doi: 10.1093/jas/skac160
22.
EllisJJacobsMDijkstraJvan LaarHCantJTulpanDet al. The role of mechanistic models in the era of big data and intelligent computing. Adv Anim Biosci. (2019) 10:286. Available online at: https://www.cambridge.org/core/services/aop-cambridge-core/content/view/4E046D128510CA654ADDA96170E0C84D/S2040470019000025a.pdf/proceedings_of_the_9th_workshop_on_modelling_nutrient_digestion_and_utilization_in_farm_animals_modnut.pdf#page=14
23.
EllisJLJacobsMDijkstraJvan LaarHCantJPTulpanDet al. Review: synergy between mechanistic modelling and data-driven models for modern animal production systems in the era of big data. Animal. (2020) 14:s223–37. doi: 10.1017/S1751731120000312
24.
EidFEElmarakebyHAChanYAFornelosNElHefnawiMVan AllenEMet al. Systematic auditing is essential to debiasing machine learning in biology. Commun Biol. (2021) 4:183. doi: 10.1038/s42003-021-01674-5
25.
LeishmanEMYouJFerreiraNTAdamsSMTulpanDZuidhofMJet al. Review: when worlds collide – poultry modeling in the ‘Big Data' era. Animal. (2023) 17:100874. doi: 10.1016/j.animal.2023.100874
26.
GrzesiakWZaborskiDPlucińskiMJedrzejczak-SilickaMPilarczykRSablikP. The use of selected machine learning methods in dairy cattle farming: a review. Animals. (2025) 15:2033. doi: 10.3390/ani15142033
27.
KuzminVAOrekhovDAAidievABTsyganovAV. Principles of mathematical modeling of infectious diseases in the zone of interaction of wildlife and livestock. Leg Regul Vet Med. (2025) 42–7. doi: 10.52419/issn2782-6252.2025.3.42
28.
TedeschiLOCavalcantiLFLFonsecaMAHerreroMThorntonPK. The evolution and evaluation of dairy cattle models for predicting milk production: an agricultural model intercomparison and improvement project (AgMIP) for livestock. Anim Prod Sci. (2014) 54:2052–67. doi: 10.1071/AN14620
29.
RossSWangHZhengHYanTShiraliM. Approaches for predicting dairy cattle methane emissions: from traditional methods to machine learning. J Anim Sci. (2024) 102:skae219. doi: 10.1093/jas/skae219
30.
de Freitas CurtiPSelliAPintoDLMerlos-RuizAde Carvalho BalieiroJCVenturaRV. Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview. Anim Reprod. (2023) 20:e20230077. doi: 10.1590/1984-3143-ar2023-0077
31.
WangXShiSAli KhanMYZhangZZhangY. Improving the accuracy of genomic prediction in dairy cattle using the biologically annotated neural networks framework. J Anim Sci Biotechnol. (2024) 15:87. doi: 10.1186/s40104-024-01044-1
32.
WangXZhangZDuHPfeifferCMészárosGDingX. Predictive ability of multi-population genomic prediction methods of phenotypes for reproduction traits in Chinese and Austrian pigs. Genet Sel Evol. (2024) 56:49. doi: 10.1186/s12711-024-00915-5
33.
DayoubMShnaigatSTarawnehRAAl-YacoubANAl-BarakehFAl-NajjarK. Enhancing animal production through smart agriculture: possibilities, hurdles, resolutions, and advantages. Ruminants. (2024) 4:22–46. doi: 10.3390/ruminants4010003
34.
BaoJXieQ. Artificial intelligence in animal farming: a systematic literature review. J Clean Prod. (2022) 331:129956. doi: 10.1016/j.jclepro.2021.129956
35.
WangXSiJWangYFangLZhangZZhangY. Integrating gene expression data via weighted multiple kernel ridge regression improved accuracy of genomic prediction. Genet Sel Evol. (2025) 57:48. doi: 10.1186/s12711-025-00997-9
36.
AlemuSWLopdellTJTrevartonAJSnellRGLittlejohnMDGarrickDJ. Comparison of genomic prediction accuracies in dairy cattle lactation traits using five classes of functional variants versus generic SNP. Genet Sel Evol. (2025) 57:20. doi: 10.1186/s12711-025-00966-2
37.
ZhengWZhangQHeJHanBZhangQSunD. Comparative evaluation of SNP-weighted, Bayesian, and machine learning models for genomic prediction in Holstein cattle. BMC Genom. (2025) 26:1–13. doi: 10.1186/s12864-025-12218-0
38.
YangJCalusMPLWientjesYCJMeuwissenTHEDuenkP. Incorporating information of causal variants in genomic prediction using GBLUP or machine learning models in a simulated livestock population. J Anim Sci Biotechnol. (2025) 16:118. doi: 10.1186/s40104-025-01250-5
39.
LamannaMBovoMCavalliniD. Wearable collar technologies for dairy cows: a systematized review of the current applications and future innovations in precision livestock farming. Animals. (2025) 15:458. doi: 10.3390/ani15030458
40.
KaurDVirkAK. Smart neck collar: IoT-based disease detection and health monitoring for dairy cows. Discov Internet Things. (2025) 5:12. doi: 10.1007/s43926-025-00109-5
41.
BouchonMChanelHRouchezLMartinBCoppaM. Method: using a commercial precision livestock farming activity collar to automatically record and classify dairy cow activity at pasture. Animal. (2025) 4:100099. doi: 10.1016/j.anopes.2025.100099
42.
BernabucciGEvangelistaCGirottiPViolaPSpinaRRonchiBet al. Precision livestock farming: an overview on the application in extensive systems. Ital J Anim Sci. (2025) 24:859–84. doi: 10.1080/1828051X.2025.2480821
43.
Suárez-VegaAFrutosPGutiérrez-GilBEsteban-BlancoCToralPGArranzJJet al. Feed efficiency in dairy sheep: an insight from the milk transcriptome. Front Vet Sci. (2023) 10:1122953. doi: 10.3389/fvets.2023.1122953
44.
TuyishimeKAdewusiMA. Data-driven prediction of cattle weight gain for evaluating key growth factors with machine learning approaches. Discov Comput. (2025) 28:275. doi: 10.1007/s10791-025-09798-6
45.
ShiRLouWDucroBvan der LindenAMulderHAOosting SJ LiSet al. Predicting nitrogen use efficiency, nitrogen loss and dry matter intake of individual dairy cows in late lactation by including mid-infrared spectra of milk samples. J Anim Sci Biotechnol. (2023) 14:8. doi: 10.1186/s40104-022-00802-3
46.
GuevaraLCastro-EspinozaFFernandesAMBenaoudaMMuñoz-BenítezALdel Razo-RodríguezOEet al. Application of machine learning algorithms to describe the characteristics of dairy sheep lactation curves. Animals. (2023) 13:2772. doi: 10.3390/ani13172772
47.
KoşkanÖErginMKöknarogluH. Application of the different machine learning algorithms to predict dry matter intake in feedlot cattle. Tarim Bilim Derg. (2025) 31:91–9. doi: 10.15832/ankutbd.1375383
48.
ChenXZhengHWangHYanT. Can machine learning algorithms perform better than multiple linear regression in predicting nitrogen excretion from lactating dairy cows. Sci Rep. (2022) 12:12478. doi: 10.1038/s41598-022-16490-y
49.
DebNCBasakJKKarkiSArulmozhiEKangDYTamrakarNet al. Prediction of digestible energy requirement in growing finishing stage of pigs using machine learning models. J Agric Food Res. (2025) 19:101700. doi: 10.1016/j.jafr.2025.101700
50.
SuJKongXWangWXieQWangCTanBet al. Weaning performance prediction in lactating sows using machine learning, for precision nutrition and intelligent feeding. Anim Nutr. (2025) 21:222–33. doi: 10.1016/j.aninu.2025.01.007
51.
WangXShiSWangGLuoWWeiXQiuAet al. Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs. J Anim Sci Biotechnol. (2022) 13:60. doi: 10.1186/s40104-022-00708-0
52.
LinQFengXLiTPanXDiaoSGaoYet al. Integrating meta-analysis of genome-wide association study with Pig Genotype-Tissue Expression resources uncovers the genetic architecture for age at first farrowing in pigs. Anim Res One Heal. (2024) 2:238–49. doi: 10.1002/aro2.62
53.
WuPWangJChenXWangTGuoZDiaoSet al. Optimization of genomic breeding value prediction for growth traits in Rongchang pigs through machine learning techniques. Mach Learn with Appl. (2025) 22:100747. doi: 10.1016/j.mlwa.2025.100747
54.
WangJTiezziFHuangYMalteccaCJiangJ. Benchmarking of feed-forward neural network models for genomic prediction of quantitative traits in pigs. Front Genet. (2025) 16:1618891. doi: 10.3389/fgene.2025.1618891
55.
RuchayAGritsenkoSErmolovaEBochkarevAErmolovSGuoHet al. Comparative study of machine learning methods for predicting live weight of Duroc, Landrace, and Yorkshire Pigs. Animals. (2022) 12:1152. doi: 10.3390/ani12091152
56.
EskiogluKYildizBIOzdemirD. Development and evaluation of machine learning models for predicting chicken meat production. Mediterr Agric Sci. (2025) 38:85–90. doi: 10.29136/mediterranean.1622702
57.
NeethirajanS. The role of sensors, big data and machine learning in modern animal farming. Sens Bio-Sensing Res. (2020) 29:100367. doi: 10.1016/j.sbsr.2020.100367
58.
RiaboffLShallooLSmeatonAFCouvreurSMadouasseAKeaneMT. Predicting livestock behaviour using accelerometers: a systematic review of processing techniques for ruminant behaviour prediction from raw accelerometer data. Comput Electron Agric. (2022) 192:106610. doi: 10.1016/j.compag.2021.106610
59.
AzodiCBBolgerEMcCarrenARoantreeM. de los Campos G, Shiu SH. Benchmarking parametric and machine learning models for genomic prediction of complex traits. G3 Genes Genom Genet. (2019) 9:3691–702. doi: 10.1534/g3.119.400498
60.
LiuYFengJLuJZhouS. A review of digital twin capabilities, technologies, and applications based on the maturity model. Adv Eng Informatics. (2024) 62:102592. doi: 10.1016/j.aei.2024.102592
61.
IslamMRSubramaniamMHuangPC. Image-based deep learning for smart digital twins: a review. Artif Intell Rev. (2025) 58:146. doi: 10.1007/s10462-024-11002-y
62.
ZhangRZhuHChangQMaoQ. A comprehensive review of digital twins technology in agriculture. Agric. (2025) 15:903. doi: 10.3390/agriculture15090903
63.
LegallNSalvadorLCM. Selective sweep sites and SNP dense regions differentiate Mycobacterium bovis isolates across scales. Front Microbiol. (2022) 13:787856. doi: 10.3389/fmicb.2022.787856
64.
AndersonCL. 2 metagenomic detection and binning of plasmids for an improved understanding of the risk of antimicrobial resistance gene transfer events. J Anim Sci. (2023) 101:62–62. doi: 10.1093/jas/skad341.068
65.
NeethirajanS. Digital phenotyping: a game changer for the broiler industry. Animals. (2023) 13:2585. doi: 10.3390/ani13162585
66.
PeladarinosNPiromalisDCheimarasVTserepasEMunteanuRAPapageorgasP. Enhancing smart agriculture by implementing digital twins: a comprehensive review. Sensors. (2023) 23:7128. doi: 10.3390/s23167128
67.
GargPVanamamalaiVKJaliISharmaS. In silico prediction of the animal susceptibility and virtual screening of natural compounds against SARS-CoV-2: molecular dynamics simulation based analysis. Front Genet. (2022) 13:906955. doi: 10.3389/fgene.2022.906955
68.
MaddenJCEnochSJPainiACroninMTD. A review of in silico tools as alternatives to animal testing: principles, resources and applications. ATLA Altern to Lab Anim. (2020) 48:146–72. doi: 10.1177/0261192920965977
69.
SajadiehSMMDo NohS. From simulation to autonomy: reviews of the integration of artificial intelligence and digital twins. Int J Precis Eng Manuf Green Technol. (2025) 12:1597–628. doi: 10.1007/s40684-025-00750-z
70.
BanhaziTBanhaziATikaszIEPalotaySMallimgerKNeubauerTet al. Facilitating PLF technology adoption in the pig and poultry industries. Stud Agric Econ. (2024) 126:43–9. doi: 10.7896/j.2725
71.
SymeonakiEMaraveasC. Arvanitis KG. Recent advances in digital twins for agriculture 50: applications and open issues in livestock production systems. Appl Sci. (2024) 14:686. doi: 10.3390/app14020686
72.
ArulmozhiEDebNCTamrakarNKangDYKangMYKookJet al. From reality to virtuality: revolutionizing livestock farming through digital twins. Agric. (2024) 14:2231. doi: 10.3390/agriculture14122231
73.
LeeSHLimKSLeeHHeoJKimJKimSHet al. The vision of big data recirculation for smart livestock farming in South Korea. J Anim Sci Technol. (2025) 67:303–13. doi: 10.5187/jast.2025.e21
74.
PurcellWNeubauerT. Digital twins in agriculture: a state-of-the-art review. Smart Agric Technol. (2023) 3:100094. doi: 10.1016/j.atech.2022.100094
75.
FuentesSViejoCGCullenBTongsonEChauhanSSDunsheaFR. Artificial intelligence applied to a robotic dairy farm to model milk productivity and quality based on cow data and daily environmental parameters. Sensors. (2020) 20:2975. doi: 10.3390/s20102975
76.
AlvesAACEspigolanRBresolinTCostaRMFernandes JúniorGAVentura RVet al. Genome-enabled prediction of reproductive traits in Nellore cattle using parametric models and machine learning methods. Anim Genet. (2021) 52:32–46. doi: 10.1111/age.13021
77.
TedeschiLO. ASN-ASAS SYMPOSIUM. FUTURE of DATA ANALYTICS in NUTRITION: Mathematical modeling in ruminant nutrition: approaches and paradigms, extant models, and thoughts for upcoming predictive analytics. J Anim Sci. (2019) 97:1921–44. doi: 10.1093/jas/skz092
78.
LeCunYBengioYHintonG. Deep learning. Nature. (2015) 521:436–44. doi: 10.1038/nature14539
79.
KivançSGSenBNarFOkAÖ. Reducing model complexity in neural networks by using pyramid training approaches. Appl Sci. (2024) 14:5898. doi: 10.3390/app14135898
80.
MiaNSarkerTHalimMAlamAAliMRahmanMet al. Machine learning overview and its application in the livestock industry. Meat Res. (2025) 5:1–10. doi: 10.55002/mr.5.1.109
81.
SetiawanAUtamiE. Predicting the weight of livestock using machine learning. Int Conf Artif Intell Mechatronics Syst AIMS 2024. Bandung: IEEE (2024). p. 1–6. doi: 10.1109/AIMS61812.2024.10512610
82.
SallehSMDanielssonRKronqvistC. Using machine learning methods to predict dry matter intake from milk mid-infrared spectroscopy data on Swedish dairy cattle. J Dairy Res. (2023) 90:5–8. doi: 10.1017/S0022029923000171
83.
WenJYangSZhuJLiuATanQRaoY. Identifying feature genes of chickens with different feather pecking tendencies based on three machine learning algorithms and WGCNA. Front Vet Sci. (2024) 11:1508397. doi: 10.3389/fvets.2024.1508397
84.
LiuBLiuHTuJXiaoJYangJHeXet al. An investigation of machine learning methods applied to genomic prediction in yellow-feathered broilers. Poult Sci. (2025) 104:104489. doi: 10.1016/j.psj.2024.104489
85.
LiXChenXWangQYangNSunC. Integrating bioinformatics and machine learning for genomic prediction in chickens. Genes. (2024) 15:690. doi: 10.3390/genes15060690
86.
TanXHuangMJinYLiJDongJWangD. Deciphering the gene expression and alternative splicing basis of muscle development through interpretable machine learning models. Biology. (2025) 14:1059. doi: 10.3390/biology14081059
87.
ChenHDouDLuMLiuXChangCZhangFet al. Optimization of genomic breeding value estimation model for abdominal fat traits based on machine learning. Animals. (2025) 15:2843. doi: 10.3390/ani15192843
88.
ImadaJArango-SabogalJCBaumanCRocheSKeltonD. Comparison of machine learning tree-based algorithms to predict future paratuberculosis ELISA results using repeat milk tests. Animals. (2024) 14:1113. doi: 10.3390/ani14071113
89.
GirdauskaiteAGrigeSDŽermeikaiteKKrištolaityteJMalašauskieneDTelevičiusMet al. Supervised machine learning approaches for early detection of metabolic and udder health disorders in dairy cows using sensor-derived data. Front Vet Sci. (2025) 12:1726719. doi: 10.3389/fvets.2025.1726719
90.
HamadaniAGanaiNA. Artificial intelligence algorithm comparison and ranking for weight prediction in sheep. Sci Rep. (2023) 13:13242. doi: 10.1038/s41598-023-40528-4
91.
EmsenEOdevciBBKutluca KorkmazM. Using machine learning to identify key predictors of maternal success in sheep for improved lamb survival. Front Anim Sci. (2025) 6:1543490. doi: 10.3389/fanim.2025.1543490
92.
Salgado-LópezPCasellasJSolar DiazIRathjeTGasaJSolà-OriolD. Applicability of machine learning methods for classifying lightweight pigs in commercial conditions. Transl Anim Sci. (2024) 8:txae171. doi: 10.1093/tas/txae171
93.
SajidSSHuGHardingJCSDyckMKFortinFPlastowGSet al. Early identification of individual nursery pigs at risk of requiring health treatment using machine learning. J Anim Sci. (2025) 30:skaf303. doi: 10.1093/jas/skaf303
94.
MagalhãesESZhangDMouraCAATrevisanGHoltkampDJLópezWAet al. Development of a pig wean-quality score using machine-learning algorithms to characterize and classify groups with high mortality risk under field conditions. Prev Vet Med. (2024) 232:106327. doi: 10.1016/j.prevetmed.2024.106327
95.
HalevAMartínez-LópezBClavijoMGonzalez-CrespoCKimJHuangCet al. Infection prediction in swine populations with machine learning. Sci Rep. (2023) 13:17738. doi: 10.1038/s41598-023-43472-5
96.
JiXLiQGuoKMaWLiMXuZet al. Machine learning-based method for pig weight estimation and the PIGRGB-weight dataset. Agriculture. (2025) 15:814. doi: 10.3390/agriculture15080814
97.
MlubaHSAtifOLeeJParkDChungY. Pattern mining-based pig behavior analysis for health and welfare monitoring. Sensors. (2024) 24:2185. doi: 10.3390/s24072185
98.
PirompudPSivapirunthepPPunyapornwithayaVChaosapC. Predictive modeling of bruising in broiler chickens using machine learning algorithms. Poult Sci. (2025) 104:105756. doi: 10.1016/j.psj.2025.105756
99.
SaadatHBTorshiziRVManafiazarGMasoudiAAEhsaniAShahinfarS. An initial investigation into the use of machine learning methods for prediction of carcass component yields in F2 broiler chickens. Anim Prod Sci. (2024) 64:AN23129. doi: 10.1071/AN23129
100.
JiHXuYTengG. Predicting egg production rate and egg weight of broiler breeders based on machine learning and Shapley additive explanations. Poult Sci. (2025) 104:104458. doi: 10.1016/j.psj.2024.104458
101.
FahrurroziI. Wahyono, Sari Y, Sari AK, Usuman I, Ariyadi B. Integrating random forest model and internet of things-based sensor for smart poultry farm monitoring system Indones. J Electr Eng Comput Sci. (2024) 33:1283–92. doi: 10.11591/ijeecs.v33.i2.pp1283-1292
102.
SuhendraLinHTAdiVSKHerawatiA. Feature-driven optimization for growth and mortality prevention in poultry farms. Poult Sci. (2025) 104:105869. doi: 10.1016/j.psj.2025.105869
103.
do Nascimento AmorimMTurcoSHNdos Santos CostaDFerreiraIJSda SilvaWPSabinoALCet al. Discrimination of ingestive behavior in sheep using an electronic device based on a triaxial accelerometer and machine learning. Comput Electron Agric. (2024) 218:108657. doi: 10.1016/j.compag.2024.108657
104.
de OliveiraFMFerrazPFPe Silva FerrazGAPereiraMNBarbariMRossiG. Prediction of body mass of dairy cattle using machine learning algorithms applied to morphological characteristics. Animals. (2025) 15:1054. doi: 10.3390/ani15071054
105.
SatołaASatołaK. Performance comparison of machine learning models used for predicting subclinical mastitis in dairy cows: Bagging, boosting, stacking, and super-learner ensembles versus single machine learning models. J Dairy Sci. (2024) 107:3959–72. doi: 10.3168/jds.2023-24243
106.
SiddiqueAPandaSSKhanSDarganSTLewisSCarterIet al. Innovations in animal health: artificial intelligence-enhanced hematocrit analysis for rapid anemia detection in small ruminants. Front Vet Sci. (2024) 11:1493403. doi: 10.3389/fvets.2024.1493403
107.
Torres-ChableOMTirinkCParra-CortésRIDelgadoMÁGMartínezIVGomez-VazquezAet al. Classification of FAMACHA© scores with support vector machine algorithm from body condition score and hematological parameters in Pelibuey sheep. Animals. (2025) 15:737. doi: 10.3390/ani15050737
108.
SrivalliMRVishnuNKKanchanaV. Teat and udder disease detection on cattle using machine learning. In: 2022 Int Conf Signal Inf Process IConSIP 2022. Pune: IEEE (2022). p. 1–5.
109.
ChadhaADaraRPearlDLGillisDRosendalTPoljakZ. Classification of porcine reproductive and respiratory syndrome clinical impact in Ontario sow herds using machine learning approaches. Front Vet Sci. (2023) 10:1175569. doi: 10.3389/fvets.2023.1175569
110.
GhoshPMandalSN. PigB: intelligent pig breeds classification using supervised machine learning algorithms. Int J Artif Intell Soft Comput. (2022) 7:242. doi: 10.1504/IJAISC.2022.126345
111.
YanHWuYBoYHanYRenG. Study on the impact of LDA preprocessing on pig face identification with SVM. Animals. (2025) 15:231. doi: 10.3390/ani15020231
112.
XuJZhouSXuAYeJZhaoA. Automatic scoring of postures in grouped pigs using depth image and CNN-SVM. Comput Electron Agric. (2022) 194:106746. doi: 10.1016/j.compag.2022.106746
113.
LuoYChenYAbdul MajeedAPP. Optimizing poultry disease classification: a feature-based transfer learning approach. Smart Agric Technol. (2025) 10:100856. doi: 10.1016/j.atech.2025.100856
114.
SupriyantoERIsnantoRPurnomoSH. Developing chicken health classification model using a convolutional neural network and support vector machine (CNN-SVM) approach. Ing Syst Inf. (2024) 29:2525–32. doi: 10.18280/isi.290637
115.
NaeemMJiaZWangJPoudelSManjankattilSAdhikariYet al. Advancements in machine learning applications in poultry farming: a literature review. J Appl Poult Res. (2025) 34:100602. doi: 10.1016/j.japr.2025.100602
116.
ShwethaVMaddodiBSLaxmiVKumarAShrivastavaS. Latest trend and challenges in machine learning– and deep learning–based computational techniques in poultry health and disease management: a review. J Comput Networks Commun. (2024) 2024:1–16. doi: 10.1155/2024/8674250
117.
BauerEAJagusiakW. The use of multilayer perceptron artificial neural networks to detect dairy cows at risk of Ketosis. Animals. (2022) 12:332. doi: 10.3390/ani12030332
118.
Vargas-Bello-PérezEEspinoza-SandovalORGonzalez RonquilloMAngeles HernandezJCChay-CanulAJLee-RangelHAet al. The role of artificial intelligence in Latin American ruminant production systems. Anim Front. (2024) 14:23–32. doi: 10.1093/af/vfae034
119.
KozakliÖCeyhanANoyanM. Comparison of machine learning algorithms and multiple linear regression for live weight estimation of Akkaraman lambs. Trop Anim Health Prod. (2024) 56:250. doi: 10.1007/s11250-024-04049-0
120.
TryhubaAMudrykKTryhubaIKotsylovskyiMSorokinDBezaltychnaOet al. Models for sustainable management of livestock waste based on neural network architectures. Sci Rep. (2025) 15:28082. doi: 10.1038/s41598-025-13150-9
121.
WangXZhouJJiangRWangYZhangYWuRet al. Development of an alternative in vitro rumen fermentation prediction model. Animals. (2024) 14:289. doi: 10.3390/ani14020289
122.
ShadpourSChudTCSHailemariamDOliveiraHRPlastowGStothardPet al. Predicting dry matter intake in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks. J Dairy Sci. (2022) 105:8257–71. doi: 10.3168/jds.2021-21297
123.
Fonseca PA deSSuarez-VegaAEsteban-BlancoCMarinaHPelayoRGutiérrez-GilBet al. Integration of epigenomic and genomic data to predict residual feed intake and the feed conversion ratio in dairy sheep via machine learning algorithms. BMC Genom. (2025) 26:313. doi: 10.1186/s12864-025-11520-1
124.
DongRSunGYuG. Estimating in vitro ruminal ammonia-N using multiple linear models and artificial neural networks based on the CNCPS nitrogenous fractions of cattle rations with low concentrate/roughage ratios. J Anim Physiol Anim Nutr. (2022) 106:841–53. doi: 10.1111/jpn.13588
125.
LiDYanGLiFLinHJiaoHHanHet al. Optimized machine learning models for predicting core body temperature in dairy cows: enhancing accuracy and interpretability for practical livestock management. Animals. (2024) 14:2724. doi: 10.3390/ani14182724
126.
FreitasLAFerreiraREPAlvesAACDóreaJRRPazCCPRosaGJM. Detection of anemic sheep using ocular conjunctiva images and deep learning algorithms. Livest Sci. (2025) 294:105669. doi: 10.1016/j.livsci.2025.105669
127.
WangLShiHHuQGaoWWangLLaiCet al. Modeling net energy partition patterns of growing-finishing pigs using nonlinear regression and artificial neural networks. J Anim Sci. (2023) 101:skac405. doi: 10.1093/jas/skac405
128.
WuZXuKChenYLiuYSongW. A new prediction model based on deep learning for pig house environment. Sci Rep. (2024) 14:31141. doi: 10.1038/s41598-024-82492-7
129.
OsitanwosuOEHuangQLiangYNwokoyeCH. Automatic measurement and prediction of Chinese Grown Pigs weight using multilayer perceptron neural networks. Sci Rep. (2023) 13:2573. doi: 10.1038/s41598-023-28433-2
130.
NieLLiBDuYJiaoFSongXLiuZ. Deep learning strategies with CReToNeXt-YOLOv5 for advanced pig face emotion detection. Sci Rep. (2024) 14:1679. doi: 10.1038/s41598-024-51755-8
131.
WangZLiQYuQQianWGaoRWangRet al. A review of visual estimation research on live pig weight. Sensors. (2024) 24:7093. doi: 10.3390/s24217093
132.
PengSZhuJLiuZHuBWangMPuS. Prediction of ammonia concentration in a pig house based on machine learning models and environmental parameters. Animals. (2023) 13:165. doi: 10.3390/ani13010165
133.
GuoZYinZLyuYWangYChenSLiYet al. Research on indoor environment prediction of pig house based on OTDBO–TCN–GRU algorithm. Animals. (2024) 14:863. doi: 10.3390/ani14060863
134.
MusabimanaJXieQZhouHZhengPLiuHMaTet al. A lightweight hybrid model for accurate ammonia prediction in pig houses. Smart Agric Technol. (2025) 12:101266. doi: 10.1016/j.atech.2025.101266
135.
RodriguezMRBesteiroROrtegaJAFernandezMDArangoT. Evolution and neural network prediction of CO2 emissions in weaned piglet farms. Sensors. (2022) 22:2910. doi: 10.3390/s22082910
136.
Lev-ronTYitzhakyYHalachmiIDruyanS. Classifying vocal responses of broilers to environmental stressors via artificial neural network. Animal. (2025) 19:101378. doi: 10.1016/j.animal.2024.101378
137.
OliveiraEBAlmeidaLGBRochaDTFurianTQBorgesKAMoraesHLSet al. Artificial neural networks to predict egg-production traits in commercial laying breeder hens. Rev Bras Cienc Avic. (2022) 24:1–10. doi: 10.1590/1806-9061-2021-1578
138.
AdliDNFatyanosaTNAl HudaFSholikinMMSugihartoS. Modelling the growth performance and thermal environment of broiler chicken houses via different machine learning algorithms assisted by a customized Internet of Things. Smart Agric Technol. (2025) 12:101421. doi: 10.1016/j.atech.2025.101421
139.
AmirivojdanANasiriAZhouSZhaoYGanH. ChickenSense: a low-cost deep learning-based solution for poultry feed consumption monitoring using sound technology. AgriEngineering. (2024) 6:2115–29. doi: 10.3390/agriengineering6030124
140.
GharajehZMKuhiHDHossein-ZadehNG. Comparative analysis of classical growth models and artificial neural networks in predicting egg production parameters in three commercial broiler parent stocks. Poult Sci. (2025) 105:106356. doi: 10.1016/j.psj.2025.106356
141.
WangYKangXHeZFengYLiuG. Accurate detection of dairy cow mastitis with deep learning technology: a new and comprehensive detection method based on infrared thermal images. Animal. (2022) 16:100646. doi: 10.1016/j.animal.2022.100646
142.
GuZZhangHHeZNiuK. A two-stage recognition method based on deep learning for sheep behavior. Comput Electron Agric. (2023) 212:108143. doi: 10.1016/j.compag.2023.108143
143.
YuRWeiXLiuYYangFShenWGuZ. Research on automatic recognition of dairy cow daily behaviors based on deep learning. Animals. (2024) 14:458. doi: 10.3390/ani14030458
144.
YadavCSPeixotoAATRufinoLALSilveiraABde AlexandriaAR. Intelligent classifier for identifying and managing sheep and goat faces using deep learning. AgriEngineering. (2024) 6:3586–601. doi: 10.3390/agriengineering6040204
145.
RonyMBaraiDRiadHasanMZ. Cattle external disease classification using deep learning techniques. In: 2021 12th Int Conf Comput Commun Netw Technol ICCCNT 2021. Kharagpur: IEEE (2021). p. 1–7.
146.
BezenREdanYHalachmiI. Computer vision system for measuring individual cow feed intake using RGB-D camera and deep learning algorithms. Comput Electron Agric. (2020) 172:105345. doi: 10.1016/j.compag.2020.105345
147.
HouSWangTQiaoDXuDJWangYFengXet al. Temporal-spatial fuzzy deep neural network for the grazing behavior recognition of herded sheep in triaxial accelerometer cyber-physical systems. IEEE Trans Fuzzy Syst. (2025) 33:338–49. doi: 10.1109/TFUZZ.2024.3398075
148.
LiseuneASalamoneMVan den PoelDvan RanstBHostensM. Predicting the milk yield curve of dairy cows in the subsequent lactation period using deep learning. Comput Electron Agric. (2021) 180:105904. doi: 10.1016/j.compag.2020.105904
149.
VerdeMTFonistoMAmatoFLiccardoAMateraRNegliaGet al. An AI-driven multimodal monitoring system for early mastitis indicators in Italian Mediterranean Buffalo. Sensors. (2025) 25:4865. doi: 10.3390/s25154865
150.
ZhangYYangXLiuYZhouJHuangYLiJet al. A time-series neural network for pig feeding behavior recognition and dangerous detection from videos. Comput Electron Agric. (2024) 218:108710. doi: 10.1016/j.compag.2024.108710
151.
DomunYPedersenLJWhiteDAdeyemiONortonT. Learning patterns from time-series data to discriminate predictions of tail-biting, fouling and diarrhoea in pigs. Comput Electron Agric. (2019) 163:104878. doi: 10.1016/j.compag.2019.104878
152.
XieQWuMBaoJZhengPLiuWLiuXet al. Deep learning-based detection method for pig body temperature using infrared thermography. Comput Electron Agric. (2023) 213:108200. doi: 10.1016/j.compag.2023.108200
153.
HakanssonFJensenDB. Automatic monitoring and detection of tail-biting behavior in groups of pigs using video-based deep learning methods. Front Vet Sci. (2023) 9:1099347. doi: 10.3389/fvets.2022.1099347
154.
CowtonJKyriazakisIPlötzTBacarditJ. A combined deep learning GRU-autoencoder for the early detection of respiratory disease in pigs using multiple environmental sensors. Sensors. (2018) 18:2521. doi: 10.3390/s18082521
155.
ChenCZhuWSteibelJSiegfordJHanJNortonT. Recognition of feeding behaviour of pigs and determination of feeding time of each pig by a video-based deep learning method. Comput Electron Agric. (2020) 176:105642. doi: 10.1016/j.compag.2020.105642
156.
YinJChenYHuangYXiaoD. Analysis and classification of pig health status using hourly activity data: Combining statistical analysis and machine learning. Appl Anim Behav Sci (2025) 282:106488. doi: 10.1016/j.applanim.2024.106488
157.
HuangYLvYXiaoDLiuJTanZLiG. Behavior classification and rhythm analysis of pigs based on wearable sensors. Smart Agric Technol. (2025) 12:101457. doi: 10.1016/j.atech.2025.101457
158.
LiuXZengXChuMLiQLiuG. Deep learning-based temperature detection for group-raised pigs via thermal images. Smart Agric Technol. (2025) 12:101206. doi: 10.1016/j.atech.2025.101206
159.
ChangCLXieBXXuRY. Spatiotemporal analysis using deep learning and fuzzy inference for evaluating broiler activities. Smart Agric Technol. (2024) 9:100534. doi: 10.1016/j.atech.2024.100534
160.
XieBXChangCL. Behavior recognition of a broiler chicken using long short-term memory with convolution neural networks. In: 2022 Int Autom Control Conf CACS 2022.Kaohsiung: IEEE (2022). p. 1–5.
161.
HePChenZHeYChenJHayatKPanJet al. A reliable and low-cost deep learning model integrating convolutional neural network and transformer structure for fine-grained classification of chicken Eimeria species. Poult Sci. (2023) 102:102459. doi: 10.1016/j.psj.2022.102459
162.
LaleyeFAAMousseMA. Attention-based recurrent neural network for automatic behavior laying hen recognition. Multimed Tools Appl. (2024) 83:62443–58. doi: 10.1007/s11042-024-18241-9
163.
NasiriAYoderJZhaoYHawkinsSPradoMGanH. Pose estimation-based lameness recognition in broiler using CNN-LSTM network. Comput Electron Agric. (2022) 197:106931. doi: 10.1016/j.compag.2022.106931
164.
SrivastavaAKPandeyBP. Deep learning based classification of poultry disease. Int J Autom Smart Technol. (2023) 13:2439. doi: 10.5875/ausmt.v13i1.2439
165.
DamilareAOMope IsiakaRSeyi BabatundeR. An enhanced image based mobile deep learning model for identification of Newcastle poultry disease. J Appl Sci Inf Comput. (2024) 5:22–32. doi: 10.59568/JASIC-2024-5-1-03
166.
HigakiSFreitas EN deANegreiroADóreaJRRCabreraVE. Leveraging unsupervised machine learning techniques for detecting outliers in the daily milk yield data of dairy cows. J Dairy Sci. (2025) 108:9696–711. doi: 10.3168/jds.2024-25889
167.
FranceschiniSGreletCLebloisJGenglerNSoyeurtHCroweMet al. Can unsupervised learning methods applied to milk recording big data provide new insights into dairy cow health?J Dairy Sci. (2022) 105:6760–72. doi: 10.3168/jds.2022-21975
168.
MatzholdCSchodlKKlimekPSteiningerFEgger-DannerC. A key-feature-based clustering approach to assess the impact of technology integration on cow health in Austrian dairy farms. Front Anim Sci. (2024) 5:1421299. doi: 10.3389/fanim.2024.1421299
169.
MichelenaÁDíaz-LongueiraANovaisPSimićDFontenla-RomeroÓCalvo-RolleJL. Comparative analysis of unsupervised anomaly detection techniques for heat detection in dairy cattle. Neurocomputing. (2025) 618:129088. doi: 10.1016/j.neucom.2024.129088
170.
TrapaneseLBifulcoGSantinelloMPasquinoNCampanileGSalzanoA. Comparison of K-Means and hierarchical clustering methods for buffalo milk production data. Animals. (2025) 15:3246. doi: 10.3390/ani15223246
171.
KiouvrekisYVasileiouNGCKatsarouEILianouDTMichaelCKZikasSet al. The use of machine learning to predict prevalence of subclinical mastitis in dairy sheep farms. Animals. (2024) 14:2295. doi: 10.3390/ani14162295
172.
Pedro Mil-HomensMWangCTrevisanGDóreaFLinharesDCLHoltkampDet al. Leveraging productivity indicators for anomaly detection in swine breeding herds with unsupervised learning. Front Vet Sci. (2025) 12:1586438. doi: 10.3389/fvets.2025.1586438
173.
UlguimRRPereiraMATavaresJMellagiAPGGBortolozzoFPPLinharesDCet al. 235 Unsupervised learning for clustering swine breeding herds based on farm characteristics and management and their impact on reproductive performance in southern Brazil breeding herd. J Anim Sci. (2025) 103:235–6. doi: 10.1093/jas/skaf102.257
174.
KimHSKimYSEDeviraFAYiMY. Application of anomaly detection to identifying aggressive pig behaviors using reconstruction loss inversion. AgriEngineering. (2024) 6:4442–59. doi: 10.3390/agriengineering6040252
175.
LeeJChaeHSonSSeoJSuhYLeeJet al. Sustainable self-training pig detection system with augmented single labeled target data for solving domain shift problem. Sensors. (2025) 25:3406. doi: 10.3390/s25113406
176.
Díaz-CaoJMLiuXKimJClavijoMJMartínez-LópezB. Evaluation of the application of sequence data to the identification of outbreaks of disease using anomaly detection methods. Vet Res. (2023) 54:75. doi: 10.1186/s13567-023-01197-3
177.
GuitianJArnoldMChangYSnaryEL. Applications of machine learning in animal and veterinary public health surveillance. OIE Rev Sci Tech. (2023) 42:230–41. doi: 10.20506/rst.42.3366
178.
SibandaTZWelchMSchneiderDKolakshyapatiMRuhnkeI. Characterising free-range layer flocks using unsupervised cluster analysis. Animals. (2020) 10:855. doi: 10.3390/ani10050855
179.
van VeenLAvan den BrandHvan den OeverACMKempBYoussefA. An adaptive expert-in-the-loop algorithm for flock-specific anomaly detection in laying hen production. Comput Electron Agric. (2025) 229:109755. doi: 10.1016/j.compag.2024.109755
180.
VakhrameevABNarushinVGLarkinaTABarkovaOYPeglivanyanGKDysinAPet al. Disentangling clustering configuration intricacies for divergently selected chicken breeds. Sci Rep. (2023) 13:3319. doi: 10.1038/s41598-023-28651-8
181.
LiMZhouZZhangQZhangJSuoYLiuJet al. Multivariate analysis for data mining to characterize poultry house environment in winter. Poult Sci. (2024) 103:103633. doi: 10.1016/j.psj.2024.103633
182.
SiddiqueAHerronCBValentaJGarnerLJGuptaASawyerJTet al. Classification and feature extraction using supervised and unsupervised machine learning approach for broiler woody breast myopathy detection. Foods. (2022) 11:3370. doi: 10.3390/foods11203270
183.
CamposRLYoonSCChungSBhandarkarSM. Semisupervised deep learning for the detection of foreign materials on poultry meat with near-infrared hyperspectral imaging. Sensors. (2023) 23:7014. doi: 10.3390/s23167014
184.
WangZKhondowePBrannickEAbashtB. Spatial transcriptomics reveals alterations in perivascular macrophage lipid metabolism in the onset of Wooden Breast myopathy in broiler chickens. Sci Rep. (2024) 14:3450. doi: 10.1038/s41598-024-53904-5
185.
NayeriSSargolzaeiMTulpanD. A review of traditional and machine learning methods applied to animal breeding. Anim Heal Res Rev. (2019) 20:31–46. doi: 10.1017/S1466252319000148
186.
ChenWAlexandrePARibeiroGFukumasuHSunWReverterAet al. Identification of predictor genes for feed efficiency in beef cattle by applying machine learning methods to multi-tissue transcriptome data. Front Genet. (2021) 12:619857. doi: 10.3389/fgene.2021.619857
187.
HollevoetADe WaeleTPeraltaDTuyttensFDe PoorterEShahidA. Goats on the move: evaluating machine learning models for goat activity analysis using accelerometer data. Animals. (2024) 14:1977. doi: 10.3390/ani14131977
188.
KingKThorntonCRoopaeiM. Smart feeding: integrating deep learning into dairy farm practices. In: 2024 IEEE 5th World AI IoT Congr AIIoT 2024. Seattle, WA: IEEE (2024). p. 151–6.
189.
AfshariSafavi E. Assessing machine learning techniques in forecasting lumpy skin disease occurrence based on meteorological and geospatial features. Trop Anim Health Prod. (2022) 54:55. doi: 10.1007/s11250-022-03073-2
190.
AliMEyduranETariqMMTirinkCAbbasFBajwaMAet al. Comparison of artificial neural network and decision tree algorithms used for predicting live weight at post weaning period from some biometrical characteristics in harnai sheep. Pak J Zool. (2015) 47:1579–85. Available online at: https://www.zsp.com.pk/pdf47/1579-1585%20(10)%20QPJZ-0146-2015%2014-7-15%20REVISEDVERSION_FINAL.pdf
191.
LeeS-MParkH-TParkSLeeJHKimDYooHSet al. A machine learning approach reveals a microbiota signature for infection with Mycobacterium avium subsp. paratuberculosis in Cattle. Microbiol Spectr. (2023) 11: e03134–22. doi: 10.1128/spectrum.03134-22
192.
BakerMZhangXMaciel-GuerraADongYWangWHuYet al. Machine learning and metagenomics reveal shared antimicrobial resistance profiles across multiple chicken farms and abattoirs in China. Nat Food. (2023) 4:707–20. doi: 10.1038/s43016-023-00814-w
193.
EllisJLAlaiz-MoretónHNavarro-VillaAMcGeoughEJPurcellPPowellCDet al. Application of meta-analysis and machine learning methods to the prediction of methane production from in vitro mixed ruminal micro-organism fermentation. Animals. (2020) 10:720. doi: 10.3390/ani10040720
194.
YanYShiTBaoXGaiYLiangXJiangYet al. Combined network analysis and interpretable machine learning reveals the environmental adaptations of more than 10,000 ruminant microbial genomes. Front Microbiol. (2023) 14:1147007. doi: 10.3389/fmicb.2023.1147007
195.
EvansMVDrakeJM. A data-driven horizon scan of bacterial pathogens at the wildlife–livestock interface. Ecohealth. (2022) 19:246–58. doi: 10.1007/s10393-022-01599-3
Summary
Keywords
animal behavior analysis, digital twin, health, livestock production, care, Machine Learning, predictive analytics
Citation
Abdelrahman M, Issa S, Elsayed Ali M, Alotaibi J and Alshanbari F (2026) From machine learning to digital twin integration for livestock production and research. Front. Vet. Sci. 13:1744053. doi: 10.3389/fvets.2026.1744053
Received
11 November 2025
Revised
02 January 2026
Accepted
05 January 2026
Published
02 February 2026
Corrected
31 March 2026
Volume
13 - 2026
Edited by
Daniel Mota-Rojas, Metropolitan Autonomous University, Mexico
Reviewed by
Andrea Bragaglio, Council for Agricultural Research and Agricultural Economy Analysis | CREA, Italy
Berkant Ismail Yildiz, Akdeniz University, Türkiye
Damiano Cavallini, University of Bologna, Italy
Updates
Copyright
© 2026 Abdelrahman, Issa, Elsayed Ali, Alotaibi and Alshanbari.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Fahad Alshanbari, shnbry@qu.edu.sa
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.