Integration of Big Data and AI Empowered Precision Poultry Nutrition: A Review

Dashen Liu; Yonghong Zhang; Zhibin Ban; Yuming Guo; Qiuyu Jiang

doi:10.63823/ARP0260010

Animal Research Perspectives ›› 2026, Vol. 1 ›› Issue (1) : 0260010 DOI: 10.63823/ARP0260010

Review Article

Open Access

Integration of Big Data and AI Empowered Precision Poultry Nutrition: A Review

Author information +

History +

PDF (7461KB)

Abstract

Global poultry production plays an important role in the livestock industry, satisfying the rising consumer demand for animal protein. However, the expansion of poultry production has brought significant challenges, including pressures on resources utilization, concerns over meat quality and animal welfare, as well as environmental footprint and pollution. Hence, precision nutrition comprising two key elements: feed nutrient contents and individual nutrient requirements has attracted increasing attention in poultry production. This paper reviews current applications of artificial intelligence (AI) and Internet of Things (IoT) technologies in poultry farming, covering the data acquisition, processing and algorithms modeling. This paper also covers the quantification and modeling of energy content in feed ingredients, the dynamic modeling of nutrient requirements using mathematical model and machine learning methods, and the application of precision poultry farming techniques. In addition, biotechnology-derived proteins offer alternatives to conventional feed ingredients, and omics tools decode the molecular blueprint of nutrient metabolism, empowering precision nutrition with deeper biological understanding. Therefore, integration of big data and AI holds promise for enhancing the economic benefits, animal welfare, and environmental sustainability of poultry farming.

Graphical abstract

Keywords

Precision nutrition / Poultry / Artificial intelligence / Internet of Things / Sensors

Cite this article

Download citation ▾

Dashen Liu, Yonghong Zhang, Zhibin Ban, Yuming Guo, Qiuyu Jiang. Integration of Big Data and AI Empowered Precision Poultry Nutrition: A Review. Animal Research Perspectives, 2026, 1(1): 0260010 DOI:10.63823/ARP0260010

登录浏览全文

4963

注册一个新账户忘记密码

Introduction

According to the Organization for Economic Co-operation and Development (OECD) and the Food and Agriculture Organization (FAO), meat production is projected to rise 12% by 2033 relative to the average level of the past decade ^[1]. This growth inevitably intensifies competition for land and food resources with human beings. Moreover, intensive farming practices generate greenhouse gas emissions and excess excretion, resulting in environmental pollution and highlighting the need for environmentally sustainable development ^[2]. The rapid growth rates selected in modern broiler production often compromise meat quality and thus lead to the frequent occurrence of myopathies such as white striping and wooden breast ^[3-5]. Hence, improving meat quality has become a critical priority for the poultry industry, driven by increasing public awareness of animal welfare and rising consumer demand for high-quality products. Given the challenges facing the poultry industry, producers should improve nutrient efficiency and reduce the overfeeding of energy and protein, while maintaining meat quality and environmental sustainability. This highlights the importance of precision nutrition, which has not been fully applied in poultry production.

Precision nutrition, defined as the precise alignment of nutrient supply with animal requirements, has emerged as a promising approach to address these challenges in poultry production^[6,7]. This concept can be primarily divided into two components: evaluation of feed nutritional value and managing dynamic nutrient requirements in poultry. Numerous studies have focused on developing mathematical models to predict energy values of feed and ingredients, as well as the nutritional requirements of poultry ^[8-10]. Simple linear regression may not be sufficiently accurate, thus, sophisticated modeling approaches that capture variations in environmental conditions and animal physiological states should be developed in poultry nutrition ^[11]. The emergence of artificial intelligence (AI) provides advanced analytical capabilities for constructing more complex models by integrating large datasets using techniques such as machine learning and deep learning. Studies have shown that machine learning methods achieve better predictive performance than traditional mathematical models. ^[12]. Big data characterized by fast processing, high diversity, and great accuracy is usually acquired via Internet of Things (IoT) devices fitted with advanced sensors and cameras ^[13,14]. AI and big data are poised to drive a technological revolution and industrial transformation in poultry nutrition, feeding, and health management ^[15]. However, there are still limited reviews on the application of AI and big data in poultry nutrition.

Therefore, this review aims to provide a systematic description of current precision nutrition in poultry, including mathematical modeling, adequate feeding strategies and precision farming enabled by AI and big data, along with their advantages and further directions (Figure 1.) In addition, biotechnology and omics technologies are also discussed, as these pioneering techniques hold promise for advancing precision poultry nutrition and promoting sustainable agricultural development.

Precision nutrition arises from current challenges in poultry production

The global poultry industry faces major challenges, especially feed source shortages and environmental pollution. Feed consumption accounts for approximately 65% of total production costs ^[16]. Hence, it is essential to enhance the production efficiency and optimize feed resources utilization. Competition for feed resources such as soybean meal and corn between livestock production and human consumption threatens global feed security. Moreover, feed production places pressure on land use and negatively affects biodiversity. Poultry excreta may also cause greenhouse gases including CH₄, N₂O and CO₂ and other harmful gases ^[17]. As reported, hen houses typically produce more ammonia (NH₃) and particulate matter (PM) than swine, dairy, and broiler buildings ^[18]. Therefore, reducing and managing the carbon footprint and environmental pollution remains a critical global imperative for poultry industry ^[19]. Notably, reducing crude protein by 2 percentage points in poultry feed decreases nitrogen content in litter by 18% ^[20]. With global climate change, heat stress has emerged as a major issue that threatens poultry production. Nutrient requirements may differ depending on health status and environmental factors, and it is essential that the actual nutrient requirements of birds are precisely met. Consequently, precision nutrition is a critical approach to better utilize resources, improve production efficiency, and reduce environmental pollution.

Quantification and modeling for energy content of feed ingredients

Feed ingredients are a critical component of poultry nutrition, accounting for a large proportion of total production costs, with energy alone representing approximately 70% of feed costs ^[21]. Net energy is recommended because it accounts for heat increment, allowing for a more accurate estimation of feed energy content ^[8,22]. Moreover, it could reduce feed costs and improve economic returns ^[23]. In recent years, the growing urgency of precision nutrition has led to increased attention and research interest in net energy system for poultry, owing to its superior accuracy in assessing feed energy. Energy content determination of ingredients relies on animal trials, which is expensive and requires large numbers of animals. Recent literature has reported AME and NE values for ingredients and diets ^[24-27]. The substitution and gavage methods are commonly used but presents certain disadvantages. The results obtained with the substitution method can be influenced by the substitution ratio and feed composition, while the gavage method fails to reflect the natural physiological condition of the animals. Determining net energy of ingredients and feed was limited by the available and the precision of calorimetry chambers. Therefore, studies have been focused on establishing equations to predict the energy requirement of ingredients and diets. The equations established based on nutritional components are summarized in Table 1. Typically, net energy content is positively correlated with crude fat and starch, while negatively related to crude fiber and crude protein. Digestible nutrient values obtained from in vitro digestion tests also serve as accurate predictors for nutrient prediction models ^[28-30]. Given the complexity of the intestinal digestion process in poultry, efforts should be made to simulate this process as accurately as possible using in vitro methods ^[31]. Indeed, feed form, particle size, and heat treatment during processing also affect the physico-chemical properties and energy values of diets ^[32]. These established equations should be validated using large datasets, and equations incorporating more data should be developed for broader feed categories, such as protein-type and energy-type feed stuffs. Accordingly, meta-analysis principles have been applied to predict energy content by systematically integrating and re-analyzing data from multiple independent but related studies, enabling representative and accurate predictions ^[33,34]. Compared to multiple linear regression, machine learning method incorporating complex algorithms, such as Gaussian processes, may provide more accurate predictions of energy content in feed and ingredients of poultry ^[35]. The decreasing cost of NIRS technology and the optimization of NIRS system have facilitated its progressive adoption by the poultry industry ^[36]. Importantly, the accuracy of NIRS predictions relies on the repeatability of reference method values and leveraging large datasets ^[37].

Modeling nutrient requirements for poultry

Precision nutrition can be described as the practice for managing nutrition for individual animals or small groups, accounting for variations in nutrient requirements related to physical status, body weight and age ^[38]. However, current feeding strategies rely primarily on simple mixed feed and multi-phase feeding programs, in which feed formulations fail to match real-time changes in nutrient requirements. For determining optimal nutrient requirements, the comprehensive method is a common approach by comparing relevant indicators such as body weight, feed efficiency, nutrient digestibility and intestinal health ^[39-44]. Nevertheless, the traditional method cannot capture the dynamics of nutrient flow in the body, and the resulting nutrient requirements are relatively static that unable to predict individual nutritional needs. The factorial method was therefore developed to enable dynamic prediction of poultry nutrient requirements by partitioning them into maintenance, growth, laying and feather requirements ^[45]. Numerous studies predict ME requirements for poultry using mathematical models based on the factorial method, along with the comparative slaughter method and linear regression (Table 2). Energy and nutrient requirement models may facilitate developing more profitable feeding programs for poultry ^[46]. Quantifying the nutrient requirement for protein and fat deposition allows to formulate feed accordingly for the production target. Furthermore, prediction equations are established in poultry following the adoption of the net energy system (Table 2). Due to the limited availability of indirect calorimetry equipment, relevant data remain scarce. The environmental factors and animal age were incorporated into non-linear regression methods to predict energy requirements. For instance, temperature parameter could be used as an indicator in prediction equations, thereby improving predictive accuracy ^[47,48]. In addition, animal age can be included as a random variable, provided that a growth curve has first been established using the Gompertz model ^[49]. Specifically, poultry raised under intensive conditions are susceptible to enteric stress, which alters their nutrient requirements. Further nutritional requirement models should account for intestinal stress to enable precision nutritional programs to support intestinal recovery and strengthen immune function ^[50]. The National Research Council (NRC) published its 9th edition of Nutrient Requirements of Poultry in 1994, relying on the empirical data without incorporating computer models ^[51]. The upcoming NASEM (2024/2025) poultry nutrient requirements report has introduced computer models for predicting amino acid requirements in broilers and laying hens, representing a shift toward more dynamic and mechanistic approaches. Although the theoretical advantages of equations are relatively obvious, the actual implementation process is complex and suffers from a lack of individual representative, limiting the practical application under commercial conditions. In practice, Inra-porc tools (available at http://www.rennes.inra.fr/inraporc/) were developed and validated to enable the visualization of distinct aspects of nutrient utilization and excretion in pig under different nutritional strategies ^[52]. A systematic tool should also be developed for poultry to enable precision of body tissue deposition and performance based on dietary nutrition.

Mathematical modeling for feed formulation and feeding strategies

Feed formulation is the process of using mathematical optimization to find the best combination of feed ingredients that meets animals' nutrient requirements while minimizing total costs. The most commonly used method is linear programming that relies on the additivity of nutrients. However, a feasible solution may not exist during multi-objective optimization. Therefore, other algorithms have been developed in the industry to solve feed ration formulation problems, including fuzzy constraint, nonlinear programming (NLP), goal programming (GP), multi-objective goal programming (MOP), multi-objective fractional programming (MOFP), chance constrained programming (CCP), quadratic programming (QP), and risk-based methods ^[53,54]. For instance, NLP is incorporated into poultry feed formulation to maximize benefits, while MOP helps satisfy production goals with regard to nutrient fluctuation control ^[55]. Beneficially, the mixed-integer programming optimized poultry feed rations, and including Moringa oleifera increased profit by US$0.89, with the Bat algorithm outperforming Cplex in solving the problem ^[54]. Feed formulation software was therefore developed based on these optimization techniques, primarily linear programming, with extensions to NLP and MOP to address complex feed formulation challenges. Integrating models into feed formulation allows feed manufacturers to optimize nutrient composition and achieve target goals for downstream production systems ^[56]. Notably, our team has established a big data intelligence platform for poultry(https://www.nahs.org.cn/dt/zzdt/202503/t20250301_453664.htm). This platform is primarily based on a net energy system, high-quality scientific evaluation data, and practical production data. It enables big data and AI-driven decision-making for precision feed formulation, precision feeding, and precision farming.

Biotechnology-derived proteins for sustainable poultry nutrition

With the expansion of global poultry production, the pressure on feed resources has been increasing, while biotechnology-derived proteins may help alleviate these challenges. Biotechnology-derived proteins, including those from microbial, insect, algal and cultured meat sources, offering nutritionally balanced, highly digestible and functionally active feed ingredients that promote growth, intestinal health and immune function ^[57]. Importantly, AI and big data are considered a critical promoter for the development of biotechnological proteins, such as artificial intelligence, machine learning, automated bio-process monitoring and multi-omics technologies ^[57]. These techniques promote strain optimization, predictive modeling of nutrient digestibility, process control, quality assurance, and precision formulation. For instance, microbial technology is commonly applied to utilize yeasts, bacteria, and filamentous fungi to produce single-cell proteins that are high in protein content, have a balanced amino acid composition, and contain bioactive components ^[58,59]. Furthermore, machine learning method offer predictive capabilities for microbial growth kinetics under different carbon sources, thereby enhancing the valorization of agro-industrial residues ^[60]. The application of biotechnology-derived proteins in poultry nutrition has been comprehensively reviewed ^[61,62], whereas further research is needed to address regulatory and safety considerations.

Precision livestock farming as the technological foundation of precision nutrition

Precision nutrition involves providing diets that meet production targets while minimizing costs. Its realization depends on precision livestock farming (Figure 2), which encompasses environment control, animal feeding systems and health management ^[38]. The precision livestock farming typically performs three key activities: automatic data collection, data processing, and system control actions ^[38,63]. The Internet of Things (IoT) serves as the foundational infrastructure for these activities, connecting sensors, feeders, computer vision systems, and environmental controllers into a real-time data and actuation network ^[64]. For environmental monitoring, common sensors include LM35 and DHT11、DHT22 for temperature and humidity ^[65-68], as well as MQ137 for NH₃ and the MQ135 for carbon dioxide (CO₂) levels ^[66]. Computer vision has been performed to detect anomalies such as lameness in poultry ^[69]. IoT-driven smart feeding system have been shown to reduce feed wastage by 23.5% and decrease production costs by 18.7% per kg of gain ^[70]. Automatic feeding systems also improve feed conversion ratio at about 4.4 and growth rate at about 8.88 g/day ^[71]. In water management, detecting drinker line leakage increases flock consistency and performance. Vision-based systems enable body weight estimation with an error of 7.8% ^[72] and lameness determination with correlations up to 0.882 ^[69], thereby enhancing animal welfare through early intervention. Edge-AI based IoT technology is capable of detecting the healthy status of poultry with accuracy of approximately 95.1% ^[73]. Early detection of lameness and other health issues allows farmers and veterinarians to take timely management actions. Furthermore, miniature implantable sensors may detect temperature, heart rate and activity in broilers ^[74,75], and even monitor intestinal inflammation in humans ^[76]. Integrating AI with computer vision enables poultry operations to continuously monitor animal behavior, feeding patterns, and environmental conditions in real time (Figure 2). This allows for dynamic feeding adjustments based on individual bird activity, early identification of lameness or illness through gait and posture analysis, and responsive environmental control informed by bird distribution and thermal behavior ^[77,78].

Artificial intelligence is revolutionizing precision nutrition

Artificial intelligence is transforming poultry farming by enhancing precision nutrition, productivity, sustainability and animal welfare through monitoring and automation ^[79,80]. Machine learning, a sub-field of artificial intelligence, uses algorithms to train models that learn patterns from experience and apply this knowledge to new data, thereby achieving functions such as prediction, classification, and decision-making ^[81,82]. Machine learning and deep learning methods, including artificial neural networks (ANN), random forest (RF), support vector machines (SVM) and YOLO, can be applied to establish predictive models involving uncertain variables or complex relationships ^[83]. Their predictive accuracy is generally superior to traditional methods, without requiring a predefined functional form, while exhibiting strong adaptability and robustness. A total of 32 literature was summarized in the Table 3 and Figure 3, employing various algorithms combined with camera or sensors for applications in predicting poultry production traits, monitoring welfare, detecting environmental conditions, and analyzing feed. For instance, sound-based AI algorithms for feeding monitoring have demonstrated 86% accuracy in detecting pecking sounds, and the detected feeding events correlate with actual feed intake at r = 0.994 ^[84]. Furthermore, machine learning could optimize pellet quality, enzyme addition and ingredient grind size in feed manufacturing ^[85]. Machine learning methods enable continuous identification and classification of behavioral patterns of poultry from video and sensor data, supporting optimize poultry welfare and performance ^[86]. Convolutional neural network (CNN) models, particularly YOLOv8, achieve over 90% accuracy in vision-based detection of health conditions such as bumblefoot and woody breast ^[87,88]. Beyond behavior and health monitoring, AI is also used to monitor and predict air quality in poultry houses. Such real-time environmental data serve as valuable inputs for precision nutrition models, as air quality directly impacts bird health, feed efficiency, and nutrient requirements ^[89]. All in all, machine learning supports individual nutrition management by predicting and monitoring nutrients intake flow, quantity and composition of biological processes of poultry, including body growth, maintenance, physical activities, reproduction and egg laying ^[89-93]. The integration of machine learning with omics data enabled the prediction of diet types ^[94], an approach that deserves further study.

Integrating omics technologies for precision nutrition

Individual variations due to age, physiological status, and sex are not always adequately addressed by current feeding techniques. In particular, the actual nutritional requirements associated with specific health status and environmental stress may be overlooked in the poultry industry. Metabolomic profiling may help in understanding the metabolism of diets and the pathways of precise nutrition ^[95]. Screening for metabolites as biomarkers enables targeted optimization of feed formulation and animal welfare ^[96]. For instance, balancing amino acids in low-protein diets is essential to reduce nitrogen excretion and facilitate precision nutrition, making the identification of metabolic biomarkers essential to fulfill this goal ^[97,98]. Microbial composition and intestinal villus parameters can be shaped by diet ^[99,100], and are closely associated with intestinal health and performance, positioning the intestine as a key organ for achieving precision nutrition through microbiomics approaches ^[101,102]. Nutrition may interact with host genetics and the microbiota, and such interactions may regulate the health and development of the next generation. Using transcriptomics and microbiomics, dietary soyasaponin was shown to modulate Bifidobacterium adolescentis levels, thereby affecting the physiological status of newly hatched poultry and offering a theoretical basis for maternal nutritional intervention ^[103]. Furthermore, genome-wide association studies (GWAS) can identify potential candidate genes linked to disease susceptibility, health traits and environmental adaptability, thereby informing targeted nutritional strategies and precision health management in poultry ^[104,105]. Although numerous reviews have recently summarized the application of omics techniques in precision poultry nutrition ^[106-108], further research is still needed to integrate multi-omics data into practical feeding strategies.

Contributions of precision nutrition to sustainable poultry production

Precision nutrition yields diverse benefits across economic, environmental, and animal welfare. For example, a precision nutrition program was developed that involves blending two different concentrations on a daily basis. This approach meets daily energy and protein requirements, thereby improving production efficiency in broilers^[109]. Although farms may need to allocate more financial resources to feed combination systems, researchers have estimated that the equipment cost could be recouped within a short period ^[16]. Moreover, the application of precision nutrition can benefit environmental protection by reducing phosphorus and protein excretion in manure, as well as greenhouse gas emissions by up to 6% ^[110]. Circadian rhythms influence physiological and metabolic processes in poultry, such as eggshell calcification, leading to daily variations in nutrient utilization and requirements. In practice, split feeding aligns nutrient supply with hen’s metabolic needs and rhythms, thereby optimizing feed efficiency and improving eggshell quality, as well as reducing unnecessary nutrient excretion ^[111]. The interplay between the circadian clock, dietary nutrients, intestinal microbiota, and animal behavior is a key consideration for advancing precision nutrition ^[112]. Moreover, poultry may experience varying degrees of intestinal challenges, and their nutrient requirements, particularly the need for energy and amino acid may differ accordingly. In this context, precision intestinal nutrition has emerged as a promising strategy to support gut health and improve growth performance, thereby contributing to more sustainable poultry production ^{[50, 113, 114]}.

Future expectations in precision poultry nutrition

Future studies should focus on the validation and integration of models for predicting energy content of feeds. Research institutions and industry stakeholder should collaborate to promote the application of energy values, especially NE content of feeds ingredients and nutrient requirements for poultry, as these two aspects form the main basis of precision poultry nutrition. Moreover, the integration of AI and IoT should be widely adopted in modern poultry industry, enabling producers to manage personalized nutrition and health. More advanced algorithms and multi-model systems hold promise for further personalizing farming practices should be developed to promote both economic and ethical sustainability in poultry production. Furthermore, environmental pollution caused by high nitrogen excretion in poultry should be addressed through precision nutrition, for example, by using low-protein diets supplemented with balanced amino acids. In this context, omics techniques should be applied to explore the underlying mechanisms for precision nutrition and individual health. Biotechnological protein substitutes should be further explored to promote nutrient utilization and agricultural waste valorization. However, literature on the application of AI and big data in environmentally friendly poultry production remains limited, representing an important direction for further research.

Conclusion

Poultry nutrition has transitioned from simple-mixed feeds, multi-phase feeding, and basic regression models toward precision nutrition enabled by camera and sensor-based monitoring, machine learning algorithms, as well as dynamic and individualized feeding strategies. IoT technology and computer vision equipped with sensors can detect feed intake, health status, and environmental factors. The resulting big data can be processed using AI, which enables more precise prediction of nutrient requirements, personalized feeding protocols, and real-time feeding strategies. Meanwhile, omics and biotechnological innovations generate critical biological data that can help mitigate the environmental footprint and enhance health monitoring in poultry production. In conclusion, big data and AI has been applied in precision nutrition, facilitating animal welfare, improving efficiency and quality of poultry products, and future efforts should be directed toward green, safe and sustainable development.

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Zhang S, Lai C, Zhao J, et al. Big Data and AI‐powered modeling: A pathway to sustainable precision animal nutrition[J]. Advanced Science, 2025, 12(41):e07564.

[2]	Khodadadi M, Masoumi A, Sadeghi M. Drying, a practical technology for reduction of poultry litter (environmental) pollution: methods and their effects on important parameters[J]. Poultry Science, 2024, 103(12):104277.

[3]	Lei J, Dong Y, Hou Q, et al. Intestinal microbiota regulate certain meat quality parameters in chicken[J]. Frontiers in Nutrition, 2022, 9.

[4]	Yue K, Cao Q-Q, Shaukat A, et al. Insights into the evaluation, influential factors and improvement strategies for poultry meat quality: A review[J]. npj Science of Food, 2024, 8(1):62.

[5]	Jiang Q, Lei J, Zhao L, et al. Ellagic acid from pomegranate peel attenuates fibrosis and remodels water distribution in chicken meat under inflammatory challenge[J]. Journal of Agricultural and Food Chemistry, 2026, 74(21):16395-16407.

[6]	Sifri M. Precision nutrition for poultry[J]. Journal of Applied Poultry Research, 1997, 6(4): 461.

[7]	Kidd M, Tillman P, Tillman N, et al. Precision feeding for optimizing poultry production[J]. CABI Reviews, 2023(2023).

[8]	Barzegar S, Wu S B, Noblet J, et al. Energy efficiency and net energy prediction of feed in laying hens[J]. Poultry Science, 2019, 98(11): 5746-5758.

[9]	Carre B, Lessire M, Juin H. Prediction of the net energy value of broiler diets[J]. Animal, 2014, 8(9): 1395-401.

[10]	Wu S B, Swick R A, Noblet J, et al. Net energy prediction and energy efficiency of feed for broiler chickens[J]. Poultry Science, 2019, 98(3): 1222-1234.

[11]	Wang L, Shi H, Hu Q, et al. Modeling net energy partition patterns of growing-finishing pigs using nonlinear regression and artificial neural networks[J]. Journal of Animal Science, 2023, 101:1-13.

[12]	Ahmadi H, Rodehutscord M. Application of artificial neural network and support vector machines in predicting metabolizable energy in compound feeds for pigs[J]. Frontiers in Nutrition, 2017, 4:27.

[13]	Taleb H M, Mahrose K, Abdel-Halim A A, et al. Using artificial intelligence to improve poultry productivity - A review[J]. Annals of Animal Science, 2025, 25(1): 23-33.

[14]	Leishman E M, You J, Ferreira N T, et al. Review: When worlds collide - poultry modeling in the 'Big Data' era[J]. Animal, 2023, 17 Suppl 5: 100874.

[15]	Valletta J J, Torney C, Kings M, et al. Applications of machine learning in animal behaviour studies[J]. Animal Behaviour, 2017, 124: 203-220.

[16]	Moss A F, Chrystal P V, Cadogan D J, et al. Precision feeding and precision nutrition: a paradigm shift in broiler feed formulation?[J]. Animal Bioscience, 2021, 34(3): 354-362.

[17]	Kacprzak M, Malińska K, Grosser A, et al. Cycles of carbon, nitrogen and phosphorus in poultry manure management technologies - environmental aspects[J]. Critical Reviews in Environmental Science and Technology, 2022, 53(8): 914-938.

[18]	Ni J-Q, Erasmus M, Jones D R, et al. Effectiveness and characteristics of a new technology to reduce ammonia, carbon dioxide, and particulate matter pollution in poultry production with artificial turf floor[J]. Environmental Technology & Innovation, 2023, 29:102976.

[19]	Zhang L L, Reaihan E, Ali M M, et al. Livestock and poultry manure management from the perspective of carbon neutrality in china[J]. Frontiers of Agricultural Science and Engineering, 2023, 10(3): 341-362.

[20]	Ferguson N S, Gates R S, Taraba J L, et al. The effect of dietary protein and phosphorus on ammonia concentration and litter composition in broilers[J]. Poultry Science, 1998, 77(8): 1085-1093.

[21]	Noblet J, Wu S-B, Choct M. Methodologies for energy evaluation of pig and poultry feeds: A review[J]. Animal Nutrition, 2022, 8: 185-203.

[22]	Noblet J, Tay-Zar A-C, Wu S-B, et al. Re-evaluation of recent research on metabolic utilization of energy in poultry: Recommendations for a net energy system for broilers[J]. Animal Nutrition, 2024, 16: 62-72.

[23]	De Groote G. A comparison of a new net energy system with the metabolisable energy system in broiler diet formulation, performance and profitability1[J]. British Poultry Science, 1974, 15(1): 75-95.

[24]	Barzegar S, Wu S-B, Choct M, Swick RAJPs. Factors affecting energy metabolism and evaluating net energy of poultry feed[J]. Elsevier BV, 2020, 99(1):487-98.

[25]	Liu W, Liu G H, Liao R B, et al. Apparent metabolizable and net energy values of corn and soybean meal for broiler breeding cocks[J]. Poultry Science, 2017, 96(1): 135-143.

[26]	Sharma N K, Ban Z, Classen H L, et al. Net energy, energy utilization, and nitrogen and energy balance affected by dietary pea supplementation in broilers[J]. Animal Nutrition, 2021, 7(2): 506-511.

[27]	Noblet J. Comparative interests and limits of metabolizable energy and net energy for evaluating poultry and pig feeds[C]. 20th European Symposium on Poultry Nutrition, 2015: 24-27.

[28]	Zaefarian F, Cowieson A J, Pontoppidan K, et al. Trends in feed evaluation for poultry with emphasis on in vitro techniques[J]. Animal Nutrition, 2021, 7(2): 268-281.

[29]

Losada B, García-Rebollar P, Álvarez C, et al. The prediction of apparent metabolisable energy content of oil seeds and oil seed by-products for poultry from its chemical components, in vitro analysis or near-infrared reflectance spectroscopy[J]. Animal Feed Science and Technology, 2010, 160(1-2): 62-72.

[30]	Sousa D, Moset V, Del Carmen López-Luján M, et al. Potential of solid-state fermentation to enhance the nutritional value of oilseed cakes for poultry[J]. Animal Feed Science and Technology, 2024, 316: 116056.

[31]	Bryan D D S L, Classen H L. In vitro methods of assessing protein quality for poultry[J]. Animals, 2020, 10(4):551.

[32]	Mateos G G, Cámara L, Fondevila G, et al. Critical review of the procedures used for estimation of the energy content of diets and ingredients in poultry[J]. Journal of Applied Poultry Research, 2019, 28(3): 506-525.

[33]	Martínez Marín A L, Gariglio M, Biasato I, et al. Meta-analysis of the effect of black soldier fly larvae meal in diet on broiler performance and prediction of its metabolisable energy value[J]. Italian Journal of Animal Science, 2023, 22(1): 379-387.

[34]	Mariano F, Paixão C A, Lima R R, et al. Prediction of the energy values of feedstuffs for broilers using meta-analysis and neural networks[J]. Animal, 2013, 7(9): 1440-1445.

[35]	Ahmadi H, Golian A. Growth analysis of chickens fed diets varying in the percentage of metabolizable energy provided by protein, fat, and carbohydrate through artificial neural network[J]. Poultry Science, 2010, 89(1): 173-179.

[36]	Simmler M, Ishizaki K, Mulloni A, et al. Enabling precision feeding: A novel micro-NIRS system for rapid on-site analysis of the nutritional composition of poultry feed and feed ingredients[J]. Smart Agricultural Technology, 2025, 12:101220.

[37]	Yegani M, Korver D R. Review: Prediction of variation in energetic value of wheat for poultry[J]. Canadian Journal of Animal Science, 2012, 92(3): 261-273.

[38]	Pomar C, Remus A. Review: Fundamentals, limitations and pitfalls on the development and application of precision nutrition techniques for precision livestock farming[J]. Animal, 2023, 17:100763.

[39]	Teofilo G F D S, Lizana R R, Camargos R D S, et al. Effect of feed restriction on the maintenance energy requirement of broiler breeders[J]. Animal Bioscience, 2022, 35(5): 690-697.

[40]	Nielsen B L, Litherland M, Nøddegaard F. Effects of qualitative and quantitative feed restriction on the activity of broiler chickens[J]. Applied Animal Behaviour Science, 2003, 83(4): 309-323.

[41]	Toghyani M, Macelline S, Selle P H, et al. Interactive effect of dietary metabolizable energy levels with amino acid density in male broiler chickens: Carcass yield, nutrient intake, digestibility and excretion[J]. Poultry Science, 2025, 104(1):104530.

[42]	Xie M, Meng R Z, Tang J, et al. Apparent metabolizable energy requirement of feed-restricted White Pekin duck breeder pullets[J]. Animal Feed Science and Technology, 2023, 295:115508.

[43]	Yusuf H B, Samuel J C, Hamma H H, et al. Effects of energy and protein ratios on the performance of grower pullet chickens in Yola, Adamawa State, Nigeria[J]. British Journal of Multidisciplinary and Advanced Studies, 2023, 4(4): 41-52.

[44]	Miao Z, Zhang G, Zhang J, et al. Effect of early dietary energy restriction and phosphorus level on subsequent growth performance, intestinal phosphate transport, and AMPK activity in young broilers[J], 2017, 12(12): e0186828.

[45]	Birkett S, Lange K D. A computational framework for a nutrient flow representation of energy utilization by growing monogastric animals[J]. British Journal of Nutrition, 2007, 86(6): 661-674.

[46]	Sakomura N K, Fernandes J B K, Resende K T, et al. Modelling energy utilization in poultry. In Modelling nutrient digestion and utilisation in farm animals. Wageningen Academic. 2010: 297-305.

[47]	Romero L, Zuidhof M, Renema R, et al. Characterization of energetic efficiency in adult broiler breeder hens[J]. Poultry Science, 2009, 88(1): 227-35.

[48]	Sakomura N, Silva R, Couto H, et al. Modeling metabolizable energy utilization in broiler breeder pullets[J]. Poultry Science, 2003, 82(3): 419-27.

[49]	Caldas J V, Boonsinchai N, Wang J, et al. The dynamics of body composition and body energy content in broilers[J]. Poultry Science, 2019, 98(2): 866-877.

[50]	Lee D T, Rochell S J. Precision intestinal nutrition: knowledge and gaps regarding the role of amino acids during an enteric challenge[J]. Poultry Science, 2022, 101(3):101674.

[51]	Klasing K C, Dozier W A, Mateos G G, et al. Informal nutrition symposium: Overview of the nutrient requirements of poultry, 10th revised edition[J]. Journal of Applied Poultry Research, 2025, 34(4):100616.

[52]	Van Milgen J, Valancogne A, Dubois S, et al. InraPorc: a model and decision support tool for the nutrition of growing pigs[J]. Animal Feed Science and Technology, 2008, 143(1-4): 387-405.

[53]	Zhang F, Roush W B. Multiple-objective (goal) programming model for feed formulation: An example for reducing nutrient variation[J]. Poultry Science, 2002, 81(2): 182-192.

[54]	Chagwiza G, Chivuraise C, Gadzirayi C T. A mixed integer programming poultry feed ration optimisation problem using the Bat algorithm[J]. Advances in Agriculture, 2016, 2016: 1-6.

[55]	Guevara V R. Use of Nonlinear programming to optimize performance response to energy density in broiler feed formulation[J]. Poultry Science, 2004, 83(2): 147-151.

[56]	Pesti G M, Choct M. The future of feed formulation for poultry: Toward more sustainable production of meat and eggs[J]. Animal Nutrition, 2023, 15: 71-87.

[57]	Keohavong B. Digital innovation integration into biotechnology for development of sustainable protein frontiers for poultry nutrition in a circular bioeconomy[J]. Poultry Science, 2025: 106276.

[58]	Ledbetter F. Single-cell protein for feed and food[J]. The EuroBiotech Journal, 2025, 9(1): 117-127.

[59]	Khan A R, Ahmad B, Khan M, et al. Production of single cell protein (SCP) from the peel waste of pea, potato, and banana by aspergillus flavus NRRL 21882 as an efficient organic poultry supplement[J]. ACS Omega, 2024, 9(36): 37763-37770.

[60]	Bajić B, Vučurović D, Vasić Đ, et al. Biotechnological production of sustainable microbial proteins from agro-industrial residues and by-products[J]. Foods, 2022, 12(1):107.

[61]	Hou Y, Wu Z, Dai Z, et al. Protein hydrolysates in animal nutrition: Industrial production, bioactive peptides, and functional significance[J]. Journal of Animal Science and Biotechnology, 2017, 8(1):24.

[62]	Tufarelli V, Selvaggi M, Dario C, et al. Genetically modified feeds in poultry diet: safety, performance, and product quality[J]. Critical Reviews in Food Science and Nutrition, 2015, 55(4): 562-569.

[63]	Banhazi T M, Babinszky L, Halas V, et al. Precision livestock farming: Precision feeding technologies and sustainable livestock production[J]. International Journal of Agricultural and Biological Engineering, 2012, 5(4): 54-61.

[64]	Mazunga F, Mzikamwi T, Mazunga G, et al. IoT based remote poultry monitoring systems for improving food security and nutrition: recent trends and issues[J]. Journal of Agriculture Science & Technology, 2023, 22(2): 4-21.

[65]	Jebari H, Hayani Mechkouri M, Rekiek S, et al. Poultry-edge-AI-IoT system for real-time monitoring and predicting by using artificial intelligence[J]. International Journal of Interactive Mobile Technologies (iJIM), 2023, 17(12): 149-170.

[66]	Handigolkar L S, Kavya M L, Veena P D. Iot based smart poultry farming using commodity hardware and software[J]. Bonfring International Journal of Software Engineering and Soft Computing, 2016, 6(Special Issue): 171-175.

[67]	Islam M M, Tonmoy S S, Quayum S, et al. Smart poultry farm incorporating GSM and IoT[C]. 2019 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), 2019: 277-280.

[68]	Raghudathesh G, Deepak D, Prasad G K, et al. IoT based intelligent poultry management system using Linux embedded system[C]. 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017: 449-454.

[69]	Aydin A. Development of an early detection system for lameness of broilers using computer vision[J]. Computers and Electronics in Agriculture, 2017, 136: 140-146.

[70]	Nasir M. Smart feeding system using IoT sensors to optimize feed conversion ratio (FCR) and growth performance in broiler production[J]. Livestock Science & Innovation Journal, 2025, 2(2): 91-115.

[71]	Peng Y, Zeng Z, Lv E, et al. A real-time automated system for monitoring individual feed intake and body weight of group-housed young chickens[J]. Applied Sciences, 2022, 12(23):12339.

[72]	Mortensen A K, Lisouski P, Ahrendt P. Weight prediction of broiler chickens using 3D computer vision[J]. Computers and Electronics in Agriculture, 2016, 123: 319-326.

[73]	Tong Q, Wang J, Yang W, et al. Edge AI-enabled chicken health detection based on enhanced FCOS-Lite and knowledge distillation[J]. Computers and Electronics in Agriculture, 2024, 226:109432.

[74]	Khan I, Soster De Carvalho P, Martos Martinez-Caja A, et al. Use of implantable heart rate, temperature and activity loggers in broiler chickens[C]. XI European Symposium on Poultry Welfare, 2023, 104.

[75]	Yang H H, Bae Y H, Min W. Implantable wireless sensor network to monitor the deep body temperature of broilers[C]. 5th ACIS International Conference on Software Engineering Research, Management & Applications (SERA 2007), 2007: 513-517.

[76]	Madhvapathy S R, Bury M I, Wang L W, et al. Miniaturized implantable temperature sensors for the long-term monitoring of chronic intestinal inflammation[J]. Nature Biomedical Engineering, 2024, 8(8): 1040-1052.

[77]	Aguilar-Lazcano C A, Espinosa-Curiel I E, Ríos-Martínez J A, et al. Machine learning-based sensor data fusion for animal monitoring: Scoping review[J]. Sensors, 2023, 23(12):5732.

[78]	Huang J, Zhang T, Cuan K, et al. An intelligent method for detecting poultry eating behaviour based on vocalization signals[J]. Computers and Electronics in Agriculture, 2021, 180:105884.

[79]	Engelbrecht D, Steyn N, Djouani K, et al. Precision farming: A review of artificial intelligence applications in broiler poultry farming[J]. Emirates Journal of Food and Agriculture, 2026, 38: 1-13.

[80]	Abdel-Wareth A a A, Ahmed A A. Advancing poultry nutrition: AI innovations for sustainable nutrient requirements of poultry: A review[J]. Agriculture, 2026, 16(4):450.

[81]	Kirk D, Catal C, Tekinerdogan B. Precision nutrition: A systematic literature review[J]. Computers in Biology and Medicine, 2021, 133:104365.

[82]	Shwetha V, Maddodi B, Laxmi V, et al. Latest trend and challenges in machine learning-and deep learning-based computational techniques in poultry health and disease management: A review[J]. Journal of Computer Networks & Communications, 2024, 2024.

[83]	Milosevic B, Ciric S, Lalic N, et al. Machine learning application in growth and health prediction of broiler chickens[J]. World's Poultry Science Journal, 2019, 75(3): 401-410.

[84]	Aydin A, Bahr C, Berckmans D. A real-time monitoring tool to automatically measure the feed intakes of multiple broiler chickens by sound analysis[J]. Computers and Electronics in Agriculture, 2015, 114: 1-6.

[85]	You J, Ellis J L, Tulpan D, et al. Review: recent advances and future technologies in poultry feed manufacturing[J]. World's Poultry Science Journal, 2024, 80(3): 643-655.

[86]	Subramani T, Jeganathan V, Kunkuma Balasubramanian S. Machine learning and deep learning techniques for poultry tasks management: A review[J]. Multimedia Tools and Applications, 2024, 84(2): 603-645.

[87]	Natsir M H, Mahmudy W F, Tono M, et al. Advancements in artificial intelligence and machine learning for poultry farming: Applications, challenges, and future prospects[J]. Smart Agricultural Technology, 2025, 12:101307.

[88]	Bist R B, Yang X, Subedi S, et al. Automatic detection of bumblefoot in cage-free hens using computer vision technologies[J]. Poultry Science, 2024, 103(7): 103780.

[89]	Debauche O, Mahmoudi S, Mahmoudi S A, et al. Edge computing and artificial intelligence for real-time poultry monitoring[J]. Procedia computer science, 2020, 175: 534-541.

[90]	González L A, Kyriazakis I, Tedeschi L O. Review: Precision nutrition of ruminants: approaches, challenges and potential gains[J]. Animal, 2018, 12: s246-s261.

[91]	Geronimo B C, Mastelini S M, Carvalho R H, et al. Computer vision system and near-infrared spectroscopy for identification and classification of chicken with wooden breast, and physicochemical and technological characterization[J]. Infrared Physics & Technology, 2019, 96: 303-310.

[92]	Pirompud P, Sivapirunthep P, Punyapornwithaya V, et al. Application of machine learning algorithms to predict dead on arrival of broiler chickens raised without antibiotic program[J]. Poultry Science, 2024, 103(4):103504.

[93]	Amraei S, Abdanan Mehdizadeh S, Salari S. Broiler weight estimation based on machine vision and artificial neural network[J]. British Poultry Science, 2017, 58(2): 200-205.

[94]	Devi P, Nath S K, Barua B, et al. Big data and artificial intelligence in animal nutrition: a new era of precision feeding[J]. Tropical Animal Health and Production, 2026, 58(4): 267.

[95]	Abd El-Hack M E, Allam A A, Aldhalmi A K, et al. Integrating metabolomics for precision nutrition in poultry: optimizing growth, feed efficiency, and health[J]. Frontiers in Veterinary Science, 2025, 12:1594749.

[96]	Goossens E, Dehau T, Ducatelle R, et al. Omics technologies in poultry health and productivity - part 2: future applications in the poultry industry[J]. Avian Pathology, 2022, 51(5): 418-423.

[97]	Kim J C, Saremi B, Siegert W, et al. Steering nitrogen emission from poultry production through precision nutrition[J]. Poultry Science, 2026, 105(7):106864.

[98]	Wang B, Zhang X, Liu Y, et al. Assessment of the dietary amino acid profiles and the relative biomarkers for amino acid balance in the low-protein diets for broiler chickens[J]. Journal of Animal Science and Biotechnology, 2024, 15(1):157.

[99]	Rychlik I. Composition and function of chicken gut microbiota[J]. Animals (Basel), 2020, 10(1):103.

[100]

Jiang Q, Zhao L, Ban Z, et al. Different fat-to-fiber ratios by changing wheat inclusion level impact energy metabolism and microbial structure of broilers[J]. Frontiers in Microbiology, 2024, 15: 1298262.

[101]

Kers J G, Velkers F C, Fischer E a J, et al. Host and environmental factors affecting the intestinal microbiota in chickens[J]. Frontiers in Microbiology, 2018, 9:235.

[102]

Kogut M H J P S. Role of diet-microbiota interactions in precision nutrition of the chicken: facts, gaps, and new concepts[J]. Poultry Science, 2022, 101(3): 101673.

[103]

Gao M, Chen S, Fan H, et al. Soyasaponin and vertical microbial transmission: Maternal effect on the intestinal development and health of early chicks[J]. Imeta, 2025, 4(4): e70044.

[104]

Liu P, Luo N, Liu D, et al. Integrating GWAS and transcriptomics to identify candidate genes conferring relative growth rate trait in white-feathered broiler[J]. Poultry Science, 2024, 103(12): 104338.

[105]

Lin X, Chen H. Genetic strategies in poultry to combat environmental stress: An analysis based on GWAS[J]. Animal Molecular Breeding, 2024, 14(1):62-71.

[106]

Ren J, Gao Z, Lu Y, et al. Application of GWAS and mGWAS in livestock and poultry breeding[J]. Animals, 2024, 14(16):2382.

[107]

Zampiga M, Flees J, Meluzzi A, et al. Application of omics technologies for a deeper insight into quali-quantitative production traits in broiler chickens: A review[J]. Journal of Animal Science and Biotechnology, 2018, 9(1):61.

[108]

Cao J, Zhou X, Liu J, et al. Single-cell multi-omics sequencing technologies and their applications in livestock and poultry research[J]. Journal of Agricultural and Food Chemistry, 2025, 73(51): 32508-32520.

[109]

Nawab A, Dao T H, Chrystal P V, et al. Evaluation of precision feeding to enhance broiler growth performance[J]. Animals (Basel), 2025, 15(16):2433.

[110]

Andretta I, Pomar C, Rivest J, et al. Precision feeding can significantly reduce lysine intake and nitrogen excretion without compromising the performance of growing pigs[J]. Animal, 2016, 10(7): 1137-1147.

[111]

Do Nascimento C H, De Lima A V, De Souza P E L, et al. Split feeding for laying hens: a step beyond precision nutrition[J]. Poultry Science, 2025, 104(7): 105158.

[112]

Moss A F, Dao T H, Crowley T M, et al. Interactions of diet and circadian rhythm to achieve precision nutrition of poultry[J]. Animal Production Science, 2023, 63(18): 1926-1932.

[113]

Jiang Q, Zhao L, Lei J, et al. Interaction between energy level and starch:fat ratio on intestinal energy metabolism of layer pullets[J]. Animal Nutrition, 2025, 20: 211-225.

[114]

Jiang Q, Zheng K, Huang B, et al. Energy restriction optimizes energy partitioning and remodels intestinal energy metabolism in layer pullets[J]. Poultry Science, 2025, 104(12): 105985.

[115]

Mariano F C M Q, de Lima R R, Rodrigues P B, et al. Prediction equations of energetic values of feedstuffs obtained using meta-analysis and principal components[J]. Ciência Rural, 2012, 42(9):1634-1641.

[116]

Nascimento G A J, Rodrigues P B, Freitas R T F, et al. Prediction equations to estimate metabolizable energy values of energetic concentrate feedstuffs for poultry by the meta-analysis process[J]. Arquivo Brasileiro de Medicina Veterinária e Zootecnia, 2011, 63, 222-230.

[117]

Nascimento G A J D, Rodrigues P B, Freitas R T F D, et al. Equações de predição para estimar os valores energéticos de alimentos concentrados de origem vegetal para aves utilizando a metanálise[J]. Revista Brasileira de Zootecnia, 2009, 38(7), 1265-1271.

[118]

Tay-Zar A C, Wongphatcharachai M, Srichana P, et al. Prediction of net energy of feeds for broiler chickens[J]. Animal Nutrition, 2024, 16: 241-250.

[119]

Palić D, Okanović D, Psodorov D, et al. Prediction of metabolisable energy of poultry feeds by estimating in vitro organic matter digestibility[J]. African Journal of Biotechnology, 2012, 11(28), 7313-7317.

[120]

Cerrate S, Ekmay R, England J A, et al. Predicting nutrient digestibility and energy value for broilers[J]. Poultry Science, 2019, 98(9): 3994-4007.

[121]

Baiz A A, Ahmadi H, Shariatmadari F, et al. A Gaussian process regression model to predict energy contents of corn for poultry[J]. Poultry Science, 2020, 99(11): 5838-5843.

[122]

Eshtejarani A A, Moravej H, Ghaziani F, et al. Development of prediction equations for apparent metabolizable energy corrected for nitrogen of fish meal and poultry by-product meal in broiler chickens[J]. Journal of Applied Poultry Research, 2024, 33(4):100485.

[123]

Alvarenga R R, Rodrigues P B, Zangeronimo M G, et al. Validation of prediction equations to estimate the energy values of feedstuffs for broilers: Performance and carcass yield[J]. Asian-Australasian Journal of Animal Sciences, 2013, 26(10): 1474-1483.

[124]

Guo X, Liu X, Cheng Z, et al. Establishment of prediction equations for available energy values of sorghum in broilers using machine learning and stepwise regression methods[J]. Poultry Science, 2026, 105(7): 106928.

[125]

Meloche K J, Kerr B J, Billor N, et al. Validation of prediction equations for apparent metabolizable energy of corn distillers dried grains with solubles in broiler chicks[J]. Poultry Science, 2014, 93(6): 1428-39.

[126]

Latifi M, Moravej H, Ghaziani F, et al. Determination of prediction equations for apparent metabolizable energy corrected for nitrogen of corn gluten meal and canola meal in broilers[J]. Poultry Science, 2023, 102(5): 102587.

[127]

Li K, Bai G, Teng C, et al. Prediction equations of the metabolizable energy in corn developed by chemical composition and enzymatic hydrolysate gross energy for roosters[J]. Poultry Science, 2024, 103(2=): 103249.

[128]

Lotfi M, Shariatmadari F, Ahmadi H, et al. Estimation and prediction of metabolizable energy contents of wheat bran for poultry[J]. Journal of Agricultural Science and Technology, 2025, 22(4): 965-976.

[129]

Sedghi M, Ebadi M R, Golian A, et al. Estimation and modeling true metabolizable energy of sorghum grain for poultry[J]. Poultry Science, 2011, 90(5): 1138-43.

[130]

De Oliveira C R C, Rabello C B, Rodrigues P B, et al. Nutritional composition and prediction of energy values of poultry offal meal and meat and bone meal for broilers[J]. Tropical Animal Health and Production, 2025, 57(7): 335.

[131]

Soleimani Roudi P, Golian A, Sedghi M. Metabolizable energy and digestible amino acid prediction of wheat using mathematical models[J]. Poultry Science, 2012, 91(8): 2055-62.

[132]

Neme R, Sakomura N K, Fialho F B, et al. Modelling energy utilization for laying type pullets[J]. Brazilian Journal of Poultry Science, 2005, 7(1), 39-46.

[133]

Rabello C B, Sakomura N K, Longo F A, et al. Modelling energy utilisation in broiler breeder hens[J]. British Poultry Science, 2006, 47(5): 622-31.

[134]

Sakomura N K. Modeling energy utilization in broiler breeders, laying hens and broilers[J]. Brazilian Journal of Poultry Science, 2004, 6(1): 1-11.

[135]

Sakomura N K, Longo F A, Oviedo-Rondon E O, et al. Modeling energy utilization and growth parameter description for broiler chickens[J]. Poultry Science, 2005, 84(9): 1363-9.

[136]

Liu W, Lin C H, Wu Z K, et al. Estimation of the net energy requirement for maintenance in broilers[J]. Asian-Australasian Journal of Animal Sciences, 2016, 30(6): 849-856.

[137]

Moscoso-Munoz J E, Chino-Velasquez L B, et al.Camero De La Cuba J, Predicting net energy in broiler chickens using the comparative slaughter technique[J]. Poultry Science, 2025, 104(10): 105569.

[138]

Jiang Q Y, Zheng K C, Ban Z B, et al. A comparative study on predicting energy requirements for layer pullets using mathematical model and machine learning methods[J]. Animal nutrition, 2026.(Accepted)

[139]

Chen J T, He P G, Jiang J S, et al. In vivo prediction of abdominal fat and breast muscle in broiler chicken using live body measurements based on machine learning[J]. Poultry Science, 2023, 102(1): 102239.

[140]

Paneru B, Bist R, Yang X, et al. Tracking dustbathing behavior of cage-free laying hens with machine vision technologies[J]. Poultry Science, 2024, 103(12): 104289.

[141]

Nyalala I, Jiayu Z, Zixuan C, et al. Online chicken carcass volume estimation using depth imaging and 3-D reconstruction[J]. Poultry Science, 2024, 103(12): 104232.

[142]

Khanal R, Choi Y, Lee J. Transforming poultry farming: A pyramid vision transformer approach for accurate chicken counting in smart farm environments[J]. Sensors (Basel), 2024, 24(10):2977.

[143]

Li G, Ji B, Li B, et al. Assessment of layer pullet drinking behaviors under selectable light colors using convolutional neural network[J]. Computers and Electronics in Agriculture, 2020, 172:105333.

[144]

Li G, Hui X, Chen Z, et al. Development and evaluation of a method to detect broilers continuously walking around feeder as an indication of restricted feeding behaviors[J]. Computers and Electronics in Agriculture, 2021, 181:105982.

[145]

You J, Lou E, Afrouziyeh M, et al. Using an artificial neural network to predict the probability of oviposition events of precision-fed broiler breeder hens[J]. Poultry Science, 2021, 100(8): 101187.

[146]

Chang C L, Xu R Y. Optimizing feeding schedule and live-weight prediction for native chicken based on machine learning[J]. Animals (Basel), 2025, 16(1):75.

[147]

Lyu P, Min J, Song J. Application of machine learning algorithms for on-farm monitoring and prediction of broilers’ live weight: A quantitative study based on body weight data[J]. Agriculture, 2023, 13(12):2193.

[148]

Xu Y, Teng G, Zhou Z. Short-term prediction method for gas concentration in poultry houses under different feeding patterns[J]. Agriculture, 2024, 14(11):1891.

[149]

Colovic R, Pezo L, Palic D. Prediction of metabolizable energy content of poultry feedstuffs response surface methodology vs. artificial neural network approac[J]. Bulgarian Journal of Agricultural Science, 2015, 21:1069-1075.

[150]

Liu Z, Qin J, Huang S, et al. Optimization of metabolizable energy prediction models for maize in laying hens by incorporating anti-nutritional factors[J]. Poultry Science, 2026, 105(6): 106776.

[151]

Mariano F C M Q, Lima R R D, Alvarenga R R, et al. Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs[J]. Pesquisa Agropecuária Brasileira, 2020, 55:e01199.

[152]

Chen B L, Cheng T H, Huang Y C, et al. Developing an automatic warning system for anomalous chicken dispersion and movement using deep learning and machine learning[J]. Poultry Science, 2023, 102(12): 103040.

[153]

Liu H W, Chen C H, Tsai Y C, et al. Identifying images of dead chickens with a chicken removal system integrated with a deep learning algorithm[J]. Sensors (Basel), 2021, 21(11):3579.

[154]

Wang J, Wang N, Li L, et al. Real-time behavior detection and judgment of egg breeders based on YOLO v3[J]. Neural Computing and Applications, 2019, 32(10): 5471-5481.

[155]

Solis I L, De Oliveira-Boreli F P, De Sousa R V, et al. Using thermal signature to evaluate heat stress levels in laying hens with a machine-learning-based classifier[J]. Animals (Basel), 2024, 14(13):1996.

[156]

Shi Y, Shi Y, Niu H, et al. Structure optimization and data processing method of electronic nose bionic chamber for detecting ammonia emissions from livestock excrement fermentation[J]. Sensors (Basel), 2024, 24(5):1628.

[157]

De Alencar Nääs I, Da Silva Lima N D, Gonçalves R F, et al. Lameness prediction in broiler chicken using a machine learning technique[J]. Information Processing in Agriculture, 2021, 8(3): 409-418.

[158]

Nolasco Perez I M, Badaro A T, Barbon S Jr, et al. Classification of chicken parts using a portable near-infrared (NIR) spectrophotometer and machine learning[J]. Applied Spectroscopy, 2018, 72(12): 1774-1780.

[159]

Chen M, Gong L, Zhu L, et al. Lipidomics combined with random forest machine learning algorithms to reveal freshness markers for duck eggs during storage in different rearing systems[J]. Poultry Science, 2024, 103(11): 104201.

[160]

Pereira D F, Miyamoto B C B, Maia G D N, et al. Machine vision to identify broiler breeder behavior[J]. Computers and Electronics in Agriculture, 2013, 99: 194-199.

[161]

Pallerla C, Feng Y, Owens C M, et al. Neural network architecture search enabled wide-deep learning (NAS-WD) for spatially heterogenous property awared chicken woody breast classification and hardness regression[J]. Artificial Intelligence in Agriculture, 2024, 14:73-85.

[162]

Grishina L S, Zhigalov A Y, Bolodurina I P, et al. Machine learning-driven analysis of feed additives and intestinal microbiota diversity in broiler chickens: Clustering of mineral profiles and predictive diet modeling[J]. Veterinary World, 2025, 18(11): 3390-3408.