Search Results (435)

Communication in mammals constitutes a complex, multimodal system that integrates visual, acoustic, tactile, and chemical signals whose functions extend beyond simple information transfer to include the regulation of social relationships, coordination of behaviour, and expression of emotional states. This article examines the fundamental mechanisms of communication from biological, neuroethological, and behavioural perspectives, with particular emphasis on domesticated and farmed species. Analysis of sensory signals demonstrates that their perception and interpretation are closely linked to the physiology of sensory organs as well as to social experience and environmental context. In companion animals such as dogs and cats, domestication has significantly modified communicative repertoires ranging from the development of specialised facial musculature in dogs to adaptive diversification of vocalisations in cats. The neurobiological foundations of communication, including the activity of the amygdala, limbic structures, and mirror-neuron systems, provide evidence for homologous mechanisms of emotion recognition across species. The article also highlights the role of communication in shaping social structures and the influence of husbandry conditions on the behaviour of farm animals. In intensive production environments, acoustic, visual, and chemical signals are often shaped or distorted by crowding, noise, and chronic stress, with direct consequences for welfare. Furthermore, the growing importance of multimodal technologies such as Precision Livestock Farming (PLF) and Animal–Computer Interaction (ACI) is discussed, particularly their role in enabling objective monitoring of emotional states and behaviour and supporting individualised care. Overall, the analysis underscores that communication forms the foundation of social functioning in mammals, and that understanding this complexity is essential for ethology, animal welfare, training practices, and the design of modern technologies facilitating human–animal interaction. Full article

To reconcile the intensifying trade-off between chronic water scarcity and escalating forage demand in the Yellow River Basin, this study optimized integrated irrigation and fertilization regimes for silage maize. Leveraging the AquaCrop model, validated by 2023–2024 field experiments and a 35-year (1990–2024) meteorological dataset, we systematically quantified the impacts of multi-factorial water–fertilizer–heat stress under drip irrigation with mulch (DIM) and shallow-buried drip irrigation (SBDI). Model performance was robust, yielding high simulation accuracy for soil moisture (RMSE < 3.3%), canopy cover (RMSE < 3.95%), and aboveground biomass (RMSE < 4.5 t·ha⁻¹), with EF > 0.7 and R² ≥ 0.85. Results revealed distinct stress dynamics across hydrological scenarios: mild temperature stress predominated in wet years, whereas severe water and fertilizer stresses emerged as the primary constraints during dry years. To mitigate these stresses, a medium fertilizer rate (555 kg·ha⁻¹) was identified as the stable optimum, while dynamic irrigation requirements were determined as 90, 135, and 180 mm for wet, normal, and dry years, respectively. Comparative evaluation indicated that DIM achieved maximum productivity in wet years (aboveground biomass yield 70.4 t·ha⁻¹), whereas SBDI exhibited superior “stable yield–water saving” performance in normal and dry years. The established “hydrological year–irrigation method–threshold” framework provides a robust decision-making tool for precision management, offering critical scientific support for the sustainable, high-quality development of livestock farming in arid regions. Full article

Digital twin technology is widely promoted as a transformative step for precision livestock farming, yet no fully realized, engineering-grade digital twins are deployed in commercial dairy or poultry systems today. This work establishes the current state of knowledge on dairy and poultry digital twins by synthesizing evidence through systematic database searches, thematic evidence mapping and critical analysis of validation gaps, carbon accounting and adoption barriers. Existing platforms are better described as near-digital-twin systems with partial sensing and modelling, digital-twin-inspired prototypes, simulation frameworks or decision-support tools that are often labelled as twins despite lacking continuous synchronization and closed-loop control. This distinction matters because the empirical foundation supporting many claims remains limited. Three critical gaps emerge: life-cycle carbon impacts of digital infrastructures are rarely quantified even as sustainability benefits are frequently asserted; field-validated improvements in feed efficiency, particularly in poultry feed conversion ratios, are scarce and inconsistent; and systematic reporting of failure rates, downtime and technology abandonment is almost absent, leaving uncertainties about long-term reliability. Adoption barriers persist across technical, economic and social dimensions, including rural connectivity limitations, sensor durability challenges, capital and operating costs, and farmer concerns regarding data rights, transparency and trust. Progress for cows and chickens will require rigorous validation in commercial environments, integration of mechanistic and statistical modelling, open and modular architectures and governance structures that support biological, economic and environmental accountability whilst ensuring that system intelligence is worth its material and energy cost. Full article

It is known that a mare’s body temperature drops before parturition, but no research has yet applied this thermal change to the prediction of foaling. In this study, the ventral tail base surface temperature (VTB-ST) was recorded by a tail-attached device equipped with a thermistor in pregnant mares kept in an outdoor paddock all day. The objective of the present study was to make an algorithm for predicting nocturnal foaling (18:00 to 6:00) and to verify the accuracy of the algorithm. Prediction of nocturnal foaling was performed at 15:00 every day. The foaling prediction model was validated using 147 days of data recorded from 22 mares. The sensitivity of the foaling prediction model proposed in this study was 68.2 to 81.8% and the precision was 51.4 to 62.5%. To our knowledge, the present study is the first one to establish an algorithm for predicting nocturnal foaling at a specific time interval using VTB-ST. Further study will be necessary to improve the foaling prediction model, as the accuracy of the algorithm proposed in this study was considered to be insufficient for practical use in stud farms. Full article

Poultry farming ranks among the most rapidly expanding sectors of global agriculture, significantly contributing to food availability, improved dietary quality, and economic stability in rural areas. The sector’s efficiency stems from short production cycles and the ability to convert agricultural by-products into high-quality protein, energy, and essential nutrients. Despite these benefits, the growing scale of poultry production raises serious environmental concerns, including intensive use of land and water, high feed demand, and impacts on greenhouse gas emissions, soil nutrient balance, and water quality. This study examines the poultry industry in the Republic of Moldova, where it forms a crucial component of the agricultural economy. Drawing on recent statistical data and scientific literature, the article reviews production dynamics, farm structures, and technological adoption, offering a comprehensive overview of the sector’s current state. The findings highlight both the sector’s essential role in strengthening food security and rural livelihoods and its susceptibility to resource limitations and environmental pressures. The analysis emphasizes the importance of implementing precision livestock farming technologies, improving biosecurity, and promoting environmentally sustainable practices as key strategies for long-term sector resilience. These insights aim to support policymakers and stakeholders in developing effective strategies to ensure a competitive and sustainable poultry industry in Moldova. Full article

Accurate and non-contact identification of individual sheep is important for intelligent livestock management, but remains challenging due to subtle inter-individual differences, breed-dependent facial morphology, and complex farm environments. This study proposes a lightweight sheep face detection and keypoint recognition framework based on an improved YOLO11 architecture, termed SAMS-KLA-YOLO11. The model incorporates a Sheep Adaptive Multi-Scale Convolution (SAMSConv) module to enhance feature extraction across breed-dependent facial scales, a Keypoint-Aware Lightweight Attention (KLAttention) mechanism to emphasize biologically discriminative facial landmarks, and the Efficient IoU (EIoU) loss to stabilize bounding box regression. A dataset of 3860 images from 68 individuals belonging to three breeds (Hu, Dorper, and Dorper × Hu crossbreeds) was collected under unconstrained farm conditions and annotated with five facial keypoints. On this dataset, the proposed model achieves higher precision, recall, and mAP than several mainstream YOLO-based baselines, while reducing FLOPs and parameter count compared with the original YOLO11. Additional ablation experiments confirm that each proposed module provides complementary benefits, and OKS-based evaluation shows accurate facial keypoint localization. All results are obtained on a single, site-specific dataset without external validation or on-device deployment benchmarks, so the findings should be viewed as an initial step toward practical sheep face recognition rather than definitive evidence of large-scale deployment readiness. Full article

Ruminant livestock production faces increasing pressure to reduce environmental impacts while maintaining productivity and food security. This comprehensive review examines current strategies and emerging technologies for enhancing environmental sustainability in ruminant systems. The review synthesizes recent advances across four interconnected domains: genetic and genomic approaches for breeding environmentally efficient animals, rumen microbiome manipulation, nutritional strategies for emission reduction, and precision management practices. Specifically, genetic and genomic strategies demonstrate significant potential for long-term sustainability improvements through selective breeding for feed efficiency, methane reduction, and enhanced longevity. Understanding host–microbe interactions and developing targeted interventions have also shown promising effects on optimizing fermentation efficiency and reducing methane production. Key nutritional interventions include dietary optimization strategies that improve feed efficiency, feed additives, and precision feeding systems that minimize nutrient waste. Furthermore, management approaches encompass precision livestock farming technologies including sensor-based monitoring systems, automated feeding platforms, and real-time emission measurement tools that enable data-driven decision making. Integration of these approaches through system-based frameworks offers the greatest potential for achieving substantial environmental improvements while maintaining economic viability. In addition, this review identifies key research gaps including the need for standardized measurement protocols, long-term sustainability assessments, and economic evaluation frameworks. Future directions emphasize the importance of interdisciplinary collaboration, policy support, and technology transfer to accelerate adoption of sustainable practices across diverse production systems. Full article

Non-invasive and intelligent technologies have been utilized to monitor agricultural systems in real time, facilitating expedient decision-making and the reduction in animal stress in diverse climatic conditions. The objective of this study was to develop a deep learning supervised model to classify Nelore cattle (Bos indicus) into two groups: those in comfort and those under thermal stress. Thirty cattle, aged between 18 and 20 months, were evaluated between June and December 2023, resulting in 676 samples collected across four daily periods (6:00, 12:00, 18:00, and 24:00). Biotic variables included rectal temperature (RT) and respiratory rate (RR), while abiotic variables included air temperature (AT) and relative humidity (RH). The neural network model exhibited an accuracy and recall of 72% but a low specificity of 42%. These metrics indicate that while the model is effective in detecting stress situations, it faces challenges in correctly identifying animals in thermal comfort, likely due to class imbalance and the need for additional input features to capture environmental adaptability. Consequently, it can be posited that supervised learning models are valuable tools for precision livestock farming, provided that discriminatory limitations are mitigated by refining input characteristics and data balancing. Full article

Precision livestock farming (PLF), by integrating multimodal sensor data, provides opportunities to enhance welfare monitoring and management in small ruminants. This study evaluated whether environmental, physiological, and behavioral measurements—including the temperature–humidity index (THI), carbon dioxide (CO₂) and ammonia (NH₃) concentrations measured at the barn level, body condition score (BCS), rectal and ocular temperatures, GPS-derived locomotion metrics, accelerometry data, and fixed animal traits—can serve as key predictors of welfare and productivity in dairy sheep. Data were collected from 90 ewes: all animals underwent the same repeated welfare assessments, while 30 of them were additionally equipped with GPS–accelerometer sensor collars; environmental conditions were continuously recorded for the entire flock, generating 773 complete multimodal records. All predictive models were developed using data from all 90 ewes; collar-derived behavioral variables were included only for individuals equipped with GPS–accelerometer collars. Nine regression methods (linear regression (LR), partial least square regression (PLSR), elastic net (EN), mixed-effects models, random forest (RF), extreme gradient boosting (XGBoost), support vector regression (SVR), neural networks (multilayer perceptron, MLP), and an ensemble of RF–XGBoost–EN were evaluated using a combination of nested cross-validation (CV) and leave-one-animal-out CV (LOAOCV) to ensure robustness and generalization at the individual animal level. Nonlinear models—particularly RF, XGBoost, SVR, and the ensemble—consistently delivered superior performance across traits. For behavioral (e.g., daily distance movement) and thermal indicators (e.g., medial canthus temperature), the highest predictive capacity (R² ≈ 0.60–0.70) was achieved, while moderate predictive capacity (R² ≈ 0.40–0.50 and ≈0.35–0.45), respectively, was observed for respiratory rate and milk yield, reflecting their multifactorial nature. Feature importance analyses underscored the relevance of THI, CO₂, NH₃, concentrations, and BCS across results. Overall, these findings demonstrate that multimodal sensor fusion can effectively support the prediction of welfare and productivity indicators in intensively reared dairy sheep and emphasize the need for larger and more diverse datasets to further enhance model generalizability and model transferability. Full article

Morocco ranked 9th in the 2024 Climate Change Performance Index (CCPI), placing it among the world’s top 10 performers in climate action. Building on this leadership, our review outlines practical and real-world steps to strengthen Morocco’s agricultural efforts to curb greenhouse gases. We base our analysis on a comparison of national communications, updated Nationally Determined Contributions (NDCs), and findings from peer-reviewed research. We identified four main areas where Morocco can boost its impact: advanced livestock methane reduction, systematic soil carbon monitoring, precision nitrogen management, and integrated renewable energy systems. To inform these levers, we studied best practices from other six high-performing countries in the 2024 CCPI—Denmark, Sweden, India, Estonia, the Netherlands, and the Philippines—and considered how their strategies could be adapted to Morocco’s semi-arid, smallholder-dominated farming context. This study delivers four concrete, multi-phase implementation roadmaps spanning 2025–2035. These roadmaps outline the technical steps, regulatory changes, and financial mechanisms. They also specified emissions reduction targets associated with each pillar: 15–30% for livestock methane, 0.3–0.8 tons of carbon per hectare per year for soil carbon sequestration, 18% for precision nitrogen management, and fossil fuel displacement through five renewable energy initiatives. The roadmaps are designed to inform the next update of Morocco’s Generation Green strategy and support the country’s 2030 NDC goal of a 45.5% emission reduction. Full article

Prompt identification of clinical signs and early treatment of hoof problems are essential to effectively manage and reduce lameness in dairy farms. This study aimed to evaluate the influence of days in milk (DIM), parity, and milk yield (MY) on the mean temperature (MT) of the hind hooves in healthy cows, with the perspective of implementing infrared thermography (IRT) as an automated tool for early lameness detection. Thermal images were collected from 156 milking cows, capturing both cranial and caudal surfaces of each hind foot. Significant differences were found between primiparous and multiparous cows across all analyzed surfaces. Moreover, cows with higher milk production exhibited significantly higher MT in the caudal left hoof and on both cranial surfaces. The variable DIM (group 1 = cows with ≤202 DIM; group 2 = cows with >202 DIM) did not significantly affect MT on caudal surfaces; however, on the cranial view, MT of the right hoof was higher in group 2, while group 1 tended to show higher MT in the left hoof (p = 0.051). In conclusion, hoof MT increases in multiparous and high-producing cows. Additionally, during the first 200 days of lactation, cranial hoof surface temperatures tend to rise. Future studies should include continuous monitoring using automated systems to record variations throughout the day. Full article

Body weight and size are critical indicators of sow health and reproductive performance. Traditional manual measurement methods are not only time-consuming and labor-intensive but also induce stress in sows. To address these limitations, we propose an innovative method for estimating sow body weight and size using 3D point cloud data. Our method began by obtaining point cloud data from depth images captured by an Intel^® RealSense™ D455 camera. First, we used a KPConv segmentation model with a deformable kernel to extract the sow‘s back. The resulting back point cloud then served as the input to a novel dual-branch, multi-output regression model named DbmoNet, which integrates features from both location and feature spaces. We evaluated the method on 2400 samples from three breeds during non-pregnant periods. The KPConv model demonstrated excellent performance, achieving an overall segmentation accuracy (OA) of 99.54%. The proposed DbmoNet model outperformed existing benchmarks, achieving mean absolute percentage errors (MAPEs) of 3.74% for body weight (BW), 3.97% for chest width (CW), 3.33% for hip width (HW), 3.82% for body length (BL), 1.94% for chest height (CH), and 2.43% for hip height (HH). Therefore, this method provides an accurate and efficient tool for non-contact body condition monitoring in intensive sow production. Full article

Accurate detection of cattle and sheep is a core task in precision livestock farming. However, the complexity of agricultural settings, where visible light images perform poorly under low-light or occluded conditions and infrared images are limited in resolution, poses significant challenges for current smart monitoring systems. To tackle these challenges, this study aims to develop a robust multimodal fusion detection network for the accurate and reliable detection of cattle and sheep in complex scenes. To achieve this, we propose YOLO-MSLT, a multimodal fusion detection network based on YOLOv10, which leverages the complementary nature of visible light and infrared data. The core of YOLO-MSLT incorporates a Cross Flatten Fusion Transformer (CFFT), composed of the Linear Cross-modal Spatial Transformer (LCST) and Deep-wise Enhancement (DWE), designed to enhance modality collaboration by performing complementary fusion at the feature level. Furthermore, a Content-Guided Attention Feature Pyramid Network (CGA-FPN) is integrated into the neck to improve the representation of multi-scale object features. Validation was conducted on a cattle and sheep dataset built from 5056 pairs of multimodal images (visible light and infrared) collected in the Manas River Basin, Xinjiang. Results demonstrate that YOLO-MSLT performs robustly in complex terrain, low-light, and occlusion scenarios, achieving an mAP@0.5 of 91.8% and a precision of 93.2%, significantly outperforming mainstream detection models. This research provides an impactful and practical solution for cattle and sheep detection in challenging agricultural environments. Full article

The demand for food is increasing with the rise in the human population. Among foods, meat is an essential part of human nutrition. Meat provides good-quality protein and all the micronutrients needed by humans. In addition, it also contains some bioactive compounds that are good for human health. Increasing demand, together with concerns over food safety, requires new approaches to guarantee a sustainable, safe, and healthy meat supply chain. The only way to get over these challenges is through technological innovations that are capable of enhancing the safety, quality, and sustainability of meat. Herein, this review identifies the need for new methods of rapid microbial detection, biosensors, AI-based monitoring, innovative processing and preservation techniques, precision livestock farming, resource-efficient feed and water management, alternative protein sources, and circular economy approaches. In particular, this review examines some meat analogs like cultured meat, hybrid products, and microbial proteins as environmentally friendly and nutritionally balanced alternatives. These changes in technology can also bring benefits to consumers in terms of their health. The health benefits of these technological innovations for consumers go beyond just safety, including improved nutritional profiles, functional bioactive ingredients, and the prevention of antimicrobial resistance. The review further analyzes policies, regulatory frameworks, and ethical considerations necessary to achieve consumer trust and social acceptance, including the global alignment of standards, certification, labeling, and all issues related to ethics. Furthermore, AI, IoT, Big Data, and nutritional technologies represent new emerging trends able to unleash new opportunities for the optimization of production, quality control, and personalized nutrition. Full article

Extensive goat farming is the dominant livestock system in the Mediterranean region, where woody rangelands represent essential forage resources for goats. Understanding how goats move and select vegetation within these heterogeneous landscapes–and how these patterns are shaped by herding decisions-is critical for improving grazing management. This study investigated the spatio-temporal movement behavior of a goat flock in a complex woody rangeland using GPS tracking combined with GIS-based vegetation and land morphology mapping. The influence of seasonal changes in forage availability and the shepherd’s management on movement trajectories and vegetation selection was specifically examined over two consecutive years. Goat movement paths, activity ranges, and speed differed among seasons and years, reflecting changes in resource distribution, physiological stage, and herding decisions. Dense oak woodland and moderate shrubland were consistently the most selected vegetation types, confirming goats’ preference for woody species. The shepherd’s management—particularly decisions on grazing duration, route planning, and provision or withdrawal of supplementary feed—strongly affected movement characteristics and habitat use. Flexibility in adjusting grazing strategies under shifting economic conditions played a crucial role in shaping spatial behavior. The combined use of GPS devices, GIS software, vegetation maps, and direct observation proved to be an effective approach for assessing movement behavior, forage selection and grazing pressure. Such integration of technological and classical methods provides valuable insights into diet composition and resource use and offers strong potential for future applications in precision livestock management. Real-time monitoring and decision support tools based on this approach could help farmers optimize grazing strategies, improve forage utilization, and support sustainable rangeland management. Full article