Search Results (502)

Respiratory disease remains a major challenge in pig production. This two-room pilot study evaluated whether room-level acoustic monitoring combined with physiological measurements could provide an early warning after an experimental Klebsiella pneumoniae challenge. Forty growing pigs balanced by sex and body weight were housed for 28 days in one control room and one challenged room (20 pigs/room; four pens/room). Challenged pigs were intranasally inoculated on days 8, 12, 16, and 20 with a culture whose dose was retrospectively verified by serial-dilution plating. Nasal and fecal samples were cultured on Klebsiella ChromoSelect agar, and colonies with expected morphology were enumerated as presumptive Klebsiella/K. pneumoniae colonies. A fine-tuned Audio Spectrogram Transformer (AST) classified five sound classes from facility-specific audio and was evaluated by group-blocked hold-out testing, five-fold group-blocked cross-validation, temporal deployment validation, and window-threshold sensitivity analysis. The model achieved hold-out macro-F1 of 0.947, five-fold macro-F1 of 0.928 ± 0.019, and 24 h deployment macro-F1 of 0.914. Presumptive nasal bacterial load was higher in challenged pigs at 1-week post-inoculation (log₁₀ 4.03 vs. 0.67). Group-size-standardized cough detections were also higher in the challenged room (54.84 vs. 36.80 detections/day), and daily coughing first exceeded the baseline threshold on day 8. Thresholds of 0.764 (control) and 1.115 (treatment) were obtained from an integrated score that included coughing, sneezing, ear temperatures, rectal temperature, and respiration rate; the treatment score and treatment–control contrast score first surpassed the threshold on day 8, and daily multimodal scores varied between groups (t = −6.636, p < 0.001). Integrated score improved discrimination of post-inoculation disturbance compared with cough detections alone (leave-one-day-out AUROC: 0.94 vs. 0.88). Because each condition was represented by one room, findings are exploratory temporal contrasts, not replicated treatment effects or a stand-alone diagnostic test. Full article

The Binglangjiang buffalo, the only indigenous river-type buffalo in China, poses significant challenges for automated keypoint detection due to its uniformly black, low-texture coat, poor foreground–background contrast, and scarcity of annotated training samples. To address these challenges, this study constructs a benchmark dataset of 10,834 lateral-view images covering 424 individuals, annotated with 10 body measurement keypoints following standardized buffalo measurement protocols. A keypoint detection pipeline is developed by adapting DINOv2 with a top-down heatmap regression head under a single-view imaging setup, reducing hardware complexity for practical farm deployment. Benchmarking against YOLOv8 series and a standard ViT baseline shows that DINOv2-Base achieves 96.51% mAP, surpassing YOLOv8m by 5.6 percentage points. Compared to standard ViT, DINOv2 demonstrates more stable localization across keypoints under model scaling. Specifically, on the scapular tip (P8), a particularly low-texture region, DINOv2 exhibits only 0.28% mAP fluctuation versus 0.82% for standard ViT, indicating greater robustness to limited training data and low-contrast imaging. Body measurement validation on 20 individuals yields MAPE values of 1.76–5.69% across five measurements, confirming reliable non-contact measurement performance. The dataset and pipeline provide practical support for precision livestock management of endangered breeds. Full article

Goat production in Peru is primarily carried out under extensive systems shaped by climatic variability, forage seasonality, infrastructure limitations, and persistent sanitary pressure. In this context, Creole goats represent a strategic animal genetic resource due to their capacity to adapt to arid and high-Andean environments. This review integrates the available evidence on production typologies in the main goat-producing regions of the country, the major sanitary and structural bottlenecks, and the state of the art of genomic, multi-omics, and reproductive biotechnology tools applicable to goats. It discusses how the transition from traditional markers to SNP genotyping, together with functional approaches such as microbiome analysis, transcriptomics, and proteomics, can contribute to understanding the biological basis of complex traits related to resilience, feed efficiency, and reproductive performance. Likewise, the potential of precision livestock farming to generate longitudinal phenotypes and strengthen genetic improvement programs in low-input systems is highlighted. Finally, priorities and considerations are outlined to advance the integration of phenotyping, genomics, and reproductive biotechnologies in extensive contexts, with emphasis on the generation of systematic data, interinstitutional coordination, and technology transfer aimed at the sustainability and conservation of goat resources. These insights may also inform genetic improvement strategies in other developing countries facing similar environmental and structural constraints in low-input goat production systems, particularly in arid and semi-arid regions. Full article

Traditional rectal temperature measurement in pigs induces stress in animals, imposes a heavy labor burden on staff, and increases the risk of cross-infection. This study proposes a non-invasive deep learning approach to predict porcine rectal temperature by combining infrared thermal images of thermal windows with environmental parameters. A multimodal dataset is constructed by synchronously collecting thermal images, environmental parameters, and actual rectal temperatures. Mask Region-based Convolutional Neural Network (Mask R-CNN), You Only Look Once version 8 small (YOLOv8s), and YOLOv11s are employed to automatically detect or segment thermal window regions, from which the maximum temperature of each region is extracted. To enhance model generalization under varying environmental conditions, a two-stage hybrid regression framework is established. In this framework, a Convolutional Neural Network (CNN) extracts spatial features from thermal images, a fully connected network (FCNN) encodes regional surface temperatures and environmental parameters, and a Transformer module captures cross-modal dependencies to generate a preliminary prediction. Subsequently, a Random Forest (RF) regressor is applied for residual correction and final output optimization. Comparative experiments on single-region, dual-region, and triple-region combinations demonstrate that the “eye + vulva” dual-region scheme yields the optimal performance, with a mean absolute error (MAE) of 0.1796 °C and a coefficient of determination (R²) of 0.8212. The prediction error of this scheme is reduced by 42.3% compared with the best-performing unimodal model. The proposed method provides a fast, accurate, and stress-free solution for porcine body temperature monitoring, thereby supporting the development of intelligent health management in livestock farming. Full article

Spatial and temporal heterogeneity in pasture quantity and nutritive value remains a major constraint to efficient nutritional management in grazing-ruminant systems. This critical narrative review was based on targeted searches of peer-reviewed literature on pasture heterogeneity, forage quality assessment, grazing management, animal monitoring, and data integration in grazing-ruminant systems, with emphasis on both recent studies and conceptually foundational work. Precision technologies have emerged as complementary tools that can improve the characterization of pasture resources, animal responses, and grazing dynamics, but their value depends on whether they support nutritionally relevant decisions under field conditions. This review examines current precision approaches, such as portable near-infrared spectroscopy, proximal and remote sensing, geospatial tools, animal-mounted sensors, and grazing-control technologies, and their capacity to improve decisions related to supplementation, stocking rate, grazing rotation, and pasture allocation. Across technologies, performance and applicability vary substantially with observational scale, calibration requirements, and validation context. This review also highlights persistent constraints, including calibration robustness, transferability across systems, field validation, interoperability, economic feasibility, and barriers to routine adoption. Precision tools can improve pasture-based nutritional management, but their practical contribution depends on how effectively they are validated, integrated, and translated into decision-support logic under commercial grazing conditions. Full article

The Performance Efficiency Factor (PEF) is a key composite metric in broiler production that integrates livability, average body weight, feed conversion ratio (FCR) and age. While tree-based machine learning models have shown promising results for live-weight prediction, they often struggle with temporal dependencies and sparse mortality data. This study evaluates five tree-based algorithms, Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and Category Boosting (CatBoost) on daily sensor data from commercial broiler farms. Data were stratified into six age categories, pre-processed with outlier retention and feature engineering, and assessed using R², RMSE, MAE, paired t-tests for statistical significance and SHapley Additive exPlanations (SHAP) for explainability. Cross-farm validation was performed to assess generalizability. The models achieved high accuracy for live-weight prediction (R² up to 0.97, RMSE as low as 9.23 g in mid-cycle categories), with Random Forest and LightGBM performing best. Mortality prediction remained challenging (R² −1.63 to 0.53) due to its sparse and stochastic nature. Nevertheless, Day 21 to Day 28 PEF forecasts showed relative errors of only 4.42–5.40%, as live-weight predictions dominated the PEF calculation. SHAP analysis consistently identified bird age, feed intake per bird and temperature as the most influential predictors. Tree-based models offer a robust, interpretable and computationally efficient solution for live-weight and PEF forecasting in commercial broiler production. The findings support proactive farm management and highlight the need for hybrid approaches to improve mortality prediction. Full article

Digital technologies are increasingly recognized as key tools for improving productivity and supporting rural development in agricultural systems. However, their effective adoption by small-scale producers remains limited in many developing regions. This study analyses the determinants of mobile application adoption among livestock farmers in Amazonas, Peru. Using a structural equation model (PLS-SEM) based on survey data from 160 producers in rural areas, the results show that perceived ease of use is the main driver of adoption, directly influencing farmers’ intention to use mobile applications and significantly determining perceived usefulness, which acts as a key mediating factor. Despite widespread smartphone ownership, their use is largely limited to communication and social media rather than production management, mainly due to barriers such as mistrust, limited rural connectivity, and insufficient digital knowledge. The findings suggest that effective adoption requires integrated strategies that combine the development of user-friendly applications, the demonstration of their economic benefits for producers, and public policies aimed at improving digital infrastructure and strengthening digital skills. By identifying the key determinants of adoption, this study contributes to understanding how mobile technologies can support productivity improvements and promote rural development in livestock systems in the Peruvian Amazon. Full article

The agricultural sector, particularly animal production, faces numerous unprecedented challenges driven by climate change, resource depletion, and an ever-growing global demand for quality food. These challenges are further compounded by the increasing environmental impact of livestock farming, including greenhouse gas emissions, overuse of water and land resources, and the destruction of vital ecosystems. Ensuring the sustainability of animal production systems while mitigating the negative environmental impacts of these factors is essential for future global food security. As the demand for animal-derived products continues to rise, there is a pressing need for innovations that can enhance productivity without compromising environmental integrity or animal welfare. Artificial intelligence (AI) has emerged as a transformative technology with the potential to revolutionize the animal production industry. AI-driven solutions offer promising avenues for optimizing production efficiency, enhancing animal health and welfare, and reducing the environmental footprint of livestock farming. Machine learning, sensor technologies, and advanced data analytics are being increasingly utilized to monitor and predict various aspects of animal farming, such as feed efficiency, disease prevention, and climate resilience. These technologies enable farmers to make data-driven decisions, fostering more sustainable and environmentally responsible practices. This review examines the integration of AI into animal production systems, emphasizing its applications in climate change mitigation, resource management, and advancing sustainability. The discussion addresses how AI technologies can be utilized to improve productivity while minimizing environmental impact and enhancing animal welfare. Additionally, the paper outlines future opportunities, challenges, and potential barriers to integrating AI technologies into livestock farming, thereby ensuring long-term sustainability amid global challenges. Full article

Accurate instance segmentation is essential for precision livestock farming, as it supports individual tracking, posture analysis, body-shape measurement, and other downstream visual monitoring tasks. However, dairy goat segmentation in dense barn scenes remains challenging because frequent mutual occlusion, instance adhesion, partial visibility, and non-rigid posture variation often lead to incomplete masks and ambiguous instance boundaries. To address these challenges, this study develops RF-GoatDet, a real-time instance segmentation framework for dairy goats built upon RT-DETR. The main component of the proposed framework is an Adaptive Receptive Field Encoder (ARFE), which enhances feature encoding by adapting the effective receptive field to irregular goat contours, scale variation, and partially visible body regions. In addition, Coordinate Attention is introduced to strengthen direction-aware spatial representation, while a Query-Conditioned Dynamic Mask Head is used to generate instance-specific masks and improve the separation of adjacent goats. A dairy goat instance segmentation dataset containing 2288 annotated images was constructed, and a two-stage cleaning procedure was applied to reduce redundancy and visual anomalies. Experimental results show that RF-GoatDet achieves 46.5% mask AP and 62 FPS on this dataset, improving the RT-DETR baseline by 4.2 percentage points in mask AP while maintaining real-time inference. These results demonstrate that the proposed ARFE-centered framework effectively improves mask quality and instance discrimination in dense dairy goat scenes, providing a robust and efficient solution for real-time visual monitoring in precision livestock farming. Full article

Accurate determination of morphometric body measurements is essential for monitoring growth, evaluating production traits, and supporting selection decisions in cattle breeding. However, traditional measurement methods require direct contact with animals, which may increase labor requirements, negatively affect animal welfare, and pose safety risks for operators. This study evaluated the relationship and agreement between traditional tape measurements and smartphone-camera-based morphometric measurements in cattle. A total of 100 cattle raised in the Mediterranean region of Türkiye, including 50 Holstein and 50 Simmental animals, were included in the study. Withers height, body length, rump height, and forechest width were measured using both conventional tools and a smartphone-camera-based method. Regression analyses demonstrated strong linear relationships between methods, particularly for body length and withers height (R² = 0.564–0.961). Bland–Altman analysis revealed small but significant systematic differences between methods, with camera-based measurements generally producing slightly higher values than tape measurements. The strongest agreement was observed for body length measurements, whereas wider limits of agreement were detected for anatomically complex traits, such as rump height and forechest width. Although the findings support the potential applicability of smartphone-based morphometric measurements as a practical and contactless alternative under field conditions, measurements were obtained only from a single lateral view, which should be considered an important methodological limitation. Future studies using multi-view or three-dimensional imaging systems may further improve measurement accuracy and agreement. Full article

This study comprehensively explores the environmental implications of two feeding strategies in pig farming, focusing on three scenarios: Brazilian tables (BT-2017), NRC (NRC-2012), and AGPIC (AGPIC-2021). The comparison involves conventional phase-feeding (CON) and the daily fit model (DFM). The five-phase system provided the same diet to all pigs within a group during each proposed phase. In contrast, the DFM adjusted the diet based on the nutritional requirements of pigs, anticipating subsequent diets through daily adjustments. We employed a cradle-to-gate approach, with the functional unit defined as one barrow with an initial body weight of 20.61 ± 0.85 kg, raised to 138.94 ± 0.90 kg over a 120-day growing-finishing period. Input data were sourced from observed commercial records from pig farms in Brazil, including over 1,000,000 data points from pigs raised under standard industry conditions. We evaluated the impact of the life cycle by considering factors such as acidification, climate change, ecotoxicity, eutrophication, land use, resource use, and water use. The OpenLCA software (version 1.11.0) and the Environmental Footprint 3.0 impact assessment method were used. Our results indicate that the DFM consistently outperforms the CON strategy in terms of reducing environmental impacts. Among the three scenarios, BT-2017 results in higher environmental impact reductions compared with NRC-2012 and AGPIC-2021. This is due to the higher concentration of corn and soybean meal in diets. Notable reductions include in relation to land use-related climate change impacts (12.55%), freshwater eutrophication (6.21%), mineral and metal resource depletion (6.11%), and fossil resource use (4.88%). These findings highlight that even modest adjustments to feeding strategies can effectively reduce the environmental footprint of pig farming. Full article

Continuous and objective monitoring of livestock behavior plays a key role in precision farming, animal welfare assessment, and reproductive management. This study proposes a non-invasive framework for sheep behavior and reproductive activity monitoring that integrates wearable actigraphy, machine learning, and a cloud-based data processing architecture. Tri-axial accelerometer data were collected at 30 Hz using collar-mounted ActiGraph sensors under real farming conditions. Raw acceleration signals were processed without temporal aggregation, preserving full temporal resolution that includes axis-specific acceleration, vector magnitude, and delta magnitude features. Several supervised learning models were evaluated for behavior classification, including BLSTM, LSTM, CNN–BLSTM, Random Forest, and Support Vector Machine, targeting behaviors such as standing, walking, grazing, lying, flehmen, and mating. The results indicate that both deep learning and classical machine learning approaches achieve high classification performance, with Random Forest obtaining an overall accuracy of 0.82, while deep sequential models effectively capture temporal patterns and behavioral transitions. Furthermore, a scalable cloud architecture is introduced to automate data ingestion, preprocessing, inference, storage in InfluxDB, and visualization through an interactive web application. The proposed framework supports continuous monitoring and offers practical tools for precision livestock management. Full article

Skeletal muscle satellite cells are indispensable for muscle growth and regeneration, and their myogenic differentiation is precisely controlled by transcription factors. As a core member of the TEAD family, TEAD4 participates in various biological processes, yet its function and regulatory mechanism in porcine skeletal muscle satellite cells (PSCs) remain largely unknown. High-purity PSCs were isolated and identified from 7-day-old Large White piglets. Combined approaches of siRNA-mediated TEAD4 knockdown, RT-qPCR, Western blotting, immunofluorescence, EdU assays, and transcriptome sequencing were applied to explore the role of TEAD4 during myogenic differentiation. TEAD4 expression was gradually upregulated during PSC differentiation and positively correlated with myogenic marker genes. Knockdown of TEAD4 did not affect PSC proliferation but significantly suppressed myogenic differentiation, as indicated by reduced expression of myogenic genes and blocked myotube formation. Transcriptomic analysis demonstrated that DEGs were highly enriched in metabolic pathways, particularly the AMPK signaling pathway. TEAD4 knockdown led to excessive upregulation of PRKAG3 and prominent induction of SLC2A4. Collectively, these results indicate that TEAD4 promotes myogenic differentiation in PSCs, likely by maintaining metabolic homeostasis. This study provides the first characterization of TEAD4 in porcine skeletal muscle satellite cells and demonstrates that it promotes myogenic differentiation. Full article

Intensive pig farming presents substantial challenges for individual health monitoring due to high stocking densities, complex occlusion scenarios, and the need for continuous real-time surveillance. Existing monitoring approaches rely heavily on manual inspection, which is labor-intensive and prone to delayed detection of abnormal behaviors and disease symptoms. This study proposes an embedded intelligent monitoring system integrating a pan-tilt gimbal platform with an improved multi-object tracking and anomaly detection framework for automated pig health surveillance. The system employs a modified Periodfill_DeepSORT algorithm that incorporates a ReID network with appearance features and motion prediction trajectories to maintain identity consistency under occlusion and re-entry scenarios. For anomaly detection, a lightweight YOLOv8-based network was trained on 772 abnormal samples across three behavioral categories: movement abnormalities, postural abnormalities, and disease-related abnormalities. Experimental results demonstrate that the Periodfill_DeepSORT algorithm achieves a Multiple Object Tracking Accuracy (MOTA) of 95.34%, a Multiple Object Tracking Precision (MOTP) of 94.77%, and an IDF1 score of 96.88%, with only 12 identity switches across 2000 frames involving 12 targets—27 fewer than the standard DeepSORT algorithm. In occlusion scenarios, MOTA improved from 61.1% to 78.3%. The anomaly detection network achieves an overall detection accuracy of 94.5%, representing an 8.8 percentage point improvement over the baseline model, with recognition accuracies of 96.2% for movement abnormalities, 94.1% for postural abnormalities, and 92.8% for disease-related abnormalities. The system operates at 90 frames per second on embedded hardware with a power consumption of 3.2 watts and a startup time of approximately 1 s, with gimbal angle errors maintained within 3°. These results demonstrate the system’s effectiveness and practical feasibility for real-time intelligent health monitoring in intensive livestock farming environments. Full article

Background: Agroecology is increasingly discussed as a strategic response to the combined challenges of drought, ecological degradation, and rural vulnerability. In Morocco, this debate has become particularly urgent because agriculture now operates under persistent hydro-climatic stress, declining water availability, and strong territorial disparities between rainfed, irrigated, mountain, and oasis systems. Methods: This article is based on a structured critical review combined with an interpretive bibliometric synthesis of Moroccan and North African literature on agroecology, water stress, agricultural transition, and food-system resilience. The review was organized through conceptual framing, targeted source selection, thematic screening, and integrative synthesis. Results: Morocco is not an agroecological blank slate. Practices compatible with agroecological transition already exist across the country, including crop diversification, legume rotations, crop–livestock integration, biological regulation, organic amendments, and multifunctional production systems. However, previous reviews have mainly documented practices, projects, or sustainability initiatives without fully explaining why these remain weakly connected, poorly scaled, and insufficiently institutionalized under Moroccan conditions. This review shows that the principal barrier is not the absence of relevant practices but the absence of a coherent transition architecture capable of aligning water governance, farm economics, advisory systems, public incentives, territorial differentiation, and market valorization. The Moroccan case reveals a central paradox: agroecology is most necessary precisely where the structural conditions for its adoption are most fragile. To capture this contradiction, the paper proposes the concept of a Hydro-Agroecological Transition Trap, defined as a condition in which worsening water stress simultaneously intensifies the need for agroecological redesign and reduces the ability of farms and institutions to implement it. Conclusions: The manuscript concludes by proposing a six-pillar transition framework for Morocco based on water-smart agroecology, territorially differentiated pathways, participatory innovation, transition finance and risk-sharing, market construction, and multidimensional assessment. The originality of the study lies in shifting the analysis from a shortage of practices to a shortage of transition architecture, thereby contributing to international debates on agroecological scaling under chronic hydro-climatic stress. Full article