Search Results (670)

Precision livestock farming (PLF) integrates sensing technologies, data acquisition (DAQ) systems, and machine learning (ML) frameworks to continuously monitor individual animals and support welfare assessment through physiological and behavioral observations. Advances in infrared thermography, radar sensing, vision-based systems, acoustic monitoring, and wearable technologies have substantially expanded the ability to collect high-resolution data describing animal responses to internal and external stimuli. However, despite considerable technological progress, a persistent gap remains between sensing performance demonstrated under controlled experimental conditions and reliable deployment within commercial livestock environments. This gap is characterized by environmental variability, unrestricted animal movement, and operational constraints within commercial environments. Using a structured review methodology, this review examines sensing modalities, embedded DAQ architectures, communication strategies, ML methodologies, data privacy, farmer adoption, and an illustrative engineering workflow through the lens of welfare-relevant physiological characteristics. Emphasis placed on the distinction between direct sensor measurements and the biological processes they represent. Sensor outputs do not directly quantify welfare, stressors, or management outcomes; rather, they provide measurements of physiological and behavioral responses that require appropriate biological context for meaningful interpretation. As a result, welfare assessment does not depend solely on the ability to acquire data, but also on the ability to accurately relate those data to underlying physiological mechanisms. Within this framework, ML serves as a critical bridge between measurement and interpretation by enabling the analysis of complex, multimodal datasets. Future advancement of welfare-oriented PLF systems will require stronger alignment among sensing methodologies, physiological understanding, and practical deployment realities to generate meaningful, scalable, and biologically grounded welfare assessments. Full article

Farm animal welfare research increasingly recognizes that farmers’ welfare decisions are shaped by ethical orientations. This study examines associations between livestock farmers’ contextual anthropocentrism, personality traits, farm structural characteristics, and links to animal welfare attitudes. Survey data from 619 German livestock farmers were analyzed using descriptive statistics, reliability analysis, correlations, and an ordinary least squares regression model. An anthropocentric orientation index (AOI) showed acceptable internal consistency (Cronbach’s alpha = 0.72; mean = 3.68 on a 1–5 scale). Higher emotionality, agreeableness, and openness were negatively associated with anthropocentric orientation. Organic farming, keeping of suckling cows, dairy cows, and laying hens were also negatively associated with anthropocentric orientations. The model explained a modest share of variance (R² = 0.147; adjusted R² = 0.119). Correlations indicated that higher anthropocentric orientations were more closely aligned with appreciation of biological functioning indicators and less aligned with positive welfare indicators, including species-typical behavior and natural outdoor access. The findings indicate tentatively that contextual anthropocentrism among livestock farmers might be operationalized empirically and might be linked to personality, farm structure, and welfare interpretation. Future research should show if contextual anthropocentrism may inform more differentiated animal welfare communication that accounts for farmers’ distinct ethical and practical animal welfare orientations. Full article

Lameness remains one of the most significant welfare and economic challenges in modern dairy production. Traditional detection methods, particularly visual locomotion scoring, are limited by subjectivity, inconsistent application, and infrequent monitoring, which often delays the recognition of painful lesions. This review synthesizes recent validation studies of automated lameness detection (ALD) technologies and evaluates their diagnostic performance, validation design, and practical implementation across dairy systems. Studies were screened for relevance by a single reviewer based on title, abstract, and full-text content. Included studies represented sensor-based, pressure-based, vision-based, and multimodal detection platforms, with reported accuracies ranging from approximately 70% to 98% depending on modality and environmental setting. Vision-based systems demonstrated strong performance in controlled conditions, whereas field-validated systems showed more moderate but potentially more generalizable accuracy. Pressure-based platforms reported high diagnostic discrimination via area under the curve (AUC) analysis but face infrastructural limitations in commercial settings. Risk-of-bias assessment indicated that controlled experimental studies without external validation may overestimate deployment performance. Despite technological advances, variability in validation protocols, lesion thresholds, and environmental robustness limits direct comparison across systems. Future research should prioritize multi-farm external validation, standardized benchmarking frameworks, and multimodal integration within precision livestock farming ecosystems to improve reliability and adoption. Full article

Cattle producers must balance animal welfare with productivity, but regular observation of animals in extensively managed operations is often impractical. Artificial intelligence (AI) integrated with computer vision offers an automated alternative, but few studies compare object detection architectures within the same dataset or focus on pastured cattle. Groups (n = 2–7) of heterogeneous beef cattle were recorded on pasture with nine solar trail cameras. Footage (~132 h) was curated in VideoLAN; annotated in Computer Vision Annotation Tool (CVAT) with bounding boxes and behavioral classes; and split 62/21/17% into training (24,508 frames), validation (8231 frames), and testing (6625 frames) sets. Four architectures were trained: Faster R-CNN (ResNet-50 FPN), Single Shot MultiBox Detector (SSD300, VGG-16), RetinaNet (ResNet-50 FPN with focal loss), and YOLOv8 nano (Ultralytics). With validation at 0.50 confidence and 0.50 IoU, Faster R-CNN achieved the highest overall F1 (0.79) and best per-class balance; RetinaNet was intermediate (peak F1 = 0.72); SSD300 saturated at F1 = 0.40; and YOLOv8 nano achieved some minority class recall at lower confidence. Each model detected the classes “grazing” and “hay feeding” accurately but confused cattle with the visually similar “normal” class. Datasets, checkpoints, and analysis scripts are provided to support further refinement of AI-enabled monitoring of extensive cattle systems. Full article

This paper examines the macro–micro impact of drought in South Africa using a computable general equilibrium model calibrated to the structure of the South African economy. Drought is represented as a severe supply-side shock: a 50% decline in total factor productivity in agriculture, forestry and fishing. The analysis traces how this shock is transmitted from agricultural production to prices, trade, employment, household income, consumption and welfare. The results show that agricultural output falls by 19.5%, agricultural prices rise by 43.3%, and agricultural imports increase by 84.8% as the economy shifts towards external supply. These sectoral effects generate wider macroeconomic losses, including a 1.0% decline in real GDP, a 1.7% increase in unemployment, a 1.2% fall in household income and a 1.5% reduction in household consumption. Welfare declines for both rural and urban households, but rural households experience larger losses because of their stronger dependence on agriculture, farm income, livestock assets and food markets. The findings show that drought is not only an agricultural or hydrological event; it is an economy-wide and distributional shock transmitted through production, price, trade and labour-market channels. Although imports help to cushion domestic scarcity, they do not fully offset higher prices or welfare losses. Policy responses should therefore combine drought-resilient agricultural investment, water-resource resilience, targeted social protection, food-supply stabilisation and rural livelihood diversification. Full article

Accurate cattle pose estimation is important for precision livestock farming because body landmarks can provide quantitative visual inputs for potential health monitoring, behavior analysis, lameness assessment, and welfare evaluation. This study focuses on keypoint-localization performance and provides a foundation for future task-specific studies of these downstream outcomes. However, real farm images commonly contain inter-cattle occlusion, cluttered backgrounds, small anatomical landmarks, and visually similar animals, which limit the reliability of existing one-stage pose estimators. This study proposes LEC-Pose, a hierarchical locality refinement framework for occlusion-robust cattle pose estimation. Built on YOLOv8-Pose, LEC-Pose first predicts cattle boxes and auxiliary coarse keypoints, then extracts instance-level ROI features to recover local anatomical evidence. A lightweight refinement network directly predicts the final keypoints from heatmaps and offsets on enhanced ROI features. The detected boxes guide the ROI pathway, while the initial keypoints remain auxiliary outputs. During training, an instance-level contrastive loss regularizes a compact global ROI descriptor. During inference, pair construction and contrastive-loss computation are removed, while descriptor fusion remains in the prediction path. Across three runs on CattleEyeView, LEC-Pose reaches 39.47 ± 0.33 mAP@50:95, compared with 33.91 ± 0.28 for YOLOv8-Pose, while running at 111.6 FPS versus 138.2 FPS for YOLOv8-Pose, corresponding to a 19.2% throughput reduction on the evaluated RTX 4090. On NWAFU-Cattle, it obtains 76.08 ± 0.36 and 80.03 ± 0.38 mAP@50:95 under the 50%/50% and 80%/20% protocols, respectively; the former is comparable to FSMC-Pose, whereas the latter is the highest mean among the three repeated principal models. An end-to-end zero-shot evaluation on three external cattle datasets, second-dataset occlusion analysis, detailed module combinations, and descriptor diagnostics further assess the framework within their stated protocols. These results suggest that LEC-Pose can serve as a pose-estimation component for future automated cattle monitoring, and future task-specific studies can connect these keypoints to health, behavior, and welfare outcomes. Full article

Climate change is transforming heat stress (HS) from a seasonal challenge into a major constraint on the sustainability of dairy cattle production. Increasing temperatures, more frequent and prolonged heat waves, and reduced opportunities for nocturnal recovery adversely affect animal health, welfare, productivity, reproductive performance, and resource-use efficiency. This narrative review provides an integrated critical synthesis of current evidence on HS in dairy cattle within a sustainable development framework. It examines the biological mechanisms underlying disruption of homeostasis together with the consequences for milk production, product quality, health, welfare, reproduction, and developmental programming. The review further evaluates biomarkers of thermal adaptation, precision livestock farming, and environmental, nutritional, managerial, genetic, and technological mitigation strategies, considering their biological effectiveness, practical applicability, economic feasibility, and environmental trade-offs. Rather than addressing these components independently, the review integrates their interactions within an original conceptual framework and comparatively evaluates adaptation strategies to support practical decision-making. Current evidence indicates that sustainable climate adaptation requires integrated, context-specific approaches combining environmental management, nutrition, genetic improvement, precision monitoring, and digital technologies. Future progress will increasingly depend on advances in omics, artificial intelligence, and predictive livestock management to enhance climate resilience while improving productivity, animal welfare, and environmental sustainability. Full article

This review analyzes sustainable and regenerative development in the beef production chain, focusing on environmental impacts and pasture-based cattle farming. Livestock emissions account for about 14.5% of global anthropogenic greenhouse gases, with beef cattle contributing 3–3.2% mainly from enteric fermentation and manure management. Pasture-based cow-calf operations generate 60–70% of these emissions, posing significant challenges for producers. Improper grazing degrades soil and vegetation, reducing productivity, while climate change and technology introduce new animal health issues. At the same time, given that beef is an important food item worldwide, it is important to strive for the regenerative management of beef cattle farming. This article lists possibilities for researchers, beef cattle breeders, and farmers to follow and implement, in the hope that the sector will become regenerative. Scientific innovation in grazing-based beef cattle systems should focus on precision livestock monitoring, regenerative pasture management, genetic selection, and improving animal health, as well as identifying opportunities within the value chain. Such innovations could help to optimize productivity, enhance sustainability, improve animal welfare, and generate new income streams through ecosystem services or premium grass-fed markets. Full article

Background: Cultured meat (CM) has emerged as a promising, albeit controversial, alternative to conventional livestock production, offering potential benefits in terms of sustainability, animal welfare, and resource efficiency. Despite these potential advantages, consumer acceptance remains uncertain, particularly in countries where CM is not yet commercially available. Objectives: this study investigates the determinants of willingness to try (WTT) cultured meat among Italian university students (n = 335), with particular attention to the role of product-related perceptions and personal values and motivations. Methods: data were collected through an online survey and analyzed using binary logistic regression to identify the main drivers of respondents’ willingness to try CM. Results: the findings suggest that acceptance of CM among university students is driven primarily by familiarity, perceived safety, and ethical considerations, particularly those related to animal welfare, rather than by demographic characteristics or resistance to novel food technologies. Conclusions: these findings offer practical implications for policymakers and industry stakeholders, highlighting the importance of transparent communication strategies emphasizing product safety and animal welfare benefits as a means of increasing familiarity with and acceptance of CM among younger consumers. Full article

Respiratory sound monitoring is a promising non-invasive tool for precision pig farming, but practical evidence from calibrated room-level deployment under degraded air-quality conditions remains limited. This study reports a 28-day exploratory room-level case study in which 52 growing pigs were housed in two rooms: one standard-ventilation room and one ventilation-restricted room, and monitored with one microphone per room emphasizing mixed room-level soundscape monitoring rather than individual pig cough counts or replicated treatment inference. Because the design lacked independent room-level replication, all room contrasts and p-values were interpreted as exploratory descriptive screening summaries rather than causal treatment effects. Airflow verification, playback calibration at multiple pen positions, and background-noise spectral analysis were performed to address measurement bias. Signal inspection showed that biologically relevant vocal energy was retained after 16 kHz resampling, while class imbalance was handled by inverse-frequency weighting and macro-F1-based model selection. The Audio Spectrogram Transformer (AST) pipeline was subjected to five-fold group-blocked cross-validation, and temporal validation. The model achieved a test macro-F1 of 0.937, five-fold macro-F1 of 0.928 ± 0.019, and three-day deployment validation macro-F1 of 0.914. In this two-room dataset, the ventilation-restricted room displayed higher room-level cough-like detections, aggressive vocalizations, normal vocalizations, lower silence, reduced growth, and poorer air quality. Cough-like detections showed recurring clock-time clustering, with the most sustained elevation during 19:00–22:00 and a smaller peak around 10:00 with the highest occurrences at 20.00 (2.84 room-level cough-like detections standardized to group size). Audio-only early-warning analysis flagged deteriorated air-quality windows with AUROC = 0.91 and AUPRC = 0.88 and provided a median 34 min lead time before environmental threshold exceedance, highlighting practical utility as an early inspection cue for farmers before air-quality deterioration becomes more pronounced. Cough-like events descriptively co-varied positively with NH₃, temperature, and CO₂. Overall, calibrated AST-based monitoring can summarize group-level acoustic changes associated with degraded room environments, while multi-room and multi-farm replication remains necessary for causal inference and generalization. Full article

Animal transport connects farms with slaughterhouses, breeding units and production sites, but remains one of the most debated animal welfare issues of recent decades. These debates also touch on the EU–Mercosur agreement in the areas of agribusiness and animal farming. The aim of this article is to examine the legislation of Brazil and Germany and the European Union (EU) regarding animal transport, using specific examples to identify differences and similarities that may form the basis for joint discussions on this area of animal welfare. The EU Transport Regulation for the Protection of Farm Animals applies in all EU member states (Council Regulation (EC) No 1/2005). In Germany, the Animal Welfare Transport Ordinance transposes EU law into national law. The transport times depend on vehicle type and equipment and vary according to the animal species to be transported. The basic maximum travel time is 8 h for commercial transport and distances longer than 65 km. In Brazil, there exists a wide range of laws, regulations, decrees and guidelines governing the protection of animals during transport in the different Brazilian states, mostly coordinated by the Brazilian Ministry of Agriculture and Livestock (MAPA). Allowed transport times in Brazil vary largely from 4 to 12 h between single state regulations and are less regulated in detail. Maximum Transport durations can be repeated several times after appropriate stops for animal feeding and watering. Similarly to Germany/EU, only animals “fit for travel” are allowed to be transported and the responsibility for the transported animals ends once the last animal has been unloaded at its place of destination. Temperatures in Germany/EU are generally moderate, whereas Brazil and South America have tropical and subtropical climates. Furthermore, the distances between farms and abattoirs in Brazil are generally greater, and transport vehicles often have to travel on unpaved (gravel) roads, e.g., to reach the farms. The key to animal-friendly transport lies in loading healthy, “transport-fit” animals on suitable vehicles with sufficient space and necessary equipment, and licensed and committed drivers. This has to be supported by appropriate legal provisions. Animal welfare laws in both Brazil and Germany/EU aim to ensure the best possible welfare of animals during transit under the given circumstances of transport, in order to prevent pain, suffering and injury. This shared commitment to animal welfare provides a substantiated basis for mutual understanding and cooperation in livestock farming, which may prove helpful in the discussions on the agricultural chapter of the EU–Mercosur Agreement. Full article

(1) Background: Transboundary notifiable infectious viral diseases, such as lumpy skin disease (LSD), highly pathogenic avian influenza (HPAI), and foot-and-mouth disease (FMD), continue to severely disrupt Europe’s animal health and welfare, food security, and the multi-burdened livestock sector. (2) Methods: Through an extensive literature search, with data collected from the scientific literature, outbreak notifications, and European Union (EU) policy reports, this study synthesises evidence on the economic and societal impacts of preventive mass vaccination compared with stamping out for listed viral animal diseases in Europe. (3) Results: Evidence from LSD, HPAI, and FMD indicates that preventive vaccination reduces outbreak size, duration, and associated economic losses, particularly in high-risk and endemic settings. For LSD, vaccination is essential in eradication, as culling alone fails. For HPAI, evolving epidemiology supports vaccination-to-live strategies. In contrast, for FMD, despite epidemiological benefits of vaccination, the maintenance of FMD-free status without vaccination remains the dominant policy objective, constraining adoption of vaccination-to-live due to trade implications. (4) Conclusions: Overall, findings support the following recommendations: shifting toward preventive vaccination tailored by country and disease, prioritising vaccine-to-live strategies within a harmonised regulatory framework, and strengthening differentiating infected from vaccinated animals (DIVA)-based surveillance and trade-compatible frameworks, all sensible approaches to protect animal welfare and economic stability in Europe’s livestock sector. Full article

The growing global demand for ethical, resource-efficient protein sources has renewed serious interest in cultured meat as a viable alternative to conventional livestock production. Two revolutionary biotechnological systems, induced pluripotent stem cell (iPSC) reprogramming and CRISPR-Cas9-mediated genome editing, when combined, offer unparalleled accuracy and scalability for the biofabrication of avian flesh. In this review, we present a comprehensive pipeline that involves the ectopic expression of Yamanaka factors (Oct4, Sox2, Klf4, and c-Myc) to reprogram primary somatic cells derived from Gallus gallus into induced pluripotent stem cells (iPSCs). This process is subsequently followed by targeted genome editing to enhance myogenic potential, growth efficiency, nutritional composition, and disease resistance. iPSCs are cultivated in a xeno-free bioreactor following genome editing, and subsequently directed to develop into myoblasts and mature myotubes. Three-dimensional tissue biofabrication is realized by combining biomaterial scaffolds and perfusion bioreactor systems, structuring an authentic muscle tissue matrix. These engineering platforms enable precise control over microenvironmental parameters, including oxygenation and nutrient perfusion. The resulting biofabricated poultry product is compositionally optimized, free of antibiotic residues, and exhibits a significantly reduced environmental footprint than poultry that is grown in the traditional way. This all-in-one solution solves important problems in food security, animal welfare, land use efficiency, and greenhouse gas emissions while also setting up a scalable biomanufacturing framework for making proteins for the next generation. Full article

Heat stress remains a significant issue in pig production, particularly in Mediterranean regions, due to the link between climate change and rising temperatures. This study evaluated the effects of heat stress on physiology, oxidative status, animal welfare, histopathological changes, and production in a commercial farrow-to-finish pig farm during the warm season of 2025. Environmental conditions, physiological parameters, welfare, and oxidative stress biomarkers were monitored throughout the study period, while continuous neck skin surface temperature monitoring in lactating sows was carried out using Bluetooth sensor technology. Heat stress was evident over an extended period, as indicated by increased temperature in lactating sows, compromised welfare, oxidative stress, reduced antioxidant capacity, poor reproductive and productive performance, decreased daily growth rate, and higher mortality-related indices. Histopathological examination also revealed multisystemic lesions, including fibrinous microthrombi in renal vessels, hepatocellular degeneration, perivascular oedema with vascular wall thickening in the skin, and lymphocyte depletion in splenic germinal centres. These findings are consistent with endothelial dysfunction, ischaemic tissue damage, and stress-induced immunomodulation. In conclusion, heat stress causes multi-dimensional biological and productive alterations in pigs under intensive farming systems, involving thermoregulatory, oxidative, welfare, reproductive, and histopathological impairments, which support the implementation of integrated precision livestock farming monitoring approaches. Full article

Accurate dairy cow behavior recognition is important for health monitoring, welfare assessment, and early warning in smart livestock farming. However, recognizing fine-grained behaviors such as feeding, drinking, and rumination remains difficult in real barns because of occlusion, complex backgrounds, subtle motion changes, and class imbalance. This study proposes a behavior recognition method that integrates temporal modeling and behavioral priors. The Contrastive Language–Image Pre-training (CLIP) visual encoder is used as the feature extraction backbone, while two temporal adapters are introduced to model dynamic information across consecutive video frames. Dairy cow behavior recognition is further decoupled into posture recognition and action recognition, and a behavioral prior loss is designed to softly constrain unlikely posture–action combinations, such as lying with feeding or lying with drinking. On the test set, the proposed method achieves a five-class accuracy of 75.45%, a five-class Macro-F1 of 0.7246, and an Action Macro-F1 of 0.7605, outperforming the CLIP baseline and several representative video recognition models. These results indicate that the proposed method can support non-contact monitoring of key dairy cow behaviors for practical barn management. Full article