Search Results (1,662)

Mastitis is a significant challenge in the buffalo industry, affecting both milk production and animal health and resulting in economic losses. This study presents the first fully automated AI-driven thermal imaging system integrated with robotic milking, specifically developed for the real-time, non-invasive monitoring of udder health in Italian Mediterranean buffalo. Unlike traditional approaches, the system leverages the synchronized acquisition of thermal images during milking and compensates for environmental variables through a calibrated weather station. A transformer-based neural network (SegFormer) segments the udder area, enabling the extraction of maximum udder skin surface temperature (USST), which is significantly correlated with somatic cell count (SCC). Initial trials demonstrate the feasibility of this approach in operational farm environments, paving the way for scalable, precision diagnostics of subclinical mastitis. This work represents a critical step toward intelligent, automated systems for early detection and intervention, improving animal welfare and reducing antibiotic use. Full article

The increasing adoption of digital technologies in the agriculture sector has significantly contributed to optimizing on-farm routines, especially in data-driven decision-making. This study aimed to develop an application to determine the slaughter point of lambs by predicting subcutaneous fat thickness (SFT) using pre-slaughter parameters such as body weight (BW), body condition score (BCS), and skinfold measurements at the brisket (BST), lumbar (LST), and tail base (TST), obtained using an adipometer. A total of 45 Pantaneiros lambs were evaluated, finished in feedlot, and slaughtered at different body weights. Each pre-slaughter weight class showed a distinct carcass pattern when all parameters were included in the model. Exploratory analysis revealed statistical significance for all variables (p < 0.001). BW and LST were selected to construct the predictive equation (R² = 55.44%). The regression equations were integrated into the developed application, allowing for in-field estimation of SFT based on simple measurements. Compared to conventional techniques such as ultrasound or visual scoring, this tool offers advantages in portability, objectivity, and immediate decision-making support. In conclusion, combining accessible technologies (e.g., adipometer) with traditional variables (e.g., body weight), represents an effective alternative for production systems aimed at optimizing and enhancing the value of lamb carcasses. Full article

Modern beef cattle reproductive management faces increasing challenges due to the growing global demand for beef. Reproductive efficiency is a critical factor determining the productivity and profitability of beef cattle operations. Optimal reproductive performance in a beef cattle herd is achieved when each cow produces one calf per year, maintaining a calving interval of 365 days. However, this goal is difficult to achieve, as the gestation period in beef cows lasts approximately 280 days, leaving only 80–85 days for successful conception. Traditional methods, such as visual estrus detection, are becoming increasingly unreliable due to expanding herd sizes and the subjectivity of visual observation. Additionally, silent estrus—where ovulation occurs without noticeable behavioral changes—further complicates the accurate estrous-based identification of the optimal insemination period. To enhance reproductive efficiency, advanced technologies are increasingly being integrated into cattle management. Sensor-based monitoring systems, including accelerometers, pedometers, and ruminoreticular boluses, enable the precise tracking of activity changes associated with the estrous cycle. Furthermore, infrared thermography offers a non-invasive method for detecting body temperature fluctuations, allowing for more accurate estrus identification and optimized timing of insemination. The use of these innovative technologies has the potential to significantly improve reproductive efficiency in beef cattle herds and contribute to overall farm productivity and sustainability. The objective of this review is to examine advancements in smart technologies applied to beef cattle reproductive management, presenting commercially available technologies and recent scientific studies on innovative systems. The focus is on sensor-based monitoring systems and infrared thermography for optimizing reproduction. Additionally, the challenges associated with these technologies and their potential to enhance reproductive efficiency and sustainability in the beef cattle industry are discussed. Despite the benefits of advanced technologies, their implementation in cattle farms is hindered by financial and technical challenges. High initial investment costs and the complexity of data analysis may limit their adoption, particularly in small and medium-sized farms. However, the continuous development of these technologies and their adaptation to farmers’ needs may significantly contribute to more efficient and sustainable reproductive management in beef cattle production. Full article

This study investigates the production and economic feasibility of biochar for smallholder and family farms in Central Amazonia, with potential implications for other tropical regions. The costs of construction of a prototype mobile kiln and biochar production were evaluated, using small-sized biomass from acai (Euterpe oleracea Mart.) agro-industrial residues as feedstock. The biochar produced was characterised in terms of its liming capacity (calcium carbonate equivalence, CaCO_3eq), nutrient content via organic fertilisation methods, and ash analysis by ICP-OES. Field trials with cowpea assessed economic outcomes, as well scenarios of fractional biochar application and cost comparison between biochar production in the prototype kiln and a traditional earth-brick kiln. The prototype kiln showed production costs of USD 0.87–2.06 kg⁻¹, whereas traditional kiln significantly reduced costs (USD 0.03–0.08 kg⁻¹). Biochar application alone increased cowpea revenue by 34%, while combining biochar and lime raised cowpea revenues by up to 84.6%. Owing to high input costs and the low value of the crop, the control treatment generated greater net revenue compared to treatments using lime alone. Moreover, biochar produced in traditional kilns provided a 94% increase in net revenue compared to liming. The estimated externalities indicated that carbon credits represented the most significant potential source of income (USD 2217 ha⁻¹). Finally, fractional biochar application in ten years can retain over 97% of soil carbon content, demonstrating potential for sustainable agriculture and carbon sequestration and a potential further motivation for farmers if integrated into carbon markets. Public policies and technological adaptations are essential for facilitating biochar adoption by small-scale tropical farmers. Full article

South Dongting Lake is an essential aquatic ecosystem that receives substantial water inflows from the Xiangjiang and Zishui Rivers. However, it is significantly impacted by human activities, including mining, smelting, and farming. These activities have led to serious contamination of the lake’s sediments with heavy metals (HMs). This study investigated the distribution, mobility, and influencing factors of HMs at the sediment–water interface. To this end, sediment samples were analyzed from three key regions (Xiangjiang River estuary, Zishui River estuary, and northeastern South Dongting Lake) using traditional sampling methods and Diffusive Gradients in Thin Films (DGT) technology. Analysis of fifteen HMs (Pb, Bi, Ni, As, Se, Cd, Sb, Mn, Zn, V, Cr, Cu, Tl, Co, and Fe) revealed significant spatial heterogeneity. The results showed that Cr, Cu, Pb, Bi, Ni, As, Se, Cd, Sb, Mn, Zn, and Fe exhibited high variability (CV > 0.20), whereas V, Tl, and Co demonstrated stable concentrations (CV < 0.20). Concentrations were found to exceed background values of the upper continental crust of eastern China (UCC), Yangtze River sediments (YZ), and Dongting Lake sediments (DT), particularly at the Xiangjiang estuary (XE) and in the northeastern regions. Speciation analysis revealed that V, Cr, Cu, Ni, and As were predominantly found in the residual fraction (F4), while Pb and Co were concentrated in the oxidizable fraction (F3), Mn and Zn appeared primarily in the exchangeable fractions (F1 and F2), and Cd was notably dominant in the exchangeable fraction (F1), suggesting a high potential for mobility. Additionally, DGT results confirmed a significant potential for the release of Pb, Zn, and Cd. Contamination assessment using the Pollution Load Index (PLI) and Geoaccumulation Index (Igeo) identified Pb, Bi, Ni, As, Se, Cd, and Sb as major pollutants. Among these, Bi and Cd were found to pose the highest risks. Furthermore, the Risk Assessment Code (RAC) and the Potential Ecological Risk Index (PERI) highlighted Cd as the primary ecological risk contributor, especially in the XE. The study identified sediment grain size, pH, electrical conductivity, and nutrient levels as the primary influencing factors. The PMF modeling revealed HM sources as mixed smelting/natural inputs, agricultural activities, natural weathering, and mining/smelting operations, suggesting that remediation should prioritize Cd control in the XE with emphasis on external inputs. Full article

Produce supply chains play a critical role in ensuring fruits and vegetables reach consumers efficiently, affordably, and at optimal freshness. In recent decades, hub-and-spoke network models have emerged as valuable tools for optimizing sustainable cold food supply chains. Traditional optimization efforts typically focus on removing inefficiencies, minimizing lead times, refining inventory management, strengthening supplier relationships, and leveraging technological advancements for better visibility and control. However, the majority of models rely on deterministic approaches that overlook the inherent uncertainties of crop yields, which are further intensified by climate variability. Rising atmospheric CO₂ concentrations, along with shifting temperature patterns and extreme weather events, have a substantial effect on crop productivity and availability. Such uncertainties can prompt distributors to seek alternative sources, increasing costs due to supply chain reconfiguration. This research introduces a stochastic hub-and-spoke network optimization model specifically designed to minimize transportation expenses by determining optimal distribution routes that explicitly account for climate variability effects on crop yields. A use case involving a cold food supply chain (CFSC) was carried out using several weather scenarios based on climate models and real soil data for California. Strawberries were selected as a representative crop, given California’s leading role in strawberry production. Simulation results show that scenarios characterized by increased rainfall during growing seasons result in increased yields, allowing distributors to reduce transportation costs by sourcing from nearby farms. Conversely, scenarios with reduced rainfall and lower yields require sourcing from more distant locations, thereby increasing transportation costs. Nonetheless, supply chain configurations may vary depending on the choice of climate models or weather prediction sources, highlighting the importance of regularly updating scenario inputs to ensure robust planning. This tool aids decision-making by planning climate-resilient supply chains, enhancing preparedness and responsiveness to future climate-related disruptions. Full article

Background/Objectives: Staphylococcus aureus is a major pathogen of concern in raw milk due to its potential to cause foodborne illness and its increasing antimicrobial resistance (AMR). In Romania, data on the occurrence and resistance patterns of S. aureus in raw sheep milk from traditional farming systems remain limited. This study investigated the presence and antimicrobial resistance of S. aureus in 106 raw sheep milk samples collected from traditional farms in the Banat region of western Romania. Methods: Coagulase-positive staphylococci (CPS) were enumerated using ISO 6888-1:2021 protocols. Isolates were identified at the species level using the Vitek 2 system and molecularly confirmed via PCR targeting the 16S rDNA and nuc genes. Methicillin resistance was assessed by detecting the mecA gene. Antimicrobial susceptibility was determined using the Vitek 2 AST-GP79 card. Results: CPS were detected in 69 samples, with S. aureus confirmed in 34.9%. The mecA gene was identified in 13.5% of S. aureus isolates, indicating the presence of methicillin-resistant S. aureus (MRSA). Resistance to at least two antimicrobials was observed in 97.3% of isolates, and 33 strains (89.2%) met the criteria for multidrug resistance (MDR). The most frequent MDR phenotype involved resistance to lincomycin, macrolides, β-lactams, tetracyclines, and aminoglycosides. Conclusions: The high prevalence of S. aureus, including MRSA and MDR strains, in raw sheep milk from traditional farms represents a potential public health risk, particularly in regions where unpasteurized dairy consumption persists. These findings underscore the need for enhanced hygiene practices, prudent antimicrobial use, and AMR monitoring in small-scale dairy systems. Full article

Continuous and accurate biomass measurement is a critical enabler for control, decision making, and optimization in modern plant production systems. It supports the development of plant growth models for advanced control strategies like model predictive control, and enables responsive, data-driven, and plant state-dependent cultivation. Traditional biomass measurement methods, such as destructive sampling, are time-consuming and unsuitable for high-frequency monitoring. In contrast, image-based estimation using computer vision and deep learning requires frequent retraining and is sensitive to changes in lighting or plant morphology. This work introduces a low-cost, load-cell-based biomass monitoring system tailored for vertical farming applications. The system operates at the level of individual growing trays, offering a valuable middle ground between impractical plant-level sensing and overly coarse rack-level measurements. Tray-level data allow localized control actions, such as adjusting light spectrum and intensity per tray, thereby enhancing the utility of controllable LED systems. This granularity supports layer-specific optimization and anomaly detection, which are not feasible with rack-level feedback. The biomass sensor is easily scalable and can be retrofitted, addressing common challenges such as mechanical noise and thermal drift. It offers a practical and robust solution for biomass monitoring in dynamic, growing environments, enabling finer control and smarter decision making in both commercial and research-oriented vertical farming systems. The developed sensor was tested and validated against manual harvest data, demonstrating high agreement with actual plant biomass and confirming its suitability for integration into vertical farming systems. Full article

Mangoes are an important part of Hainan’s tropical characteristic agriculture. In response to the requirements of building an ecological civilization pilot demonstration zone in Hainan, China, green and sustainable development will be the future development trend of the mango planting system. However, the economic benefits and environmental impact during its planting and management process remain unclear. This paper combines emergy, life cycle assessment (LCA), and economic analysis to compare the system sustainability, environmental impact, and economic benefits of the traditional mango cultivation system (TM) in Dongfang City, Hainan Province, and the early-maturing mango cultivation system (EM) in Sanya City. The emergy evaluation results show that the total emergy input of EM (1.37 × 10¹⁶ sej ha⁻¹) was higher than that of TM (1.32 × 10¹⁶ sej ha⁻¹). From the perspective of the emergy index, compared with TM, EM exerted less pressure on the local environment and has better stability and sustainability. This was due to the higher input of renewable resources in EM. The LCA results showed that based on mass as the functional unit, the potential environmental impact of the EM is relatively high, and its total environmental impact index was 18.67–33.19% higher than that of the TM. Fertilizer input and On-Farm emissions were the main factors causing environmental consequences. Choosing alternative fertilizers that have a smaller impact on the environment may effectively reduce the environmental impact of the system. The economic analysis results showed that due to the higher selling price of early-maturing mango, the total profit and cost–benefit ratio of the EM have increased by 55.84% and 36.87%, respectively, compared with the TM. These results indicated that EM in Sanya City can enhance environmental sustainability and boost producers’ annual income, but attention should be paid to the negative environmental impact of excessive fertilizer input. These findings offer insights into optimizing agricultural inputs for Hainan mango production to mitigate multiple environmental impacts while enhancing economic benefits, aiming to provide theoretical support for promoting the sustainable development of the Hainan mango industry. Full article

The scarab species Protaetia brevitarsis, an edible insect, has been used in traditional medicine, as animal feed, and for converting agricultural organic wastes into biofertilizer. The intestinal tract, which contains a diverse array of microbiota, including viruses, plays a critical role in animal health and homeostasis. We previously conducted a comparative analysis of the gut microbiota of third-instar larvae of P. brevitarsis obtained from five different farms and found significant differences in the composition of the gut bacterial microbiota between farms. To better understand the gut microbiota, the composition of DNA viruses in the hindgut contents of P. brevitarsis larvae obtained from five farms was investigated using metagenomic sequencing in this study. The β-diversity was significantly different between metagenomic data obtained from the five farms (PERMANOVA, pseudo-F = 46.95, p = 0.002). Family-based taxonomic analysis indicated that the relative abundance of viruses in the gut overall metagenome varied significantly between farms, with viral reads comprising approximately 41.2%, 15.0%, 4.3%, 4.0%, and 1.6% of metagenomic sequences from the farms Tohamsan gumbengi farm (TO), Secomnalagum gumbengi (IS), Gumbengi brothers (BR), Kyungpook farm (KB), and Jhbio (JH), respectively. More than 98% of the DNA viruses in the hindgut were bacteriophages, mainly belonging to the Siphoviridae family. At the species level, Phage Min1, infecting the genus Microbacterium, was detected in all farms, and it was the most abundant bacteriophage in intestinal microbiota, with a prevalence of 0.9% to 29.09%. The detected eukaryotic DNA viruses accounted for 0.01% to 0.06% of the intestinal microbiota and showed little or no relationship with insect viruses. Therefore, they most likely originated from contaminated feed or soil. These results suggest that the condition of substrates used as feed is more important than genetic factors in shaping the intestinal viral microbiota of P. brevitarsis larvae. These results can be used as reference data for understanding the hindgut microbiota of P. brevitarsis larvae and, more generally, the gut virome of insects. Full article

This study investigated the impact of incorporating hemp fibers into composites for manufacturing industrial parts. The Global Warming Potential (GWP) of producing a traditional polymer matrix composite containing glass fibers was compared to that of producing a counterpart from natural hemp fibers. The investigation concluded that the partial replacement of synthetic fibers with biomass reduced the GWP of the product by up to 25% without compromising its mechanical properties. This study also quantified and discussed the GWP of intermediate products obtained from alternative routes, such as the manufacture of hemp stalks and pellets. In these cases, the findings showed that the amount of CO₂ absorbed during plant growth exceeded the emissions related to soil preparation, farming, and processing of hemp stalks by up to 15 times, and the processing of row hemp bales into pellets could result in an even “greener” product. This study highlights the importance of using bio-based inputs in reducing greenhouse gas emissions in the materials manufacturing industry and concludes that even partial substitutions of synthetic inputs with natural fibers can show significant reductions in this type of environmental impact. Full article

The aim of this research is to identify policy and practice interventions that support a just transition towards resilient practices for resource-dependent communities. We focus on Thai Nguyen and Phu Tho, two provinces in the Northern Midlands and Mountains of Vietnam. The region is reliant on agriculture but is assessed as highly vulnerable to climate change. We surveyed 105 farming households. A Likert-type questionnaire asked respondents to self-assess their experiences of weather extremes and of changes they had made to their farming practices. Our results show that for both Thai Nguyen and Phu Tho, farmers see the effects of climate change on their crops. Respondents in Thai Nguyen were more likely to report technically driven adaptation and engagement with extension services. Respondents in Pho Tho were more likely to continue traditional practices. For both, use of traditional knowledge and practices was related to taking measures to adapt to climate change. Our main conclusion is that at least three actions could support a just transition to resilient livelihoods. First is incorporating natural science and traditional knowledge into decision-making for just transitions. Second is considering long-term implications of interventions that appear to support livelihoods in the short term. Third is tailoring messaging and engagement strategies to the requirements of the most vulnerable people. The main message of this study is that a just transition for resource-dependent communities will inevitably be context-specific. Even in centralized and authoritarian contexts, flexibility to adapt top-down policies to locals’ own experiences of changing climates is needed. Full article

Agriculture is the foundational industry for human survival, profoundly impacting economic, ecological, and social dimensions. In the face of global challenges such as rapid population growth, resource scarcity, and climate change, achieving technological innovation in agriculture and advancing smart farming have become increasingly critical. In recent years, deep learning and computer vision have developed rapidly. Key areas in computer vision—such as deep learning-based image processing, object detection, and multimodal fusion—are rapidly transforming traditional agricultural practices. Processes in agriculture, including planting planning, growth management, harvesting, and post-harvest handling, are shifting from experience-driven methods to digital and intelligent approaches. This paper systematically reviews applications of deep learning and computer vision in agricultural growth management over the past decade, categorizing them into four key areas: crop identification, grading and classification, disease monitoring, and weed detection. Additionally, we introduce classic methods and models in computer vision and deep learning, discussing approaches that utilize different types of visual information. Finally, we summarize current challenges and limitations of existing methods, providing insights for future research and promoting technological innovation in agriculture. Full article

With the large-scale integration of renewable energy into distribution networks, traditional fixed-setting overcurrent protection strategies struggle to adapt to rapid fluctuations in renewable energy (e.g., wind and photovoltaic) output. Optimizing current settings is crucial for enhancing the stability of modern distribution networks. This paper proposes an adaptive overcurrent protection method based on an improved NSGA-II algorithm. By dynamically detecting renewable power fluctuations and generating adaptive solutions, the method enables the online optimization of protection parameters, effectively reducing misoperation rates, shortening operation times, and significantly improving the reliability and resilience of distribution networks. Using the rate of renewable power variation as the core criterion, renewable power changes are categorized into abrupt and gradual scenarios. Depending on the scenario, either a random solution injection strategy (DNSGA-II-A) or a Gaussian mutation strategy (DNSGA-II-B) is dynamically applied to adjust overcurrent protection settings and time delays, ensuring real-time alignment with grid conditions. Hard constraints such as sensitivity, selectivity, and misoperation rate are embedded to guarantee compliance with relay protection standards. Additionally, the convergence of the Pareto front change rate serves as the termination condition, reducing computational redundancy and avoiding local optima. Simulation tests on a 10 kV distribution network integrated with a wind farm validate the effectiveness of the proposed method. Full article

The integration of artificial intelligence into sustainable agriculture holds significant potential to transform traditional agricultural practices. This transformation of agricultural practices through AI directly intersects with several critical sustainable development goals, such as Climate Action (SDG13), Life Below Water (SDG 14), and Life on Land (SDG 15). However, such implementations are fraught with multifaceted challenges. This study explores the technological, organizational, and environmental challenges confronting top management in the agricultural sector utilizing the technological–organizational–environmental framework. As interest in AI-enabled sustainable initiatives continues to rise globally, this exploration is timely and relevant. The study employs an interpretive case study approach, drawing insights from a carbon sequestration project within the agricultural sector where AI technologies have been integrated to support sustainability goals. The findings reveal six key challenges: sustainable policy inconsistency, AI experts lacking farming knowledge, farmers’ resistance to change, limited knowledge and expertise to deploy AI, missing links in the existing system, and transition costs, which often hinder the achievement of long-term sustainability outcomes. This study emphasizes the importance of field realities and cross-disciplinary collaboration to optimize the role of AI in sustainability efforts. Full article