Search Results (1,088)

Chili (Capsicum sp.) is a high-value crop cultivated by farmers, but its production is vulnerable to weather extremes (such as irregular rainfall, high temperatures, and storms), pest and disease outbreaks, and spatially fragmented cultivation, resulting in unstable yields and income. Remote sensing (RS) and geographic information systems (GIS) offer promising tools for the timely, spatially explicit monitoring of chili crops. Despite growing interest in agricultural applications of these technologies, no systematic review has yet synthesized how RS and GIS have been used in chili production. This systematic review addresses this gap by evaluating existing literature on methodological approaches and thematic trends in the use of RS and GIS in chili crop monitoring and management. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines a comprehensive literature search was conducted using predefined keywords across Scopus, Web of Science, and Google Scholar. Sixty-five peer-reviewed articles published through January 2025 were identified and grouped into different thematic areas: crop mapping, biotic stress, abiotic stress, land suitability, crop health, soil and fertilizer management, and others. The findings indicate RS predominantly serves as the primary analytical method (82% of studies), while GIS primarily supports spatial integration and visualization. Key research gaps identified include limitations in spatial resolution, insufficient integration of intelligent predictive models, and limited scalability for smallholder farming contexts. The review highlights the need for future research incorporating high-resolution RS data, advanced modelling techniques, and spatial decision-support frameworks. These insights aim to guide researchers, agronomists, and policymakers toward enhanced precision monitoring and digital innovation in chili crop production. Full article

For fruit harvesting robots, rapid and accurate detection of fruits and picking points is one of the main challenges for their practical deployment. Several fruits typically grow in clusters or bunches, such as grapes, cherry tomatoes, and blueberries. For such clustered fruits, it is desired for them to be picked by bunches instead of individually. This study proposes utilizing a low-cost off-the-shelf RGB-D sensor mounted on the end effector and a lightweight improved YOLOv8-Pose neural network to detect cherry tomato bunches and picking points for robotic harvesting. The problem of occlusion and overlap is alleviated by merging RGB and depth images from the RGB-D sensor. To enhance detection robustness in complex backgrounds and reduce the complexity of the model, the Starblock module from StarNet and the coordinate attention mechanism are incorporated into the YOLOv8-Pose network, termed StarBL-YOLO, to improve the efficiency of feature extraction and reinforce spatial information. Additionally, we replaced the original OKS loss function with the L1 loss function for keypoint loss calculation, which improves the accuracy in picking points localization. The proposed method has been evaluated on a dataset with 843 cherry tomato RGB-D image pairs acquired by a harvesting robot at a commercial greenhouse farm. Experimental results demonstrate that the proposed StarBL-YOLO model achieves a 12% reduction in model parameters compared to the original YOLOv8-Pose while improving detection accuracy for cherry tomato bunches and picking points. Specifically, the model shows significant improvements across all metrics: for computational efficiency, model size (−11.60%) and GFLOPs (−7.23%); for pickable bunch detection, mAP50 (+4.4%) and mAP50-95 (+4.7%); for non-pickable bunch detection, mAP50 (+8.0%) and mAP50-95 (+6.2%); and for picking point detection, mAP50 (+4.3%), mAP50-95 (+4.6%), and RMSE (−23.98%). These results validate that StarBL-YOLO substantially enhances detection accuracy for cherry tomato bunches and picking points while improving computational efficiency, which is valuable for resource-constrained edge-computing deployment for harvesting robots. Full article

Drones have been widely used in precision agriculture to capture high-resolution images of crops, providing farmers with advanced insights into crop health, growth patterns, nutrient deficiencies, and pest infestations. Although several machine and deep learning models have been proposed for plant stress and disease detection, their performance regarding accuracy and computational time still requires improvement, particularly under limited data. Therefore, this paper aims to address these challenges by conducting a comparative analysis of three State-of-the-Art object detection deep learning models: YOLOv8, RetinaNet, and Faster R-CNN, and their variants to identify the model with the best performance. To evaluate the models, the research uses a real-world dataset from potato farms containing images of healthy and stressed plants, with stress resulting from biotic and abiotic factors. The models are evaluated under limited conditions with original data of size 360 images and expanded conditions with augmented data of size 1560 images. The results show that YOLOv8 variants outperform the other models by achieving larger mAP@50 values and lower inference times on both the original and augmented datasets. The YOLOv8 variants achieve mAP@50 ranging from 0.798 to 0.861 and inference times ranging from 11.8 ms to 134.3 ms, while RetinaNet variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 118.7 ms to 158.8 ms, and Faster R-CNN variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 265 ms to 288 ms. These findings highlight YOLOv8’s robustness, speed, and suitability for real-time aerial crop monitoring, particularly in data-constrained environments. Full article

In precision livestock farming, synchronous and high-precision instance segmentation of multiple key body parts of sika deer serves as the core visual foundation for achieving automated health monitoring, behavior analysis, and automated antler collection. However, in real-world breeding environments, factors such as lighting changes, severe individual occlusion, pose diversity, and small targets pose severe challenges to the accuracy and robustness of existing segmentation models. To address these challenges, this study proposes an improved model, MPDF-DetSeg, based on YOLO11-seg. The model reconstructs its neck network, and designs the multipath diversion feature fusion pyramid network (MPDFPN). The multipath feature fusion and cross-scale interaction mechanism are used to solve the segmentation ambiguity problem of deer body occlusion and complex illumination. The design depth separable extended residual module (DWEResBlock) improves the ability to express details such as texture in specific parts of sika deer. Moreover, we adopt the MPDIoU loss function based on vertex geometry constraints to optimize the positioning accuracy of tilted targets. In this study, a dataset consisting of 1036 sika deer images was constructed, covering five categories, including antlers, heads (front/side views), and legs (front/rear legs), and used for method validation. Compared with the original YOLO11-seg model, the improved model made significant progress in several indicators: the mAP50 and mAP50-95 under the bounding-box metrics increased by 2.1% and 4.9% respectively; the mAP50 and mAP50-95 under the mask metrics increased by 2.4% and 5.3%, respectively. In addition, in the mIoU index of image segmentation, the model reached 70.1%, showing the superiority of this method in the accurate detection and segmentation of specific parts of sika deer, this provides an effective and robust technical solution for realizing the multidimensional intelligent perception and automated applications of sika deer. Full article

Coxiella burnetii, the etiological agent of Q fever, is a globally distributed zoonotic pathogen affecting both animals and humans. Despite its known endemicity in various Mediterranean regions, data on human seroprevalence in Sardinia are still lacking. This study aimed to assess seroprevalence in patients and to analyze the annual positivity rate related to the serum samples collected in Sardinia over a ten-year period (2015–2024). For this purpose, a total of 1792 patients were involved in the survey, and 4310 serum samples were analyzed using indirect immunofluorescence assay (IFI) to detect IgM and IgG antibodies against C. burnetii. The global seroprevalence rates relating to all the patients over a ten-year period were determined along with the annual positivity rate and trends from all sera. An overall seroprevalence of 27.0% and an average of annual positivity rate of 16.0% were determined, with the IFI detecting IgG antibodies in 15.2% of positive samples and IgM antibodies in 0.9%, suggesting significant prior exposure of the population evaluated. Annual positivity rates ranged from 24.8% in 2016 to 8.0% in 2020. These results confirmed the endemic circulation of C. burnetii in Sardinia and the ongoing risk of human exposure. A GIS-based map was built to evidence the spatial distribution of Q fever in Sardinia. Interestingly, areas with higher seroprevalence appear to coincide with the distribution of sheep and goat farms, indicating a link between livestock and human exposure. These findings confirm the circulation of C. burnetii in Sardinia and underscore the importance of epidemiological monitoring, public health interventions, and educational efforts in populations at increased risk. Full article

This study presents a terrain-integrated Soil Management Unit (SMU) framework for precision agriculture in semi-arid tropical basaltic soils. Using high resolution (10-ha grid) sampling across 4627 geo-referenced locations and machine learning-enhanced integration of terrain attributes with legacy soil maps, and (3) quantitative validation of intra-SMU homogeneity, 15 SMUs were delineated based on landform, soil depth, texture, and slope. Principal Component Analysis (PCA) revealed SMU11 as the most heterogeneous (68.8%). Geo-statistical analysis revealed structured variability in soil pH (range = 1173 m) and nutrients availability with micronutrient sufficiency following Mn > Fe > Cu > Zn, (Zn deficient in SMU13). Organic carbon strongly correlated with key nutrients (AvK, r = 0.83 and Zn, r = 0.86). This represents the first systematic implementation of terrain-integrated SMU delineation in India’s basaltic landscapes, demonstrating a potential for 20–25% input savings. The spatially explicit fertility-integrated SMU framework provides a robust basis for developing decision support systems aimed at optimizing location-specific nutrient and land management strategies. Full article

Human-Wildlife conflict (HWC) presents a growing challenge for wildlife conservation, especially as species recover and reoccupy human-dominated landscapes, creating tensions between ecological goals and local livelihoods. Such conflicts are increasingly reported across Europe, including Romania, involving semi-aquatic species like the Eurasian beaver (Castor fiber L.) and Eurasian otter (Lutra lutra L.). Enhancing coexistence with wildlife through the integration of conflict mapping, stakeholder engagement, and spatial analysis into conservation planning is therefore essential for ensuring the long-term protection of conflict species. A mixed-methods approach was used, including structured surveys among stakeholders, standardized damage report collection from institutions, and expert field assessments of species activity. The results indicate that while most respondents recognize the legal protection of both species, a minority have experienced direct conflict, primarily with beavers through flooding and crop damage. Tolerance varied markedly among demographic groups: researchers and environmental agency staff were most accepting, whereas farmers and fish farm owners were the least accepting; respondents with no personal damage experience and those with university or post-secondary education also displayed significantly higher acceptance toward both species. Institutional reports confirmed multiple beaver-related damage sites, and through field validation, conflict forecast zones with spatial clustering in Harghita, Brașov, Covasna, and Sibiu counties were developed. These findings underscore the importance of conflict forecasting maps, understanding the coexistence dynamics and drivers of acceptance, and the need to maintain high acceptance levels toward the studied species. The developed maps can serve as a basis for targeted interventions, helping to balance ecological benefits with socioeconomic concerns. Full article

Rainwater harvesting for sustainable agriculture (RWHSA) offers a viable and eco-friendly strategy to alleviate water scarcity in semi-arid regions, particularly for agricultural use. This study aims to identify optimal sites for implementing RWH systems in northern Iraq to enhance water availability and promote sustainable farming practices. An integrated geospatial approach was adopted, combining Remote Sensing (RS), Geographic Information Systems (GIS), and Multi-Criteria Decision Analysis (MCDA). Key thematic layers, including soil type, land use/land cover, slope, and drainage density were processed in a GIS environment to model runoff potential. The Soil Conservation Service Curve Number (SCS-CN) method was used to estimate surface runoff. Criteria were weighted using the Analytical Hierarchy Process (AHP), enabling a structured and consistent evaluation of site suitability. The resulting suitability map classifies the region into four categories: very high suitability (10.2%), high (26.6%), moderate (40.4%), and low (22.8%). The integration of RS, GIS, AHP, and MCDA proved effective for strategic RWH site selection, supporting cost-efficient, sustainable, and data-driven agricultural planning in water-stressed environments. Full article

Land use conversion to perennial cropland often degrades the soil structure and fertility, particularly under Mediterranean climatic conditions. This study assessed spatial and temporal dynamics of soil properties and tree responses to 3-year repeated mature compost additions in a citrus orchard. Digital soil mapping revealed strong baseline heterogeneity in texture, CEC, and Si pools. Compost application markedly increased total organic C and N levels, aggregate stability, and pH with noticeable changes after the first amendment, whereas a limited C storage potential was found following further additions. NDVI values of tree canopies monitored over a 3-year period showed significant time-dependent changes not correlated with the soil fertility variables, thus suggesting that multiple interrelated factors affect plant responses. The non-crystalline amorphous Si/total amorphous Si (_iSi:Si_amor) ratio is here proposed as a novel indicator of pedogenic alteration in disturbed agroecosystems. These findings highlight the importance of tailoring organic farming strategies to site-specific conditions and reinforce the value to combine C and Si pool analysis for long-term soil fertility assessment. Full article

The accuracy of classification and localization of plants on images obtained from the board of an unmanned aerial vehicle (UAV) is of great importance when implementing precision farming technologies. It allows for the effective application of variable rate technologies, which not only saves chemicals but also reduces the environmental load on cultivated fields. Machine learning algorithms are widely used for plant classification. Research on the application of the YOLO algorithm is conducted for simultaneous identification, localization, and classification of plants. However, the quality of the algorithm significantly depends on the training set. The aim of this study is not only the detection of a cultivated plant (soybean) but also weeds growing in the field. The dataset developed in the course of the research allows for solving this issue by detecting not only soybean but also seven weed species common in the fields of Kazakhstan. The article describes an approach to the preparation of a training set of images for soybean fields using preliminary thresholding and bound box (Bbox) segmentation of marked images, which allows for improving the quality of plant classification and localization. The conducted research and computational experiments determined that Bbox segmentation shows the best results. The quality of classification and localization with the application of Bbox segmentation significantly increased (f1 score increased from 0.64 to 0.959, mAP50 from 0.72 to 0.979); for a cultivated plant (soybean), the best classification results known to date were achieved with the application of YOLOv8x on images obtained from the UAV, with an f1 score = 0.984. At the same time, the plant detection rate increased by 13 times compared to the model proposed earlier in the literature. Full article

Increased food production demands, labor shortages, and environmental concerns are driving the need for innovative agricultural technologies. However, effective adoption depends critically on aligning robot innovations with the needs of farmers. This paper examines the alignment between the needs of farmers and the robotic systems used in row crop farming. We review current commercial agricultural robots and research, and map these to the needs of farmers, as expressed in the literature, to identify the key issues holding back large-scale adoption. From initial pool of 184 research articles, 19 survey articles, and 82 commercial robotic solutions, we selected 38 peer-reviewed academic studies, 12 survey articles, and 18 commercially available robots for in-depth review and analysis for this study. We identify the key challenges faced by farmers and map them directly to the current and emerging capabilities of agricultural robots. We supplement the data gathered from the literature review of surveys and case studies with in-depth interviews with nine farmers to obtain deeper insights into the needs and day-to-day operations. Farmers reported mixed reactions to current technologies, acknowledging efficiency improvements but highlighting barriers such as capital costs, technical complexity, and inadequate support systems. There is a notable demand for technologies for improved plant health monitoring, soil condition assessment, and enhanced climate resilience. We then review state-of-the-art robotic solutions for row crop farming and map these technological capabilities to the farmers’ needs. Only technologies with field validation or operational deployment are included, to ensure practical relevance. These mappings generate insights that underscore the need for lightweight and modular robot technologies that can be adapted to diverse farming practices, as well as the need for farmers’ education and simpler interfaces to robotic operations and data analysis that are actionable for farmers. We conclude with recommendations for future research, emphasizing the importance of co-creation with the farming community to ensure the adoption and sustained use of agricultural robotic solutions. Full article

Accurate identification of predator–pest relationships is essential for implementing effective and sustainable biological control in agriculture. However, existing image-based methods struggle to recognize insect co-occurrence under complex field conditions, limiting their ecological applicability. To address this challenge, we propose a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and Transformer architectures for multi-label recognition of predator–pest combinations. The model leverages a novel co-occurrence attention mechanism to capture semantic relationships between insect categories and employs a pairwise label matching loss to enhance ecological pairing accuracy. Evaluated on a field-constructed dataset of 5,037 images across eight categories, the model achieved an F1-score of 86.5%, mAP50 of 85.1%, and demonstrated strong generalization to unseen predator–pest pairs with an average F1-score of 79.6%. These results outperform several strong baselines, including ResNet-50, YOLOv8, and Vision Transformer. This work contributes a robust, interpretable approach for multi-object ecological detection and offers practical potential for deployment in smart farming systems, UAV-based monitoring, and precision pest management. Full article

The rising demand for sustainable protein is driving interest in insects as a raw material for advanced food ingredients. This review collates and critically analyses over 300 studies on the conversion of crickets, mealworms, black soldier flies, and other farmed species into powders, protein isolates, oils, and chitosan-rich fibers with targeted techno-functional roles. This survey maps how thermal pre-treatments, blanch–dry–mill routes, enzymatic hydrolysis, and isoelectric solubilization–precipitation preserve or enhance the water- and oil-holding capacity, emulsification, foaming, and gelation, while also mitigating off-flavors, allergenicity, and microbial risks. A meta-analysis shows insect flours can absorb up to 3.2 g of water g⁻¹, stabilize oil-in-water emulsions for 14 days at 4 °C, and form gels with 180 kPa strength, outperforming or matching eggs, soy, or whey in specific applications. Case studies demonstrate a successful incorporation at 5–15% into bakery, meat analogs and dairy alternatives without sensory penalties, and chitin-derived chitosan films extend the bread shelf life by three days. Comparative life-cycle data indicate 45–80% lower greenhouse gas emissions and land use than equivalent animal-derived ingredients. Collectively, the evidence positions insect-based ingredients as versatile, safe, and climate-smart tools to enhance food quality and sustainability, while outlining research gaps in allergen mitigation, consumer acceptance, and regulatory harmonization. Full article

Achieving optimal agricultural yields and promoting sustainable farming relies on accurate crop recommendations. However, the applicability of many current systems is limited by their considerable computational requirements and dependence on comprehensive datasets, especially in resource-limited contexts. This paper presents HOLISTIQ RS, a novel crop recommendation system explicitly designed for operation on low-specification hardware and in data-scarce regions. HOLISTIQ RS combines collaborative filtering with a Markov model to predict appropriate crop choices, drawing upon user profiles, regional agricultural data, and past crop performance. Results indicate that HOLISTIQ RS provides a significant increase in recommendation accuracy, achieving a MAP@5 of 0.31 and nDCG@5 of 0.41, outperforming standard collaborative filtering methods (the KNN achieved MAP@5 of 0.28 and nDCG@5 of 0.38, and the ANN achieved MAP@5 of 0.25 and nDCG@5 of 0.35). Significantly, the system also demonstrates enhanced recommendation diversity, achieving an Item Variety (IV@5) of 23%, which is absent in deterministic baselines. Significantly, the system is engineered for reduced energy consumption and can be deployed on low-cost hardware. This provides a feasible and adaptable method for encouraging informed decision-making and promoting sustainable agricultural practices in areas where resources are constrained, with an emphasis on lower energy usage. Full article

Caring for the lives and welfare of animals is central to veterinary and animal sanctuary work, yet the meaning remains a subject of complex debates. Different stakeholders negotiate what constitutes appropriate care, leading to conflicting demands and expectations from internal and external sources. This article is based on two qualitative studies: Study I explores the multifaceted aspects of death work in farm animal medicine, emphasising the practical, emotional and ethical challenges involved. Study II examines human–animal interaction in sanctuaries, which reveal tensions between instrumental and relational care in animal-centred work. Relational care represents a subjectifying approach with individual attention to animals, while instrumental care is a more objectifying perspective based on species representation. These demands can often be contradictory, complicating day-to-day decision making under pressure. To analyse these complexities, this study employs Clarke’s situational analysis (social worlds/arenas mapping), providing a means of comparing care work across different fields. This approach highlights how actor constellations, institutional settings, and structural constraints influence the negotiation of care. Addressing these issues provides a more nuanced understanding of the professional challenges of animal-centred care and the necessary skills to navigate its inherent contradictions. Full article