Search Results (111)

The Santurbán paramo is a sensitive high-mountain ecosystem exposed to pressures from extractive and agricultural activities, as well as increasing tourism. In response, this study presents a context-aware recommendation system designed to support sustainable tourism through the integration of deep neural networks and ontology-based semantic modeling. The proposed system delivers personalized recommendations—such as activities, accommodations, and ecological routes—by processing user preferences, geolocation data, and contextual features, including cost and popularity. The architecture combines a trained TensorFlow Lite model with a domain ontology enriched with GeoSPARQL for geospatial reasoning. All inference operations are conducted locally on Android devices, supported by SQLite for offline data storage, which ensures functionality in connectivity-restricted environments and preserves user privacy. Additionally, the system employs geofencing to trigger real-time environmental notifications when users approach ecologically sensitive zones, promoting responsible behavior and biodiversity awareness. By incorporating structured semantic knowledge with adaptive machine learning, the system enables low-latency, personalized, and conservation-oriented recommendations. This approach contributes to the sustainable management of natural reserves by aligning individual tourism experiences with ecological protection objectives, particularly in remote areas like the Santurbán paramo. Full article

Biochar, a carbon-rich material derived from biomass, presents a sustainable solution to several pressing challenges in U.S. agriculture, including soil degradation, carbon emissions, and waste management. Despite global advancements, the U.S. biochar market remains underexplored in terms of economic viability, adoption potential, and sector-specific applications. This narrative review synthesizes two decades of literature to examine biochar’s applications, production methods, and market dynamics, with a focus on its economic and environmental role within the United States. The review identifies biochar’s multifunctional benefits: enhancing soil fertility and crop productivity, sequestering carbon, reducing greenhouse gas emissions, and improving water quality. Recent empirical studies also highlight biochar’s economic feasibility across global contexts, with yield increases of up to 294% and net returns exceeding USD 5000 per hectare in optimized systems. Economically, the global biochar market grew from USD 156.4 million in 2021 to USD 610.3 million in 2023, with U.S. production reaching ~50,000 metric tons annually and a market value of USD 203.4 million in 2022. Forecasts project U.S. market growth at a CAGR of 11.3%, reaching USD 478.5 million by 2030. California leads domestic adoption due to favorable policy and biomass availability. However, barriers such as inconsistent quality standards, limited awareness, high costs, and policy gaps constrain growth. This study goes beyond the existing literature by integrating market analysis, SWOT assessment, cost–benefit findings, and production technologies to highlight strategies for scaling biochar adoption. It concludes that with supportive legislation, investment in research, and enhanced supply chain transparency, biochar could become a pivotal tool for sustainable development in the U.S. agricultural and environmental sectors. Full article

Accurate weed detection in soybean fields is essential for enhancing crop yield and reducing herbicide usage. This study proposes a YOLO-SW model, an improved version of YOLOv8, to address the challenges of detecting weeds that are highly similar to the background in natural environments. The research stands out for its novel integration of three key advancements: the Swin Transformer backbone, which leverages local window self-attention to achieve linear O(N) computational complexity for efficient global context capture; the CARAFE dynamic upsampling operator, which enhances small target localization through context-aware kernel generation; and the RTDETR encoder, which enables end-to-end detection via IoU-aware query selection, eliminating the need for complex post-processing. Additionally, a dataset of six common soybean weeds was expanded to 12,500 images through simulated fog, rain, and snow augmentation, effectively resolving data imbalance and boosting model robustness. The experimental results highlight both the technical superiority and practical relevance: YOLO-SW achieves 92.3% mAP@50 (3.8% higher than YOLOv8), with recognition accuracy and recall improvements of 4.2% and 3.9% respectively. Critically, on the NVIDIA Jetson AGX Orin platform, it delivers a real-time inference speed of 59 FPS, making it suitable for seamless deployment on intelligent weeding robots. This low-power, high-precision solution not only bridges the gap between deep learning and precision agriculture but also enables targeted herbicide application, directly contributing to sustainable farming practices and environmental protection. Full article

Lifestyle blocks (LBs) are small rural holdings primarily used for residential and recreational purposes rather than commercial farming. Despite the rapid expansion of LBs over the last 25 years, which has been driven by lifestyle amenity preference and land subdivision incentives, their environmental performance remains understudied. This is the case even though their proliferation is leading to an irreversible loss of highly productive soils and accelerating land fragmentation in peri-urban areas. Through undertaking a systematic literature review of relevant studies on LBs in New Zealand and comparable international contexts, this paper aims to quantify existing knowledge and suggest future research needs and management strategies. It focuses on the environmental implications of LB activities in relation to water consumption, food production, energy use, and biodiversity protection. The results indicate that variation in land use practices and environmental awareness among LB owners leads to differing environmental outcomes. LBs offer opportunities for biodiversity conservation and small-scale food production through sustainable practices, while also presenting environmental challenges related to resource consumption, greenhouse gas (GHG) emissions, and loss of productive land for commercial agriculture. Targeted landscape design could help mitigate the environmental pressures associated with these properties while enhancing their potential to deliver ecological and sustainability benefits. The review highlights the need for further evaluation of the environmental sustainability of LBs and emphasises the importance of property design and adaptable planning policies and strategies that balance environmental sustainability, land productivity, and lifestyle owners’ aspirations. It underscores the potential for LBs to contribute positively to environmental management while addressing associated challenges, providing valuable insights for ecological conservation and sustainable land use planning. Full article

Danube River represents a critical axis of ecological and economic importance for the countries along its course. From this perspective, this paper aims to assess the most significant characteristics of the river and of its main tributaries, as well as its impact on the environmental sustainability and socio-economic development. Navigation and the economic contribution of the Danube River are the key issues of this work, emphasizing its importance as an international transport artery that facilitates trade and tourism, and develops the energy industry through hydropower plants. The study includes an analysis of the volume of goods transported from 2019 to 2023, as well as an analysis of the goods traffic in the busiest port on the Danube. Furthermore, climate change affects the hydrological regime of the Danube, as well as the ecosystems, economy, and energy security of the riparian countries. Main impacts include changes in the hydrological regime, increased frequency of droughts and floods, reduced water quality, deterioration of biodiversity, and disruption of the economic activities dependent on the river, such as navigation, agriculture, and hydropower production. Thus, hydrological risks and challenges are investigated, focusing on the extreme events of the last two decades and the awareness of their repercussions. In this context, the national and international institutions responsible for monitoring and managing the Danube are presented, and their role in promoting a sustainable river policy is explored. Methods and technologies are shown to be essential tools for monitoring and prediction studies. The Danube includes an extensive network of hydrometric stations that help to prevent and manage the most significant risks. Finally, a SWOT (Strengths, Weaknesses, Opportunities, and Threats) analysis of the development of the hydrological studies was conducted, highlighting the potential of the river. Full article

Hyperspectral imaging (HSI) plays a pivotal role in modern agriculture by capturing fine-grained spectral signatures that support crop classification, health assessment, and land-use monitoring. However, the transition from raw spectral data to reliable semantic understanding remains challenging—particularly under fragmented planting patterns, spectral ambiguity, and spatial heterogeneity. To address these limitations, we propose UniHSFormer-X, a unified transformer-based framework that reconstructs agricultural semantics through prototype-guided token routing and hierarchical context modeling. Unlike conventional models that treat spectral–spatial features uniformly, UniHSFormer-X dynamically modulates information flow based on class-aware affinities, enabling precise delineation of field boundaries and robust recognition of spectrally entangled crop types. Evaluated on three UAV-based benchmarks—WHU-Hi-LongKou, HanChuan, and HongHu—the model achieves up to 99.80% overall accuracy and 99.28% average accuracy, outperforming state-of-the-art CNN, ViT, and hybrid architectures across both structured and heterogeneous agricultural scenarios. Ablation studies further reveal the critical role of semantic routing and prototype projection in stabilizing model behavior, while parameter surface analysis demonstrates consistent generalization across diverse configurations. Beyond high performance, UniHSFormer-X offers a semantically interpretable architecture that adapts to the spatial logic and compositional nuance of agricultural imagery, representing a forward step toward robust and scalable crop classification. Full article

Remote sensing image segmentation holds significant application value in precision agriculture, environmental monitoring, and other fields. However, in the task of fine-grained segmentation of weeds and crops, traditional deep learning methods often fail to balance global semantic information with local detail features, resulting in over-segmentation or under-segmentation issues. To address this challenge, this paper proposes a segmentation model based on a dual-branch Transformer architecture—DBFormer—to enhance the accuracy of weed detection in remote sensing images. This approach integrates the following techniques: (1) a dynamic context aggregation branch (DCA-Branch) with adaptive downsampling attention to model long-range dependencies and suppress background noise, and (2) a local detail enhancement branch (LDE-Branch) leveraging depthwise-separable convolutions with residual refinement to preserve and sharpen small weed edges. An Edge-Aware Loss module further reinforces boundary clarity. On the Tobacco Dataset, DBFormer achieves an mIoU of 86.48%, outperforming the best baseline by 3.83%; on the Sunflower Dataset, it reaches 85.49% mIoU, a 4.43% absolute gain. These results demonstrate that our dual-branch synergy effectively resolves the global–local conflict, delivering superior accuracy and stability in the context of practical agricultural applications. Full article

The proliferation of the Internet of Things (IoT) has led to an abundance of data streams and real-time dashboards in domains such as smart cities, healthcare, manufacturing, and agriculture. However, many current IoT dashboards emphasize complex visualizations with minimal textual cues, posing significant barriers to users with visual impairments who rely on screen readers or other assistive technologies. This paper presents AccessiDashboard, a web-based IoT dashboard platform that prioritizes accessible design from the ground up. The system uses semantic HTML5 and WAI-ARIA compliance to ensure that screen readers can accurately interpret and navigate the interface. In addition to standard chart presentations, AccessiDashboard automatically generates long descriptions of graphs and visual elements, offering a text-first alternative interface for non-visual data exploration. The platform supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and leverages Large Language Models (LLMs) to produce context-aware textual representations of sensor data. A privacy-by-design approach is adopted for the AI integration to address ethical and regulatory concerns. Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities, demonstrating its potential as a blueprint for future inclusive IoT monitoring solutions. Full article

This study investigated the perceptions of animal welfare and the consumption of alternative protein sources among future professionals in agronomy, food science, and veterinary medicine. A sample of 769 participants from three faculties [ESALQ (“Luiz de Queiroz” College of Agriculture), FZEA (School of Animal Science and Food Engineering), and FMVZ (School of Veterinary Medicine and Animal Science)] of the University of São Paulo was used. These faculties have different teaching focuses: agronomy, food and animal production, and veterinary, respectively. A relationship between the perception of animal welfare and alternative sources of protein based on the participants’ educational background was verified, specifically: (i) participants from the FZEA (food science) and FMVZ (veterinary) units would be interested in consuming farmed meat and expressed interest in trying it; (ii) students from the ESALQ (agronomy) have a low level of knowledge about animal welfare and are not very interested in knowing how animals are reared, and few participants attribute the presence of the health inspection seal as influencing their purchasing intention; (iii) participants, regardless of their academic background, did not express an intention to reduce their red meat consumption; (iv) the ESALQ was the campus which showed the most skepticism about animal sentience; (v) most participants from the FMVZ and FZEA reported being willing to pay 4–5% more for products that guarantee animal welfare. The findings suggest that the academic context influences individuals’ perceptions and food choices, highlighting the need for educational strategies that foster a greater awareness of animal welfare, encourage the adoption of more sustainable practices, and promote the acceptance of alternative protein sources within the agri-food sector. Full article

Water scarcity is a critical challenge in arid and semi-arid regions, where agricultural water consumption accounts for a significant portion of freshwater use. Conventional agriculture (CA) methods with high reliance on chemical and mechanical inputs often exacerbate this issue through soil degradation and water loss. This review aims to examine how different organic practices, such as mulching, cover cropping, composting, crop rotation, and no-till (NT) in combination with precision technologies, can contribute to water optimization, and it discusses the opportunities and challenges for the adoption and implementation of those practices. Previous findings show that organic agriculture (OA) may outperform CA in drought conditions. However, the problems of weed management in organic NT, trade-offs in cover crop biomass and moisture conservation, limited access to irrigation technologies, lack of awareness, and certification barriers challenge agricultural resilience and sustainability. Since the outcomes of OA practices depend on the crop type, local environment, and accessibility of knowledge and inputs, further context-specific research is needed to refine a scalable solution that maintains both productivity and resilience. Full article

Occupational Health and Safety (OHS) in agriculture is a critical concern worldwide, with self-propelled machinery accidents, particularly tip/roll-overs, being a leading cause of injuries and fatalities. In such a context, while great attention has been paid to machinery safety improvement, a major challenge is the lack of studies addressing the analysis of the work environment to provide farmers with precise information on field slope steepness. This information, merged with an awareness of machinery performance, such as tilt angles, can facilitate farmers in making decisions about machinery operations in hilly and mountainous areas. To address this gap, the Italian Compensation Authority (INAIL) launched a research programme to integrate georeferenced slope data with the tilt angle specifications of common self-propelled machinery, following EN ISO 16231-2:2015 standards. This study presents the first results of this research project, which was focused on vineyards in the alpine region of the Autonomous Province of Trento, where terrestrial LiDAR technology was used to analyze slope steepness. The findings aim to provide practical guidelines for safer machinery operation, benefiting farmers, risk assessors, and manufacturers. By enhancing awareness of tip/roll-over risks and promoting informed decision-making, this research aims to contribute to improving OHS in agriculture, particularly in challenging terrains. Full article

The restrictions imposed by the European Green Deal on Europe are expected to make Europe climate-neutral by 2050. In this context, this article examines the current efforts to reduce emission levels, focusing on available international scientific papers concerning European territory, particularly Poland. The study paid special attention to the sector of agriculture, which is considered a key contributor to greenhouse gas generation. It also analysed the impact of various tillage techniques and the application of organic and inorganic fertilisers, e.g., nitrogen fertilisers, digestate, or compost, on the emissions of greenhouse gases and other environmentally harmful substances. Although there are few scientific articles available that comprehensively describe the problem of greenhouse gas emissions from agriculture, it is still possible to observe the growing awareness of farmers and their daily impact on the environment. The current study demonstrated that agricultural activities significantly contribute to the emissions of three main greenhouse gases: carbon dioxide, nitrous oxide, and methane. The tillage and soil fertilisation methods used play a crucial role in their emissions into the atmosphere. The use of no-tillage (or reduced-tillage) techniques contributes to the sustainable development of agriculture while reducing greenhouse gas emissions. The machinery and fuels used, along with innovative systems and sensors for precise fertilisation, play a significant role in lowering emission levels in agriculture. The authors intend to identify potential opportunities to improve crop productivity and contribute to sustainable reductions in gas emissions. Full article

Background/Objective: Besides the common risks associated with agriculture, recently, there has been growing concern about the impact of agriculture on farmers’ mental health, due to high stress levels, depression, anxiety, and increasing rates of suicide, especially complex considering that many of these farmers are older people. The potential of the practice of mindfulness to minimize mental health problems and improve people’s sense of well-being has been studied in recent decades, although there is a dearth of literature related to farmer populations. This study aimed to correlate the presence of mindfulness traits with general life quality and well-being and assess the levels of mindfulness and life satisfaction among family farmers, as well as to evaluate which characteristics might be associated with them. Method: The sample was composed of 30 farmers from the region of Viseu—Portugal, who were randomly selected for a survey consisting of an adaptation of the Mindful Attention Awareness Scale (MAAS) and the Satisfaction with Life Scale (SWLS), with some new items specific to the context of agriculture. A proposed Farmers’ Mindfulness and Life Satisfaction Scale (FMLSS) was validated through factor analysis and internal reliability analysis. Result: The results showed a relatively high average score for the 10 items of the mindfulness scale (4.23 ± 0.56) and the global sum of scores for the 5 items of the life satisfaction scale (26.67 ± 4.76). Factor analysis revealed six factors, globally explaining 77% of the variance, with values of alpha varying from 0.640 to 0.874. The FMLSS was validated with 19 items of the 20 initially considered (α = 0.672). Cluster analysis revealed two typologies of participants, “Pleased” and “Accommodated” family farmers. These two clusters had global values for the FMLSS of 5.19 ± 0.51 and 4.37 ± 0.59, with the higher value obtained for the “Pleased” family farmers, who were mostly of male gender and worked more hours per week and whose agricultural activities had higher significance for their family income. Conclusions: Overall, we observed a relatively high level of mindfulness and satisfaction with life among family farmers. This suggests the importance of future research on mental health among family farmers. Full article

With growing awareness of health and sustainability benefits, organic food has surged in popularity, highlighting the critical need for effective communication strategies in product promotion. While extant research extensively examines the effects of textual content in organic food advertising, little attention has been paid to the persuasive power of typeface design on consumers’ responses. Grounded in cue utilization theory and message consistency framework, this study investigates how handwritten typefaces and narrative perspectives influence consumer responses in organic food advertising. Two experiments were conducted. Study 1 (N = 139) shows their positive effects on consumer attitudes and purchase intentions than machine-typed fonts; Study 2 (N = 206) extends these findings by revealing a significant interaction between typeface and narrative perspective, where first-person narratives amplify the positive effects of handwritten fonts. Moreover, a moderated mediation model shows that the influence of handwritten typefaces on consumer responses is sequentially mediated by perceived congruence and perceived sincerity, with the indirect effects being stronger for first-person narratives than third-person ones. The findings advance marketing theory by demonstrating how visual–semantic alignment enhances communication efficacy, especially in organic product contexts. Practically, this study proposes the strategic implementation of handwritten typography combined with the use of first-person narratives for organic food promotion. These insights hold significant implications for fostering organic consumption patterns, potentially driving environmentally conscious agriculture practices and supporting environmental sustainability efforts. Full article

This paper presents HERMEES—Holistic Evaluation and Ranking Model for Energy Efficient Systems. HERMEES is based on a multi-criteria decision-making (MCDM) model designed to select the optimal combination of lightweight cryptography (LWC) and topology construction protocol (TCP) algorithms for wireless sensor networks (WSNs) based on user-defined scenarios. The proposed model is evaluated using a scenario based on a medium-sized agricultural field. The Simple Additive Weighting (SAW) method is used to assign scores to the candidate algorithm pairs by weighting the scenario-specific criteria according to their significance in the decision-making process. To further refine the selection, mean shift clustering is utilized to group and identify the highest scored candidates. The resulting model is versatile and adaptable, enabling WSNs to be configured according to specific operational needs. The provided pseudocode elucidates the model workflow and aids in an effective implementation. The presented model establishes a solid foundation for the development of guided self-configuring context-aware WSNs capable of dynamically adapting to a wide range of application requirements. Full article