Search Results (2,004)

Accurate wind power forecasting is essential for the stable and economic operation of power systems with high renewable penetration. Although machine learning models have been widely adopted for this task, the assumption that greater model complexity invariably yields superior forecasting accuracy has received insufficient scrutiny. This paper presents a systematic experimental investigation that covers two complementary stages, i.e., wind speed correction and wind power forecasting. For wind speed correction, we compare 10 machine learning methods, including spanning linear, instance-based, and tree-based ensemble learners, under four newly proposed progressively enriched feature configurations. For wind power forecasting, we benchmark 20 methods spanning traditional machine learning, time-series deep learning, and Transformer-based architectures on two geographically distinct wind farms. Our results reveal a clear task-dependent pattern. In wind speed correction, tree-based ensemble methods, particularly gradient boosting variants, consistently dominate, and feature engineering contributes more to accuracy gains than model selection. In wind power forecasting, deep learning architectures substantially and consistently outperform traditional methods, with attention-based models generalizing the most robustly across regimes and recurrent networks proving to be the most sensitive to regime shifts. These findings provide actionable task-specific guidance for model selection in operational wind power forecasting systems. Full article

The importance of accurate and fast forecasting of wind speed is critical for guiding investment decisions, grid integration of wind power plants, and dispatch management. However, due to surface smoothness and the effects of thermal processes, wind-speed time series obtained from onshore and offshore sites have very statistically and dynamically distinct characteristics in terms of volatility, non-stationarity, autocorrelation, and noise components. This study proposes a Sinusoidal Representation Network (SIREN)-based framework to provide accurate, fast, and direct multi-horizon wind-speed forecasting for both onshore and offshore wind farms. Two datasets of onshore and offshore wind speeds, which have long durations and data continuity, are used to assess the performance of the suggested approach from very-short-term to long-term forecasting horizons. Both of the datasets use Savitzky–Golay filters and moving medians to reduce short-term noise and sudden spikes and winsorization and Hampel filters to limit the effect of outliers. Additionally, robust scaling is done to ensure stability of the scales of the variables, while log transformation is applied to counteract the problem of skewness and variation in the data distribution. The SIREN model is trained, validated, and tested independently for each forecast horizon, corresponding to times ranging from 5 min to 30 days. Ablation and sensitivity analyses are conducted to evaluate the effect of the parameters used in the model on forecast performance. In addition, comparative analyses incorporating traditional time series, and ML and DL techniques are conducted to more comprehensively evaluate the model’s performance. The obtained graphical and numerical results have revealed that the proposed SIREN approach is a highly accurate and computationally convenient alternative wind-speed forecasting method that can be flexibly adapted to different time resolutions and forecast horizons in both onshore and offshore systems. Full article

Coconut is an important livelihood and industrial crop for coastal communities in Thailand; however, limited information is available on the phenotypic diversity of traditional aromatic coconut populations cultivated by smallholders in southern Thailand. An on-farm survey was conducted in Phang Nga, Trang, Krabi, and Nakhon Si Thammarat, evaluating 27 palms representing nine populations (three palms per population) for 28 quantitative morphological, reproductive, fruit, yield, and coconut-water quality traits. A hierarchical linear mixed model, with province treated as a fixed effect and populations nested within province, was used to characterize phenotypic variation and obtain adjusted population-level BLUPs. Substantial phenotypic variation was observed among the surveyed populations. Var7 in Krabi recorded the highest fruit weight (2039 g) and kernel thickness; Var6 in Trang had the highest number of fruits per bunch (13.3); Var2 in Phang Nga had the highest water volume (430 mL); and Var9 in Nakhon Si Thammarat had the highest number of female flowers (20). Principal component analysis showed that the first five components explained 72.6% of the total phenotypic variation, with fruit, reproductive, water, and vegetative traits contributing strongly to population differentiation. Correlation network analysis further identified coordinated associations among vegetative vigor, leaf morphology, and fruit and yield traits. The study provides a baseline phenotypic characterization of Nam Hom coconut populations under smallholder conditions and identifies population–province combinations with promising trait profiles for further evaluation. Full article

The hilly agroecosystems of north-western Maharashtra harbor rich agrobiodiversity, but agricultural intensification and widespread adoption of improved cultivars are accelerating the erosion of traditional crop landraces. However, comprehensive information on the current status of on-farm agrobiodiversity and the extent of ongoing genetic erosion in these tribal-dominated landscapes remains limited. This study assessed on-farm agri-horticultural diversity, landrace prevalence, genetic erosion, and indigenous conservation practices across Akole, Igatpuri, Shahada, and Dhadgaon. Field surveys, household interviews, and focus group discussions documented traditional crop landraces, wild edible species, and farmer-led conservation practices. Agrobiodiversity was evaluated using the Prevalence Index, Berger–Parker Index, Menhinick’s Diversity Index, and Shannon Diversity Index. More than 150 traditional landraces representing cereals, millets, pulses, oilseeds, vegetables, fruits, and legumes, together with over 35 wild edible plant species, were recorded. Hyacinth bean (PI = 10.00), mango (PI = 5.35), groundnut (PI = 5.25) and wheat (PI = 4.17) showed the highest prevalence in Akole–Igatpuri, whereas cowpea (PI = 2.50) and pigeonpea (PI = 2.33) predominated in Shahada–Dhadgaon. Shannon diversity values ranged from 0.69 to 3.01 and 1.01 to 2.17, indicating substantial variation in landrace diversity. Community seed banks and farmer-managed seed systems continue to support the conservation of locally adapted landraces despite ongoing varietal replacement. This study provides a comprehensive baseline for understanding the status of on-farm agrobiodiversity in north-western Maharashtra. It highlights the importance of integrating indigenous knowledge with community-based and policy-driven conservation strategies to strengthen the long-term resilience and sustainability of traditional farming systems. Full article

Fermentation is now recognized as extending well beyond its traditional role in mucilage removal during coffee processing; rather it is a biochemically complex, microbially driven process that exerts a critical influence on coffee flavor, aroma, and cup quality. Yeasts, including Hanseniaspora, Pichia, Torulaspora, Candida, Meyerozyma, and Saccharomyces, form ecologically diverse communities whose composition is shaped by processing method, geographical origin, and environmental conditions, contributing not only to flavor development but also to mucilage degradation, microbial stability, and the suppression of undesirable microorganisms. Although starter cultures formulated from both Saccharomyces and non-Saccharomyces yeasts have frequently improved sensory quality and process control, fermentation outcomes remain highly strain-, dose-, and process-dependent, such that neither ecological dominance nor pectinolytic activity consistently predicts fermentation performance or cup quality. This review identifies environmental variability, microbial competition, the incompletely elucidated mechanisms underlying mucilage degradation, and the frequent disconnect between ecological dominance and technological functionality as principal constraints on the reliable implementation of starter cultures. Collectively, the evidence supports a shift from sensory-driven strain selection toward a multidimensional framework that integrates ecological fitness, stress tolerance, metabolic stability, persistence, mucilage-degrading capacity, and defect-mitigating potential under farm-representative, non-sterile conditions. Full article

The precise extraction of field roads in hilly and terrace farmlands poses great challenges for remote sensing analysis. Farm roads are narrow and irregular, with spectra close to crop ridges, and frequently covered by tree and building shadows. Traditional segmentation methods easily produce missed detection, broken and distorted road outlines. Most existing deep learning networks are optimized for cities and lack generalization to complex rural scenes. This work presents a multi-scale feature enhancement and edge-aware network (BRPE-Unet), an improved U-Net for accurate rural road extraction from high-resolution remote sensing images. An optimized DenseASPP block is inserted into encoders to fix U-Net’s weak multi-scale feature capacity and fuse tiny road details with global context. Parallel Polarized Self-Attention is added to skip links to highlight road areas and suppress crop and shadow noise. A new Adaptive Edge Refinement module is placed at the decoder output, using image-dependent threshold generation and multi-directional gradient information to refine blurred and fragmented road boundaries and improve segmentation continuity. Tests on DeepGlobe Road and WHU-RuR+ datasets yield IoUs of 67.54% and 52.30%, respectively, and the proposed BRPE-UNet demonstrates competitive road extraction performance among the representative methods evaluated in this study. BRPE-UNet can reliably extract rural roads and offers technical support for farm modernization and rural revitalization. Full article

Driven by the escalating global agricultural workforce shortage and the urgent need to meet the “Zero Hunger” mandate, the automation of harvest–transport workflows has emerged as a cornerstone of Agriculture 4.0. This paper highlights the latest research progress in multi-robot collaborative logistics scheduling across highly unstructured farming environments, underpinned by cutting-edge spatial perception and digital twin frameworks. Initially, we summarize the technological leap from conventional 2D geometric mapping to multi-modal semantic 3D reconstruction—fusing light detection and ranging (LiDAR), unmanned aerial vehicle (UAV) imagery, and spatial data—to enable high-fidelity forward-looking predictions. The discussion then transitions to algorithmic advancements, emphasizing the shift from traditional centralized operations research to decentralized, data-driven approaches such as Multi-Agent Reinforcement Learning (MARL). We also explore micro-kinematic predictive control mechanisms and the growing integration of ecological sustainability metrics into routing models. To demonstrate practical engineering progress, multi-agent implementations are analyzed across three typical spatial settings: high-throughput continuous relays in open fields, global navigation satellite system (GNSS)-denied discrete routing in dense orchards, and close-proximity human–robot collaboration (HRC) in smart greenhouses. Finally, we identify the remaining barriers to the large-scale commercialization of Agricultural Cyber-Physical Systems (ACPS), such as the “Sim-to-Real” gap restricted by edge-computing capacities, unclosed economic loops, and HRC ethical dilemmas, offering a forward-looking roadmap for next-generation resilient agricultural networks. Full article

The Overall Equipment Effectiveness (OEE) indicator is a widely used key performance indicator (KPI) in industrial environments to assess equipment efficiency through the combination of availability, performance, and quality metrics. However, its direct application to renewable energy systems presents significant limitations due to the stochastic nature of the energy resource and the operating characteristics of wind turbines. This paper proposes an adaptation of Overall Equipment Effectiveness (OEE) for the wind energy sector, referred to as Overall Equipment Effectiveness for Renewable Energy (OEE_RE), in which the traditional availability, performance, and quality factors are reformulated to reflect the operational reality of utility-scale wind turbines. The proposed methodology defines the OEE_RE indicators using variables directly available from standard wind farm Supervisory Control and Data Acquisition systems (SCADA), enabling practical implementation without additional instrumentation. Special attention is devoted to the calculation of the performance indicator, which incorporates manufacturer power curve normalization according to IEC 61400-12 recommendations, including air density correction and turbulence intensity compensation. The quality indicator is derived from turbine-level electrical parameters associated with power generation performance. The methodology is validated using operational measurements collected from seven wind turbines within a commercial wind farm. The results demonstrate the feasibility of the proposed approach and show that performance and quality are the dominant contributors to OEE_RE variability, while availability remains close to unity under normal operating conditions. The proposed framework provides a practical and interpretable KPI for monitoring wind turbine efficiency, identifying operational deviations, and supporting performance optimization in renewable energy assets. Full article

Climate change poses significant challenges to agricultural production, water availability, and food and nutrition security, particularly in semi-arid regions where rural livelihoods depend heavily on rain-fed agriculture. In Eswatini, increasing temperatures, erratic rainfall, and recurrent droughts have intensified pressures on smallholder farming systems; however, limited empirical research has examined how climate variability simultaneously affects agriculture, water resources, and household food security within an integrated food–water–nutrition nexus framework. Therefore, this study assessed the impacts of climate change on agricultural production, water availability, food security, and access to nutritious food among smallholder households in the Lubombo Region of Eswatini. A concurrent triangulated mixed-methods approach was employed, combining quantitative data from 880 households with qualitative insights from open-ended responses. Descriptive statistics, Spearman’s correlation, binary logistic regression, and thematic analysis were used to analyse the data. The findings reveal that climate change significantly affects both agricultural and water systems, which in turn directly influence household food security outcomes. The majority of households reported declining crop yields (56.5%), widespread food shortages (79.5%), meal skipping (69.0%), and high levels of food-related anxiety (87.6%). Water insecurity is also prevalent, with over 83% of households experiencing water shortages and nearly all respondents indicating that climate change has affected water access. Correlation and regression analyses demonstrate that drought frequency and reduced rainfall are the strongest predictors of both water insecurity and food insecurity, highlighting the central role of climate variability. Water scarcity emerged as a critical pathway linking climate change to food insecurity, with strong associations between water shortages and reduced crop yields, food shortages, and coping strategies such as skipping meals. Qualitative findings further highlighted declining agricultural productivity, loss of traditional foods, reduced dietary diversity, and increased psychological stress associated with food insecurity. The study concludes that food insecurity in the Lubombo region is multidimensional, driven by the interconnected effects of climate variability, water scarcity, and socio-economic constraints. The findings emphasise the need for integrated, climate-resilient strategies that simultaneously address agricultural production, water resource management, and household adaptive capacity to enhance food and nutrition security. Future research should evaluate the effectiveness of nexus-based adaptation strategies and climate-smart interventions in enhancing long-term food, water, and nutrition security in vulnerable smallholder farming systems. Full article

Background: Manure-amended agricultural soil is a critical reservoir of antibiotic resistance genes (ARGs), posing escalating threats to environmental health and food safety. However, the temporal trajectories of ARG prevalence throughout the complete reproductive cycle of cash crops, and their mechanistic linkages with fertilization regimes and microbial community succession, remain inadequately understood. Methods: To bridge this knowledge gap, we conducted an in situ field experiment over the entire growth period of Chinese cabbage at a long-term manure-amended farm in Tianjin, China. Six contrasting fertilization strategies were evaluated: unfertilized control (CK1), unfertilized baseline control (CK2), traditional full-rate combined manure–chemical fertilization (TF), traditional half-rate combined manure–chemical fertilization (T1), half-dose sole manure fertilizer (T2), and half-dose sole chemical fertilizer only (T3). Results: Our results demonstrated that ARG abundance and associated mobile genetic elements (MGEs) exhibited a pronounced transient surge immediately post-fertilization, yet reverted to baseline levels by harvest, revealing a tangible resilience of the soil resistome. Notably, the optimized half-organic fertilization (T2) effectively curtailed the proliferation of manure-derived pathogenic taxa while preserving beneficial keystone phyla (e.g., Acidobacteria and Proteobacteria), indicating a trade-off between nutrient provisioning and ecological filtering. Co-occurrence network analysis further identified MB-A2-108, Saccharimonadales, and Rokubacteriales as pivotal hosts for multidrug-resistant ARGs, underscoring that microbial interspecific interactions—rather than taxonomic richness alone—are the primary drivers of resistome succession. Quantitative risk assessment confirmed that the T2 regimen reduced the composite ARG contamination index (CF_zone) by 25% relative to conventional full fertilization (TF), while maintaining comparable cabbage yields. Conclusions: Collectively, our findings advocate for precision organic fertilization as a nature-based solution that synchronizes nutrient supply with crop demand, curtails ARG propagation, and mitigates long-term agroecological risks. 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

Intelligent agents are emerging as an important system-level paradigm for smart agriculture. This review focuses on modern agricultural intelligent agents driven by large language models and related multimodal foundation models and examines how this emerging field is reshaping the organization of intelligent agricultural systems. It first clarifies the conceptual boundaries of agricultural intelligent agents and distinguishes them from traditional multi-agent systems, agent-based modeling, agricultural foundation models, and static retrieval-augmented question-answering systems. It then synthesizes their architectural foundations, key capabilities, application scenarios, deployment challenges, and future research directions. The reviewed literature indicates that agricultural intelligent agents are moving beyond isolated perception, prediction, and response generation toward the goal-oriented coordination of agricultural knowledge, dynamic data, external tools, and decision-making processes across agricultural task chains. They are beginning to support more integrated forms of knowledge services, crop monitoring and diagnosis, decision support, and farm-level collaborative management. Nevertheless, their transition from prototype systems to dependable and deployable agricultural systems remains constrained by context-aware knowledge grounding, heterogeneous data and tool integration, long-horizon reliability, the stability of multi-agent collaboration, and system security. This review further introduces an assessment perspective based on evidence reported in the original studies, comparing representative agricultural intelligent agents in terms of task decomposition, agronomic evidence applicability, tool-use validity, workflow reliability, multi-agent coordination, and deployment-related evidence. By distinguishing demonstrated capabilities from unevaluated dimensions, this review provides a structured framework for understanding the current status of agricultural intelligent agents and for guiding their future development toward reliable, deployable, and domain-oriented intelligent systems for smart agriculture. Full article

Agricultural drones have been increasingly adopted to improve production efficiency and address labor shortages in agriculture. However, their broader socioeconomic effects remain unclear, particularly regarding whether drone-assisted farming may increase unemployment pressure or attract excessive capital intervention that threatens farmers’ access to farmland and the sustainable development of agricultural production systems. To address these issues, this study evaluates the development scale and economic effects of agricultural drones in China. A comparative analytical framework is constructed to quantify production costs, return on investment (ROI), and labor demand under traditional and drone-assisted farming modes. Corn and citrus are selected as representative grain and fruit crops for empirical analysis. The results indicate the following: (1) Drone-assisted farming reduces production costs. (2) At the baseline prices, the ROI of drone-assisted corn and citrus production increases to 10.53% and 7.65%, respectively, but remains low, suggesting a limited risk of excessive capital intervention. (3) At the national scale, drone-assisted farming generates estimated cost savings for corn and citrus. (4) In terms of labor effects, agricultural drones mainly help alleviate agricultural labor shortages rather than generate large-scale unemployment, while also improving production efficiency and supporting sustainable agricultural development. Full article

Accurate wind speed forecasting plays a crucial role in the safe and stable operation of wind farms and the efficient integration of renewable energy into modern power systems. However, wind speed exhibits complex spatiotemporal variations affected by diverse meteorological conditions, making high-precision prediction a long-standing bottleneck in wind power scheduling. This paper develops a U-shaped spatiotemporal feature fusion network named U-STNet, which realizes joint modeling of inter-turbine spatial correlations and multi-period long-range temporal dependencies. The model maps raw wind speed series to high-dimensional embeddings and adopts an encoder–decoder U-shaped architecture to complete feature encoding, reconstruction and multi-scale feature extraction, which effectively captures the inherent periodic and seasonal patterns of wind speed. Experiments on the SDWPF wind farm dataset show that U-STNet obtains competitive prediction accuracy across all multi-step forecasting horizons. Compared with traditional statistical models, recurrent neural networks and state-of-the-art Transformer baselines, the proposed method exhibits more stable error accumulation characteristics and superior long-step prediction performance. This verifies the effectiveness of jointly modeling turbine spatial topology and multi-scale temporal dependencies for wind speed forecasting. Full article

In response to the severe challenges posed by extreme sandstorm weather to the operational safety of WTs and grid stability, this paper proposes an MPC-based power optimization control strategy for WFs. Simulation results indicate that, compared with the traditional PD strategy, the proposed MPC strategy significantly reduces the active power fluctuations of individual WTs, smoothly tracks grid dispatch orders with an overall power tracking accuracy improvement, and effectively lowers the operational risk index of turbines across the farm (ranging from 6.90% to 57.14% for the ten evaluated turbines). Furthermore, the proposed strategy substantially mitigates the angular acceleration fluctuation amplitude of the drive train components (e.g., reducing peak angular accelerations of drive-train masses by up to 35%) and reduces the fore-aft and lateral displacement oscillations of the tower top (reducing peak displacement variations by approximately 25% and 40%, respectively), providing comprehensive structural load mitigation while ensuring WF power output stability and grid safety. This study provides a theoretical basis and technical approach for the intelligent operation and risk prevention and control of WFs under extreme meteorological conditions. Full article