Search Results (959)

The temperature management models for solar greenhouses exhibit strong regional dependency. Their application in non-target environments often faces significant limitations, frequently resulting in severe temperature control deviations. To address this challenge, seven solar greenhouses located in Lingyuan (Liaoning Province) and Yinan (Shandong Province) were utilized as experimental platforms. Using real-time environmental data collected by the NEUT-80S IoT monitoring system, backpropagation (BP) neural network models were trained and validated. Multiple stepwise regression analysis identified total solar radiation and sunshine duration as the primary determinants of cucumber yield. Based on these findings, a dynamic weight matrix was constructed using a solar radiation clustering algorithm. By integrating similarity distance and similarity coefficient, a microclimate similarity determination logic was established, leading to the proposal of an automatic model selection strategy with an 11-day update cycle. Quantitative validation demonstrated that when the threshold conditions—a similarity coefficient (R) ≥ 0.6 and a similarity distance (D) ≤ 0.85—are met, triggering the optimally matched model significantly improves the simulation goodness-of-fit (R²) from 0.6716 in the unmatched state to 0.9851. This strategy effectively achieves the cross-regional adaptation of high-yield temperature management models, providing robust technical support for the advancement of precision protected agriculture. Full article

With the continuous growth of global population and increasing pressure on food security, the transformation toward precise and intelligent agricultural production has become an inevitable trend. In this context, accurate identification of field weeds is crucial for improving crop yields and reducing agricultural inputs. However, agricultural Internet of Things (IoT) edge devices are generally subject to strict constraints in terms of power consumption, storage, and real-time performance. Existing lightweight convolutional neural networks often struggle to simultaneously achieve high accuracy and low resource consumption for fine-grained weed identification tasks. To address this challenge, this paper proposes a hardware aware lightweight convolutional neural network named Weed-Aware Ghost Enhanced Network (WAGENet) for microcontroller deployment. The network synergistically integrates Ghost low-cost feature generation, Mobile Inverted Bottleneck Convolution (MBConv) for deep semantic extraction, Squeeze and Excitation (SE) and Coordinate Attention (CA) dual attention mechanisms for channel space joint calibration, and Atrous Spatial Pyramid Pooling (ASPP) for multi-scale context fusion. It constructs a progressive feature abstraction system from shallow textures to high-level semantics. On the public DeepWeeds dataset, WAGENet achieves 95.71% classification accuracy and 93.80% F1 score with only 0.163 M parameters and 2.43 × 10⁸ multiply accumulate operations (MACC), attaining a parameter efficiency of 587.19%/M and significantly outperforming existing mainstream lightweight models. The model has been successfully deployed on the STM32H7B3I microcontroller development board, achieving a single inference latency of 94.63 ms, an internal Flash footprint of only 686.95 KiB, and a single inference energy consumption of 41.45 mJ. Experimental results demonstrate that WAGENet achieves a trade off among accuracy, latency, and energy consumption under strict resource constraints, providing a reproducible microcontroller deployment paradigm for battery powered field robots, drones, and other agricultural IoT edge devices. Full article

Asymmetry is a prevalent phenomenon in low-power and lossy networks (LLNs) due to resource constraints and unstable links. The routing protocol for the low power and lossy network (RPL), standardized by the Internet Engineering Task Force (IETF), is specifically designed for LLNs with characteristics of resource constraints, lossy links, and complex communication environments. However, its performance is fundamentally limited by node capabilities and unstable links, a contradiction exacerbated by the stringent QoS demands of emerging applications like IIoT or precision agriculture. Consequently, new RPL routing technologies based on the digital twin-enabled computing power network, called RPL-DTCP, were designed to improve network QoS and support practical applications. First, a low-power and lossy network architecture based on twin-enabled computing network was proposed, considering LLN requirements and computing twin services. Second, in response to the requirements of the digital twin, computing power network and LLNs for low synchronization latency, high data accuracy, efficient computing resource utilization, and energy conservation, several routing metrics were designed, including the data processing model, model deployment rate, end-to-end delay, node remaining energy, and ETX. Then an initial matrix and a comprehensive objective function were formulated to comprehensively evaluate these metrics. Third, to solve the multi-objective optimization problem, an enhanced whale optimization algorithm (E-WOA) was developed. E-WOA improved upon the standard version by using improved Tent chaotic mapping for population initialization, nonlinear adaptive convergence factor, and Cauchy variation mutation operator for solution perturbation, thereby enhancing its global search capability and convergence speed, enabling it to effectively identify the optimal routing path. Simulations confirmed that RPL-DTCP outperforms benchmark algorithms, achieving significant reductions in end-to-end delay, higher packet delivery ratios, extended network lifetime, etc. These findings demonstrate that RPL-DTCP effectively addresses the resource-performance contradiction in LLNs, providing a reliable and efficient routing framework for emerging compute-intensive IoT applications. Full article

The Agricultural Energy Internet (AEI) represents an emerging systemic paradigm driven by the convergence of intelligent agriculture and rural energy transformation. It is not a simple extension of agricultural informatization or rural electrification; rather, it redefines agricultural processes—such as irrigation, greenhouse environmental control, supplementary lighting, cold-chain logistics, and agricultural machinery—as perceptible, computable, and schedulable energy-related processes, thereby enabling the deep integration of agriculture, energy, environmental management, and intelligent decision-making. This review systematically examines the evolutionary trajectory of AEI, from early agricultural digitalization and Internet of Things (IoT)-based monitoring to edge intelligence and digital twin technologies, and ultimately to the coordinated optimization of agriculture–energy–environment systems. A comprehensive technical framework is established, encompassing physical energy coupling, multi-source sensing and actuation, interconnection and interoperability, edge–cloud collaborative control, data governance, digital twin modeling, artificial intelligence-enabled optimization, and application-oriented decision-making. The review further highlights that high-quality data governance, edge–cloud collaboration, and digital twin calibration are critical enablers of the transition from visualization-oriented management to closed-loop intelligent operation. In addition, this study clarifies the complementary relationship between agricultural informatization and electrification: the former provides capabilities for perception, prediction, optimization, and coordination, whereas the latter provides a controllable execution chain. Together, they constitute the foundation of a cyber-physical agricultural energy system. Finally, frontier research directions are identified, including high-temperature solid oxide electrolysis for hydrogen production, edge AI–IoT-enabled closed-loop agricultural operation, and privacy, security, and trust mechanisms in federated edge intelligence. The findings suggest that AEI can serve as a strategic technological framework for supporting the next generation of smart agriculture toward low-carbon, resilient, and collaborative operation. Full article

Agricultural soils are a major source of greenhouse gas (GHG) emissions, particularly carbon dioxide (CO₂) and methane (CH₄), highlighting the need for cost-effective and field-applicable monitoring solutions. This study developed and evaluated a low-cost real-time monitoring system for soil CO₂ and CH₄ emissions by integrating surface emission chambers, low-cost gas sensors, a solar-powered energy supply, and IoT-based wireless communication. Three acrylic chambers with different heights (40, 60, and 80 cm) were fabricated to investigate the influence of chamber geometry on measurement performance. System performance was assessed through simultaneous measurements against a Biogas 5000 analyzer under simulated conditions and during field deployment in a sugarcane cultivation area in Khon Kaen Province, Thailand. Relative agreement was used to compare the developed system with the reference instrument. The results showed that relative agreement varied with chamber height for both gases. Under simulated conditions, the 80 cm chamber achieved the highest overall relative agreement for CO₂ and CH₄, underscoring the importance of sufficient headspace volume in chamber-based measurements. Field experiments confirmed the system’s capability for continuous CO₂ monitoring in an agricultural environment. However, CH₄ emissions were not detected during the study period, likely due to drought-induced, well-aerated soil conditions. The developed system demonstrated stable autonomous operation, low energy consumption, and ease of installation, making it suitable for long-term field applications. Overall, the proposed platform provides a practical and scalable approach for real-time soil GHG monitoring and offers strong potential for integration into precision agriculture and climate-smart farming systems to support GHG mitigation strategies. Full article

Water quality has become a major concern for public health, agriculture, and industry, necessitating reliable and continuous monitoring. Conventional monitoring methods are often time-consuming, rely on manual sampling, and involve complex equipment or procedures, making them unsuitable for real-time applications. This study presents an Internet of Things (IoT)-based system for real-time water quality monitoring using ESP32 hardware integrated with the ThingSpeak platform. The system enhances the accuracy of turbidity and pH measurements using advanced sensor calibration techniques. Nephelometric methods and glass electrodes are employed for turbidity detection and pH sensing, respectively, across various water types—including tap water, groundwater, wastewater, saline water, and treated water—to address issues such as environmental drift and measurement inaccuracies. The turbidity sensor was calibrated using a standard six-point method with formazin solutions (0–1064 NTU), whereas pH calibration utilized a three-point approach with NIST-traceable buffer solutions (pH 4, 7, and 10). The results indicate that turbidity measurement errors, initially ranging from 15.75% to 422%, were reduced to below 10% after calibration. Similarly, pH accuracy was significantly improved across all tested water matrices. The system enables real-time data visualization via ThingSpeak, and the implementation of multi-point calibration ensures high data reliability for continuous monitoring. Overall, this approach offers an accurate, efficient, and practical solution for real-time water quality management. Full article

Microgreens have emerged as a nutrient-dense specialty crop with great potential to address global nutritional challenges through urban farming and controlled-environment agriculture. While interest in enhancing both the yield and nutritional quality of hydroponic microgreens is growing, a comprehensive synthesis of horticultural strategies is still lacking. This gap hinders the development of integrated approaches needed for efficient and targeted quality improvement. This review systematically examines the current literature on horticultural interventions for improving hydroponic microgreen production, focusing on nutrient solution management, light environmental manipulation, substrate selection, genetic potential, and emerging synergistic approaches. Nutrient solution optimization, including appropriate concentration, timing, and targeted biofortification with essential elements, enhances both productivity and nutritional density. Light spectral manipulation, particularly through red-to-far-red ratios or blue-light supplementation, enables precise control of morphology and the accumulation of bioactive compounds. Substrate physicochemical properties influence nutrient availability and uptake, while genetic variability among species and cultivars provides the foundation for biofortification efforts. Emerging approaches including biostimulant application, integrated pre- and post-harvest practices, and phenotyping and artificial intelligence integration offer additional avenues for sustainable quality enhancement. This review provides a framework for optimizing hydroponic microgreen production systems to simultaneously achieve high yield and enhanced nutritional quality. Full article

Despite producing much of the world’s food, small-scale farms face severe resource shortages, climate risks, and infrastructure gaps. While digital advances ranging from IoT sensing to AI-driven analytics offer pathways to improve productivity, adoption remains uneven. This integrative review synthesizes evidence on smart-farming technologies specifically for smallholders, identifying primary barriers, enabling conditions, and design principles for successful deployment. Unlike broader smart-farming reviews, the article explicitly evaluates small-farm suitability, evidence quality, and implementation architecture rather than technological capability alone. The synthesis shows that adoption is consistently constrained by clustered barriers, notably high capital and maintenance costs, limited technical capacity, and unreliable electricity or internet access. It also finds that evidence is strongest for modular, offline-capable monitoring and alerting tools, while evidence for durable gains from highly integrated full-platform systems remains thinner and more pilot-dependent. To advance equitable innovation, the review proposes a fit-for-context deployment logic centered on co-design, local repair and advisory capacity, and financing and policy support aligned with small-farm realities. Overall, smart farming can strengthen productivity, resilience, and environmental performance on small farms, but only when technologies are embedded in inclusive service models and implementation systems. Full article

Reliable monitoring of hydraulic networks is essential for efficient and sustainable water management in agriculture. To address the growing need for intelligent, low-latency anomaly detection in such systems, we propose HydroNeuro, a domain-aware embedded framework that integrates hydraulic domain knowledge with data-driven neural inference for the real-time detection of leaks and obstructions. Rather than embedding physical equations directly into the learning objective, we leverage established hydraulic principles, including Bernoulli’s equation and the Darcy–Weisbach formulation, to structure the experimental design, interpret pressure–flow relationships, and ensure physical consistency of the learned representations. These principles confirm that pressure deviations induced by leaks or obstructions are causally explainable and measurable. We employ a fractional factorial design (FFD) to optimize valve activation combinations and sensor configurations during dataset acquisition, thereby reducing redundant experiments, water circulation, and energy consumption while limiting mechanical stress on system components. We deploy a lightweight neural network on an ESP32 microcontroller using TensorFlow Lite for Microcontrollers to enable energy-efficient, low-latency edge inference under severe hardware constraints. Our experimental validation on a laboratory-scale hydraulic testbed demonstrates anomaly detection accuracy exceeding 96%, with strong robustness under sensor noise and hydraulic perturbations. Compared to a multiple linear regression baseline, the proposed neural model reduces the prediction error from an RMSE of 0.58 to 0.12. By coupling physically consistent experimental modeling with embedded neural inference, HydroNeuro provides a scalable and practically deployable solution for autonomous hydraulic monitoring in precision irrigation and smart water distribution systems. Full article

Since the publication of the “Review of Embedded Artificial Intelligence Research” in 2023, driven by innovations in hardware architectures, advances in lightweight algorithms, and the maturation of edge–cloud collaboration technologies, embedded artificial intelligence (embedded AI) has progressed from “technically feasible” to “large-scale deployment”. As a continuation of that review, this article systematically surveys the core advances in embedded AI from 2023 to 2026. At the hardware level, it examines engineering progress in non-von Neumann architectures such as compute-in-memory and neuromorphic chips, as well as heterogeneous integration technologies. At the algorithmic level, it covers dynamic adaptive lightweighting, specialized edge-side optimization of large models (including on-device large language model fine-tuning and edge diffusion models), and lightweight multimodal approaches. In terms of deployment paradigms, it discusses edge-side full training, federated edge learning, edge–cloud collaborative intelligence, and emerging paradigms. At the application level, it illustrates the “perception–decision–execution” pipeline in industrial IoT, wearable healthcare, autonomous driving, embodied intelligence, and smart agriculture. The article also analyzes core challenges including ultra-low-power design for extreme scenarios, cross-platform standardization, edge-side data security and privacy, and model robustness in complex environments. Based on these findings, four research directions are proposed to guide future work. Full article

The transition from conventional laboratory-based soil analysis to real-time, data-driven evaluation has become essential for advancing precision agriculture and ensuring sustainable resource management. This review provides a comprehensive and structured synthesis of emerging technologies for soil evaluation, focusing on the integration of spectrometric sensing, Internet of Things (IoT) systems, and machine learning approaches. A systematic analysis of peer-reviewed studies published between 2012 and 2026 was conducted to assess the performance of these technologies in terms of accuracy, robustness, and scalability under variable environmental conditions. Spectrometry techniques, including visible–near-infrared and mid-infrared sensing, enable rapid and non-destructive estimation of soil chemical properties, while IoT-based sensor networks facilitate continuous in situ monitoring of key parameters such as moisture, pH, and nutrient content. Machine learning models further enhance soil assessment by enabling predictive analytics, data fusion, and high-resolution mapping. Despite their significant potential, challenges related to data quality, model transferability, sensor calibration, and implementation costs remain critical barriers to large-scale adoption. The review highlights the need for standardized evaluation frameworks, improved multimodal data integration, and increased focus on model interpretability and real-world applicability. Overall, the synergistic use of these technologies supports more efficient input management, reduces environmental impact, and contributes to the development of resilient and sustainable agricultural systems. Full article

Accurate estimation of dynamic environmental phenomena through intelligent sensing systems plays a critical role in enabling reliable monitoring and decision-making in complex real-world scenarios. With the rapid development of artificial intelligence-driven sensing technologies and Internet of Things systems, modern agricultural monitoring is evolving from isolated data acquisition toward intelligent, multimodal perception and decision-making. However, traditional approaches predominantly rely on single data sources, making it difficult to simultaneously capture plant phenotypic variations and environment-driven mechanisms, thereby limiting model applicability in complex field scenarios. To address this issue, a multimodal pest density estimation framework, namely the Pest Density Estimation Framework (PDEF), is proposed, which integrates UAV-based imagery, trap monitoring data, and environmental sensor measurements. In this framework, crop canopy damage features are extracted using convolutional neural networks, while temporal encoding is employed to model dynamic environmental variations. Cross-modal feature alignment and environment-aware enhancement mechanisms are further introduced to achieve deep integration of multi-source information, enabling the construction of a unified feature representation space and improving estimation accuracy. Extensive experiments conducted on a constructed multimodal agricultural dataset demonstrate that the proposed method achieves MAE, RMSE, and MAPE values of $5.47$, $7.62$, and $14.9\%$, respectively, significantly outperforming the Transformer-based fusion model (MAE $6.01$, RMSE $8.16$). Meanwhile, the coefficient of determination reaches $R^2=0.84$, indicating superior fitting capability and stability. In multimodal combination experiments, the three-modality fusion reduces error metrics by more than $20\%$ on average compared with single-modality models, validating the effectiveness of multi-source collaborative modeling. From the perspective of integrating plant phenotypic analysis and environmental perception, this study provides a novel AI-driven intelligent sensing framework for pest monitoring and crop management, contributing to improved pest prediction capability and enhanced intelligence in agricultural production systems. This study further provides practical implications for agricultural economics and supply chain optimization by enabling data-driven decision-making through intelligent sensing systems. Full article

Viticulture is highly vulnerable to weather variability and climate change. Growers increasingly face risks associated with extreme weather events, water scarcity, and emerging pests and diseases. To address these challenges, this study presents the development and implementation of the first operational digital decision support platform (DSP) tailored to Montenegrin vineyards within the MONTEVITIS project. The platform integrates IoT sensor data, national meteorological records and high-resolution global climate datasets to provide real-time monitoring and climate projections for vineyard management. The system was piloted in four vineyards representing diverse microclimatic and soil conditions of Montenegro. Key functionalities include phenology, irrigation and disease alerts supported by a user-friendly dashboard, map-based visualisation tools and data export functions. The pilot deployment demonstrated that combining heterogeneous data streams increases the reliability of outputs and enables timely, site-specific recommendations. Challenges identified during implementation include connectivity limitations, gaps in data and variable levels of digital expertise among growers; however, lessons learned point to the importance of continuous stakeholder engagement and institutional support for sustained use. The MONTEVITIS experience demonstrates how digital agriculture tools can bridge tradition and innovation in viticulture. By fostering collaboration between growers, researchers and policy makers, the platform enables adaptive strategies for climate resilience and sustainable vineyard management. Although the platform has been successfully deployed and tested under pilot conditions, a comprehensive long-term validation of its performance and impact on vineyard decision-making remains part of ongoing future work. Full article

This work presents the design, development, and proof-of-concept validation of a smart greenhouse for romaine lettuce (Lactuca sativa var. longifolia) that integrates Internet of Things (IoT) sensing/actuation with an image-based crop state assessment pipeline. The proposed pipeline combines a lightweight AI image classifier with fractal texture descriptors (box-counting fractal dimension) to support the non-destructive monitoring of leaf condition and growth stage. The system also implements resilience-oriented resource strategies, including rainwater harvesting, graywater reuse, and a hybrid power supply (photovoltaic + grid backup). Water and energy indicators are reported as estimated values derived from the prototype operating profile and literature-based baseline values (i.e., contextual comparisons rather than a contemporaneous controlled trial). Using an expanded dataset (n = 1500 images) and an independent held-out test subset (n = 350), the image classifier achieved 97.1% accuracy, with detailed precision/recall/F1 metrics reported in the Results. Overall, the proposed architecture and evaluation workflow provide an accessible and reproducible pathway toward sustainable, low-cost smart greenhouses in resource-constrained settings. Full article

With the rapid development of precision agriculture and smart farming management, accurate crop disease detection has become a critical tool for optimizing agricultural resource allocation, controlling operational costs, and supporting scientific plant protection strategies. However, real-world field environments are often characterized by strong background interference, multiple concurrent diseases, and fine-grained lesion differences, posing significant challenges to existing detection methods in practical agricultural Internet of Things (IoT) applications. In this paper, we propose Freq-spatial Context Dynamic Network(FCDNet), an efficient and cost-effective detection model tailored for multi-category strawberry disease recognition in complex field management scenarios. The proposed model integrates a Freq-Spatial Feature Module (FSFM), a Context Guide Fusion Module (CGFM), and a Task Align Dynamic Detection Head (TADDH), enabling enhanced expression of high-frequency micro-lesions, adaptive filtering of field background noise, and spatial alignment of classification and regression tasks, while maintaining a lightweight architecture suitable for low-cost agricultural edge devices. Extensive experiments conducted on the newly constructed Strawberry Disease Dataset-7(S7DD) demonstrate that FCDNet consistently outperforms existing mainstream methods, achieving an F1-score of 91.0% and an mAP@0.5 of 94.6%. The model’s architectural robustness and capacity for generalization are further substantiated by evaluations across diverse agricultural datasets using PlantDoc and ALDOD. Ultimately, FCDNet became a practical and cost-effective tool for real-time detection of strawberry diseases, directly supporting more accurate yield forecasting and risk management in smart agriculture systems. Full article