Search Results (5,891)

Soil moisture is a key factor in the exchange of energy and matter between the soil and atmosphere, playing a vital role in the hydrological cycle and agricultural management. Traditional monitoring methods are limited in achieving large-scale, real-time observations, while deep learning offers new avenues to model the complex nonlinear relationships between spectral features and soil moisture content. This study focuses on the Wei-Ku Oasis in Xinjiang, using multi-source remote sensing data (Landsat series and Sentinel-1) and in situ multi-layer soil moisture measurements. The BOSS feature selection algorithm was applied to construct 46 feature parameters, including vegetation indices, soil indices, and microwave indices, and to identify optimal variable sets for each depth. Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and their hybrid model (CNN-LSTM) were used to build soil moisture inversion models at various depths. Their performances were systematically compared on both training and testing sets, and the optimal model was used for spatiotemporal mapping. The results show that the CNN-LSTM-based multi-depth soil moisture inversion model achieved superior performance, with the 0–10 cm model showing the highest accuracy and a testing R² of 0.64, outperforming individual models. The testing R² values for the soil moisture inversion models at depths of 10–20 cm, 20–40 cm, and 40–60 cm were 0.59, 0.54, and 0.59, respectively. According to the mapping results, soil moisture in the 0–60 cm profile of the Wei-Ku Oasis exhibited a vertical gradient, increasing with depth. Spatially, soil moisture was higher in the central oasis and lower toward the periphery, forming a “center-high, edge-low” pattern. This study provides a high-accuracy method for multi-layer soil moisture remote sensing in arid regions, offering valuable data support for oasis water resource management and precision irrigation planning. Full article

The activities of birds present increasing challenges in agriculture, aviation, and environmental conservation. This has led to economic losses, safety risks, and ecological imbalances. Attempts have been made to address the problem, with traditional deterrent methods proving to be labour-intensive, environmentally unfriendly, and ineffective over time. Advances in artificial intelligence (AI) and the Internet of Things (IoT) present opportunities for enabling automated real-time bird detection and repellence. This study reviews recent developments (2020–2025) in AI-driven bird detection and repellence systems, emphasising the integration of image, audio, and multi-sensor data in IoT and edge-based environments. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used, with 267 studies initially identified and screened from key scientific databases. A total of 154 studies met the inclusion criteria and were analysed. The findings show the increasing use of convolutional neural networks (CNNs), YOLO variants, and MobileNet in visual detection, and the growing use of lightweight audio-based models such as BirdNET, MFCC-based CNNs, and TinyML frameworks for microcontroller deployment. Multi-sensor fusion is proposed to improve detection accuracy in diverse environments. Repellence strategies include sound-based deterrents, visual deterrents, predator-mimicking visuals, and adaptive AI-integrated systems. Deployment success depends on edge compatibility, power efficiency, and dataset quality. The limitations of current studies include species-specific detection challenges, data scarcity, environmental changes, and energy constraints. Future research should focus on tiny and lightweight AI models, standardised multi-modal datasets, and intelligent, behaviour-aware deterrence mechanisms suitable for precision agriculture and ecological monitoring. Full article

In the southeast of China, seasonal rainfall intensity is high, the distribution of mountains and hills is extensive, and many small-scale, shallow landslides frequently occur after consecutive seasons of heavy rainfall. High-precision automated identification systems can quickly pinpoint the scope of the disaster and help with important decisions like evacuating people, managing engineering, and assessing damage. Many people have designed systems for detecting such shallow landslides, but few have designed systems that combine high resolution, high automation, and real-time capability of landslide identification. Taking accuracy, automation, and real-time capability into account, we designed an automatic rainfall-induced shallow landslide detection system based on deep learning and Unmanned Aerial Vehicle (UAV) images. The system uses UAVs to capture high-resolution imagery, the U-Net (a U-shaped convolutional neural network) to combine multi-scale features, an adaptive edge enhancement loss function to improve landslide boundary identification, and the development of the “UAV Cruise Geological Hazard AI Identification System” software with an automated processing chain. The system integrates UAV-specific preprocessing and achieves a processing speed of 30 s per square kilometer. It was validated in Wanli District, Nanchang City, Jiangxi Province. The results show a Mean Intersection over Union (MIoU) of 90.7% and a Pixel Accuracy of 92.3%. Compared with traditional methods, the system significantly improves the accuracy of landslide detection. Full article

The present-day issues related to the cotton-growing industry, namely yield estimation, pest effect, and growth phase diagnostics, call for integrated, scalable monitoring solutions. This write-up reveals Cotton Multitask Learning (CMTL), a transformer-driven multitask framework that launches three major agronomic tasks from UAV pictures at one go: boll detection, pest damage segmentation, and phenological stage classification. CMTL does not change separate pipelines, but rather merges these goals using a Cross-Level Multi-Granular Encoder (CLMGE) and a Multitask Self-Distilled Attention Fusion (MSDAF) module that both allow mutual learning across tasks and still keep their specific features. The biologically guided Stage Consistency Loss is the part of the architecture of the network that enables the system to carry out growth stage transitions that occur in reality. We executed CMTL on a tri-source UAV dataset that fused over 2100 labeled images from public and private collections, representing a variety of crop stages and conditions. The model showed its virtues state-of-the-art baselines in all the tasks: setting 0.913 mAP for boll detection, 0.832 IoU for pest segmentation, and 0.936 accuracy for growth stage classification. Additionally, it runs at the fastest speed of performance on edge devices such as NVIDIA Jetson Xavier NX (Manufactured in Shanghai, China), which makes it ideal for deployment. These outcomes evoke CMTL’s promise as a single and productive instrument of aerial crop intelligence in precision cotton agriculture. Full article

The shrubland ecosystems in arid areas are highly sensitive to global climate change and human activities. Accurate extraction of shrubs using computer vision techniques plays an essential role in monitoring ecological balance and desertification. However, shrub extraction from high-resolution GF-2 satellite images remains challenging due to their dense distribution and small size, along with complex background. Therefore, this study introduces a Feature Enhancement and Transformer Network (FETNet) by integrating the Feature Enhancement Module (FEM) and Transformer module (EdgeViT). Correspondently, they can strengthen both global and local features and enable accurate segmentation of small shrubs in complex backgrounds. The ablation experiments demonstrated that incorporation of FEM and EdgeViT can improve the overall segmentation accuracy, with 1.19% improvement of the Mean Intersection Over Union (MIOU). Comparison experiments show that FETNet outperforms the two leading models of FCN8s and SegNet, with the MIOU improvements of 7.2% and 0.96%, respectively. The spatial details of the extracted results indicated that FETNet is able to accurately extract dense, small shrubs while effectively suppressing interference from roads and building shadows in spatial details. The proposed FETNet enables precise shrub extraction in arid areas and can support ecological assessment and land management. Full article

With the explosive growth of Internet of Things (IoT) devices, massive amounts of heterogeneous data are continuously generated. However, IoT data transactions and sharing face multiple challenges such as limited device resources, untrustworthy network environment, highly sensitive user privacy, and serious data silos. How to achieve fine-grained access control and privacy protection for massive devices while ensuring secure and reliable data circulation has become a key issue that needs to be urgently addressed in the current IoT field. To address the above challenges, this paper proposes a blockchain-based data transaction and privacy protection framework. First, the framework builds a multi-layer security architecture that integrates blockchain and IPFS and adapts to the “end–edge–cloud” collaborative characteristics of IoT. Secondly, a data sharing mechanism that takes into account both access control and interest balance is designed. On the one hand, the mechanism uses attribute-based encryption (ABE) technology to achieve dynamic and fine-grained access control for massive heterogeneous IoT devices; on the other hand, it introduces a game theory-driven dynamic pricing model to effectively balance the interests of both data supply and demand. Finally, in response to the needs of confidential analysis of IoT data, a secure computing scheme based on CKKS fully homomorphic encryption is proposed, which supports efficient statistical analysis of encrypted sensor data without leaking privacy. Security analysis and experimental results show that this scheme is secure under standard cryptographic assumptions and can effectively resist common attacks in the IoT environment. Prototype system testing verifies the functional completeness and performance feasibility of the scheme, providing a complete and effective technical solution to address the challenges of data integrity, verifiable transactions, and fine-grained access control, while mitigating the reliance on a trusted central authority in IoT data sharing. Full article

Named Data Networking (NDN) represents a promising Information-Centric Networking architecture that addresses limitations of traditional host-centric Internet protocols by emphasizing content names rather than host addresses for communication. While NDN offers advantages in content distribution, mobility support, and built-in security features, its stateful forwarding plane introduces significant vulnerabilities, particularly Interest Flooding Attacks (IFAs). These IFA attacks exploit the Pending Interest Table (PIT) by injecting malicious interest packets for non-existent or unsatisfiable content, leading to resource exhaustion and denial-of-service attacks against legitimate users. This survey examines research advances in IFA detection and mitigation from 2013 to 2024, analyzing seven relevant published detection and mitigation strategies to provide current insights into this evolving security challenge. We establish a taxonomy of attack variants, including Fake Interest, Unsatisfiable Interest, Interest Loop, and Collusive models, while examining their operational characteristics and network performance impacts. Our analysis categorizes defense mechanisms into five primary approaches: rate-limiting strategies, PIT management techniques, machine learning and artificial intelligence methods, reputation-based systems, and blockchain-enabled solutions. These approaches are evaluated for their effectiveness, computational requirements, and deployment feasibility. The survey extends to domain-specific implementations in resource-constrained environments, examining adaptations for Internet of Things deployments, wireless sensor networks, and high-mobility vehicular scenarios. Five critical research directions are proposed: adaptive defense mechanisms against sophisticated attackers, privacy-preserving detection techniques, real-time optimization for edge computing environments, standardized evaluation frameworks, and hybrid approaches combining multiple mitigation strategies. Full article

Modern cloud-based Internet of Things (IoT) infrastructures face increasingly sophisticated and diverse cyber threats that challenge traditional detection systems in terms of scalability, adaptability, and explainability. In this paper, we present (H-DIR)², a hybrid entropy-based framework designed to detect and mitigate anomalies in large-scale heterogeneous networks. The framework combines Shannon entropy analysis with Associated Random Neural Networks (ARNNs) and integrates semantic reasoning through RDF/SPARQL, all embedded within a distributed Apache Spark 3.5.0 pipeline. We validate (H-DIR)² across three critical attack scenarios—SYN Flood (TCP), DAO-DIO (RPL), and NTP amplification (UDP)—using real-world datasets. The system achieves a mean detection latency of 247 ms and an AUC of 0.978 for SYN floods. For DAO-DIO manipulations, it increases the packet delivery ratio from 81.2% to 96.4% (p < 0.01), and for NTP amplification, it reduces the peak load by 88%. The framework achieves vertical scalability across millions of endpoints and horizontal scalability on datasets exceeding 10 TB. All code, datasets, and Docker images are provided to ensure full reproducibility. By coupling adaptive neural inference with semantic explainability, (H-DIR)² offers a transparent and scalable solution for cloud–IoT cybersecurity, establishing a robust baseline for future developments in edge-aware and zero-day threat detection. Full article

Efficient task offloading for delay-sensitive applications, such as autonomous driving, presents a significant challenge in multi-hop Vehicular Edge Computing (VEC) networks, primarily due to high vehicle mobility, dynamic network topologies, and complex end-to-end congestion problems. To address these issues, this paper proposes a graph attention-based reinforcement learning algorithm, named GAPO. The algorithm models the dynamic VEC network as an attributed graph and utilizes a graph neural network (GNN) to learn a network state representation that captures the global topological structure and node contextual information. Building on this foundation, an attention-based Actor–Critic framework makes joint offloading decisions by intelligently selecting the optimal destination and collaboratively determining the ratios for offloading and resource allocation. A multi-objective reward function, designed to minimize task latency and to alleviate link congestion, guides the entire learning process. Comprehensive simulation experiments and ablation studies show that, compared to traditional heuristic algorithms and standard deep reinforcement learning methods, GAPO significantly reduces average task completion latency and substantially decreases backbone link congestion. In conclusion, by deeply integrating the state-aware capabilities of GNNs with the decision-making abilities of DRL, GAPO provides an efficient, adaptive, and congestion-aware solution to the resource management problems in dynamic VEC environments. Full article

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks. Full article

Carbon flow tracking and spatial pattern optimization at the scale of urban functional zones are key scientific challenges in achieving carbon neutrality. However, due to the complexity of carbon metabolism processes within urban functional zones, related studies remain limited. To address these scientific challenges, this study, based on the “source–sink–flow” ecosystem services framework, develops an integrated analytical approach at the scale of urban functional zones. The carbon balance is quantified using the CASA model in combination with multi-source data. A network model is employed to trace carbon flow pathways, identify critical nodes and interruption points, and optimize the urban spatial pattern through a low-carbon land use structure model. The research results indicate that the overall carbon balance in Hangzhou exhibits a spatial pattern of “deficit in the center and surplus in the periphery.” The main urban area shows a significant carbon deficit and relatively poor connectivity in the carbon flow network. Carbon sequestration services primarily flow from peripheral areas (such as Fuyang and Yuhang) with green spaces and agricultural functional zones toward high-emission residential–commercial and commercial–public functional zones in the central area. However, due to the interruption of multiple carbon flow paths, the overall carbon flow transmission capacity is significantly constrained. Through spatial optimization, some carbon deficit nodes were successfully converted into carbon surplus nodes, and disrupted carbon flow edges were repaired, particularly in the main urban area, where 369 carbon flow edges were restored, resulting in a significant improvement in the overall transmission efficiency of the carbon flow network. The carbon flow visualization and spatial optimization methods proposed in this paper provide a new perspective for urban carbon metabolism analysis and offer theoretical support for low-carbon city planning practices. Full article

Critical Internet of Things (IoT) data in Fifth Generation Vehicular Ad Hoc Networks (5G VANETs) demands Ultra-Reliable Low-Latency Communication (URLLC) to support mission-critical vehicular applications such as autonomous driving and collision avoidance. Achieving the stringent Quality of Service (QoS) requirements for these applications remains a significant challenge. This paper proposes a novel framework integrating Software-Defined Networking (SDN) and Network Functions Virtualisation (NFV) as embedded functionalities in connected vehicles. A lightweight SDN Controller model, implemented via vehicle on-board computing resources, optimised QoS for communications between connected vehicles and the Next-Generation Node B (gNB), achieving a consistent packet delivery rate of 100%, compared to 81–96% for existing solutions leveraging SDN. Furthermore, a Software-Defined Wide-Area Network (SD-WAN) model deployed at the gNB enabled the efficient management of data, network, identity, and server access. Performance evaluations indicate that SDN and NFV are reliable and scalable technologies for virtualised and distributed 5G VANET infrastructures. Our SDN-based in-vehicle traffic classification model for dynamic resource allocation achieved 100% accuracy, outperforming existing Artificial Intelligence (AI)-based methods with 88–99% accuracy. In addition, a significant increase of 187% in flow rates over time highlights the framework’s decreasing latency, adaptability, and scalability in supporting URLLC class guarantees for critical vehicular services. Full article

Traditional unmanned aerial vehicle (UAV) detection and tracking methods have long faced the twin challenges of high cost and poor efficiency. In real-world battlefield environments with complex backgrounds, occlusions, and varying speeds, existing techniques struggle to track small UAVs accurately and stably. To tackle these issues, this paper presents an enhanced YOLOv8N-Drone-based algorithm for improved target tracking of small UAVs. Firstly, a novel module named C2f-DSFEM (Depthwise-Separable and Sobel Feature Enhancement Module) is designed, integrating Sobel convolution with depthwise separable convolution across layers. Edge detail extraction and multi-scale feature representation are synchronized through a bidirectional feature enhancement mechanism, and the discriminability of target features in complex backgrounds is thus significantly enhanced. For the feature confusion problem, the improved lightweight Context Anchored Attention (CAA) mechanism is integrated into the Neck network, which effectively improves the system’s adaptability to complex scenes. By employing a position-aware weight allocation strategy, this approach enables adaptive suppression of background interference and precise focus on the target region, thereby improving localization accuracy. At the level of loss function optimization, the traditional classification loss is replaced by the focal loss (Focal Loss). This mechanism effectively suppresses the contribution of easy-to-classify samples through a dynamic weight adjustment strategy, while significantly increasing the priority of difficult samples in the training process. The class imbalance that exists between the positive and negative samples is then significantly mitigated. Experimental results show the enhanced YOLOv8 boosts mean average precision (Map@0.5) by 12.3%, hitting 99.2%. In terms of tracking performance, the proposed YOLOv8 N-Drone algorithm achieves a 19.2% improvement in Multiple Object Tracking Accuracy (MOTA) under complex multi-scenario conditions. Additionally, the IDF1 score increases by 6.8%, and the number of ID switches is reduced by 85.2%, indicating significant improvements in both accuracy and stability of UAV tracking. Compared to other mainstream algorithms, the proposed improved method demonstrates significant advantages in tracking performance, offering a more effective and reliable solution for small-target tracking tasks in UAV applications. Full article

The accurate detection of small objects remains a critical challenge in autonomous driving systems, where improving detection performance typically comes at the cost of increased model complexity, conflicting with the lightweight requirements of edge deployment. To address this dilemma, this paper proposes LEAD-YOLO (Lightweight Efficient Autonomous Driving YOLO), an enhanced network architecture based on YOLOv11n that achieves superior small object detection while maintaining computational efficiency. The proposed framework incorporates three innovative components: First, the Backbone integrates a lightweight Convolutional Gated Transformer (CGF) module, which employs normalized gating mechanisms with residual connections, and a Dilated Feature Fusion (DFF) structure that enables progressive multi-scale context modeling through dilated convolutions. These components synergistically enhance small object perception and environmental context understanding without compromising network efficiency. Second, the neck features a hierarchical feature fusion module (HFFM) that establishes guided feature aggregation paths through hierarchical structuring, facilitating collaborative modeling between local structural information and global semantics for robust multi-scale object detection in complex traffic scenarios. Third, the head implements a shared feature detection head (SFDH) structure, incorporating shared convolution modules for efficient cross-scale feature sharing and detail enhancement branches for improved texture and edge modeling. Extensive experiments validate the effectiveness of LEAD-YOLO: on the nuImages dataset, the method achieves 3.8% and 5.4% improvements in mAP@0.5 and mAP@[0.5:0.95], respectively, while reducing parameters by 24.1%. On the VisDrone2019 dataset, performance gains reach 7.9% and 6.4% for corresponding metrics. These findings demonstrate that LEAD-YOLO achieves an excellent balance between detection accuracy and model efficiency, thereby showcasing substantial potential for applications in autonomous driving. Full article

UAV-based inspections are an effective way to ensure railway safety and have gained significant attention. However, images captured during complex weather conditions, such as rain, snow, or fog, often suffer from severe degradation, affecting image recognition accuracy. Existing algorithms for removing rain, snow, and fog have two main limitations: they do not adaptively learn features under varying weather complexities and struggle with managing complex noise patterns in drone inspections, leading to incomplete noise removal. To address these challenges, this study proposes a novel framework for removing rain, snow, and fog from drone images, called WeatherClean. This framework introduces a Weather Complexity Adjustment Factor (WCAF) in a parameterized adjustable network architecture to process weather degradation of varying degrees adaptively. It also employs a hierarchical multi-scale cropping strategy to enhance the recovery of fine noise and edge structures. Additionally, it incorporates a degradation synthesis method based on atmospheric scattering physical models to generate training samples that align with real-world weather patterns, thereby mitigating data scarcity issues. Experimental results show that WeatherClean outperforms existing methods by effectively removing noise particles while preserving image details. This advancement provides more reliable high-definition visual references for drone-based railway inspections, significantly enhancing inspection capabilities under complex weather conditions and ensuring the safety of railway operations. Full article