Search Results (4,917)

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

Infrastructure as code (IaC) is essential for modern cloud development, enabling teams to define, deploy, and manage infrastructure in a consistent and repeatable manner. As organizations migrate to Azure, selecting the right approach is crucial for managing complexity, minimizing errors, and supporting DevOps practices. This paper examines the use of Azure Bicep with GitHub Actions to automate infrastructure deployment for an application in the Azure cloud. It explains how Bicep improves readability, modularity, and integration compared to traditional ARM templates and other automation tools. The solution utilizes a modular Bicep design to deploy resources, including virtual networks, managed identities, container apps, databases, and AI services, with environment-specific parameters for development, QA, and production. GitHub Actions workflows automate the building, deployment, and tearing down of infrastructure, ensuring consistent deployments across environments. Security considerations include managed identities, private networking, and secret management in continuous integration (CI) and continuous delivery (CD) pipelines. This paper provides a detailed architectural overview, workflow analysis, and implementation guidance to help teams adopt a robust, automated approach to Azure infrastructure deployment. By leveraging automation tooling and modern DevOps practices, organizations can streamline delivery and maintain secure, maintainable cloud environments. Full article

Barn districts—ensembles of agricultural buildings situated at the edges of rural settlements—once played a key role in the spatial and economic organization of agrarian communities in Central Europe. Today, many of these structures remain marginalized and underexplored in contemporary landscape and heritage planning. This paper presents a comparative study of six barn districts in Poland’s Kraków-Częstochowa Upland, where vernacular construction, ecological adaptation, and local tradition shaped distinctive rural–urban interfaces. We applied a mixed-methods approach combining cartographic and archival analysis, field surveys, and interviews with residents and experts. The research reveals consistent patterns of landscape transformation, functional decline, and latent adaptive potential across varied morphological and material typologies. Despite differing levels of preservation, barn districts retain symbolic, spatial, and socio-cultural value for communities and local landscapes. The study emphasizes the importance of reintegrating these marginal heritage structures through adaptive reuse strategies rooted in the values of the New European Bauhaus—sustainability, aesthetics, and inclusion. The findings contribute to broader discussions on rural socio-ecological resilience and landscape-based development, highlighting how place-based strategies can bridge past identities with future-oriented spatial planning. Full article

Three-dimensional environment reconstruction refers to the creation of mathematical models of three-dimensional objects suitable for computer representation and processing. This paper proposes a novel 3D environment reconstruction approach that addresses the field-of-view limitations commonly faced by LiDAR-based systems. A rotary-driven LiDAR mechanism is designed to enable uniform and seamless full-field-of-view scanning, thereby overcoming blind spots in traditional setups. To complement the hardware, a multi-sensor fusion framework—LV-SLAM (LiDAR-Visual Simultaneous Localization and Mapping)—is introduced. The framework consists of two key modules: multi-threaded feature registration and a two-phase loop closure detection mechanism, both designed to enhance the system’s accuracy and robustness. Extensive experiments on the KITTI benchmark demonstrate that LV-SLAM outperforms state-of-the-art methods including LOAM, LeGO-LOAM, and FAST-LIO2. Our method reduces the average absolute trajectory error (ATE) from 6.90 m (LOAM) to 2.48 m, and achieves lower relative pose error (RPE), indicating improved global consistency and reduced drift. We further validate the system in real-world indoor and outdoor environments. Compared with fixed-angle scans, the rotary LiDAR mechanism produces more complete reconstructions with fewer occlusions. Geometric accuracy evaluation shows that the root mean square error between reconstructed and actual building dimensions remains below 5 cm. The proposed system offers a robust and accurate solution for high-fidelity 3D reconstruction, particularly suitable for GNSS-denied and structurally complex environments. Full article

Proxy re-signature enables transitive authentication of digital identities across different domains and has significant application value in areas such as digital rights management, cross-domain certificate validation, and distributed system access control. However, most existing proxy re-signature schemes, which are predominantly based on traditional public-key cryptosystems, face security vulnerabilities and certificate management bottlenecks. While identity-based schemes alleviate some issues, they introduce key escrow concerns. Certificateless schemes effectively resolve both certificate management and key escrow problems but remain vulnerable to quantum computing threats. To address these limitations, this paper constructs an efficient post-quantum certificateless proxy re-signature scheme based on algebraic lattices. Building upon algebraic lattice theory and leveraging the Dilithium algorithm, our scheme innovatively employs a lattice basis reduction-assisted parameter selection strategy to mitigate the potential algebraic attack vectors inherent in the NTRU lattice structure. This ensures the security and integrity of multi-party communication in quantum-threat environments. Furthermore, the scheme significantly reduces computational overhead and optimizes signature storage complexity through structured compression techniques, facilitating deployment on resource-constrained devices like Internet of Things (IoT) terminals. We formally prove the unforgeability of the scheme under the adaptive chosen-message attack model, with its security reducible to the hardness of the corresponding underlying lattice problems. 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

Aiming at the lightweight design of a bridge-shed integration structure, this paper presents a three-layered absorbing system in which a part of the sand cushion is replaced by expanded polystyrene (EPS) geofoam and the reinforced concrete (RC) protective slab is arranged above the sand cushion to enhance the composite system’s safety. A three-dimensional Smoothed Particle Hydrodynamics–Finite Element Method (SPH-FEM) coupled numerical model is developed in LS-DYNA (Livermore Software Technology Corporation, Livermore, CA, USA, version R13.1.1), with its validity rigorously verified. The dynamic response of rockfall impacts on the shed slab with composite cushions of various thicknesses is analyzed by varying the thickness of sand and EPS materials. To optimize the cushion design, a specific energy dissipation ratio (SEDR), defined as the energy dissipation rate per unit mass (η/M), is introduced as a key performance metric. Furthermore, the complicated interactional mechanism between the rockfall and the optimum-thickness composite system is rationally interpreted, and the energy dissipation mechanism of the composite cushion is revealed. Using logistic regression, the ultimate stress state of the reactive powder concrete (RPC) slab is methodically analyzed, accounting for the speed and mass of the rockfall. The results are indicative of the fact that the composite cushion not only has less dead weight but also exhibits superior impact resistance compared to the 90 cm sand cushions; the impact resistance performance index SEDR of the three-layered absorbing system reaches 2.5, showing a remarkable 55% enhancement compared to the sand cushion (SEDR = 1.61). Additionally, both the sand cushion and the RC protective slab effectively dissipate most of the impact energy, while the EPS material experiences relatively little internal energy build-up in comparison. This feature overcomes the traditional vulnerability of EPS subjected to impact loads. One of the highlights of the present investigation is the development of an identification model specifically designed to accurately assess the stress state of RPC slabs under various rockfall impact conditions. Full article

Accomplishing China’s national targets of carbon peaking and carbon neutrality necessitates proactive solutions, hinging critically on fundamentally transforming rural construction models. Current construction practices in rural areas are characterized by inefficiency, high resource consumption, and reliance on imported materials. These shortcomings not only jeopardize the attainment of climate objectives, but also hinder equitable development between urban and rural regions. Using the Digital Industrial Park in Yongtai County, Fuzhou City, as a case study, this study focuses on prefabricated public buildings in regions with extreme hot–humid climate, and innovatively integrates BIM (Building Information Modeling)-driven carbon modeling with the Gaussian Two-Step Floating Catchment Area (G2SFCA) method for spatial accessibility assessment to investigate the carbon emissions and economic benefits of prefabricated buildings during the embodied stage, and analyzes the spatial accessibility of prefabricated building material suppliers in Fuzhou City and identifies associated bottlenecks, seeking pathways to promote sustainable rural revitalization. Compared with traditional cast-in-situ buildings, embodied carbon emissions of prefabricated during their materialization phase significantly reduced. This dual-perspective approach ensures that the proposed solutions possess both technical rigor and logistical feasibility. Promoting this model across rural areas sharing similar climatic conditions would advance the construction industry’s progress towards the dual carbon goals. Full article

Machine learning and artificial intelligence have transformed fault detection and maintenance strategies for industrial machinery. This study applies well-established data-driven techniques to a rarely explored industrial application—the condition monitoring of high-precision paper cutting machines—enhancing condition-based maintenance to improve operational efficiency, safety, and cost-effectiveness. A key element of the proposed approach is the integration of an infrared pyrometer into vibration monitoring, utilizing accelerometer data to evaluate the state of health of machinery. Unlike traditional fault detection studies that focus on extreme degradation states, this work successfully identifies subtle deviations from optimal, which even expert technicians struggle to detect. Building on a feasibility study conducted with Tecnau SRL, a comprehensive diagnostic system suitable for industrial deployment is developed. Endurance tests pave the way for continuous monitoring under various operating conditions, enabling real-time industrial diagnostic applications. Multi-scale signal analysis highlights the significance of transient and steady-state phase detection, improving the effectiveness of real-time monitoring strategies. Despite the physical similarity of the classified states, simple time-series statistics combined with machine learning algorithms demonstrate high sensitivity to early-stage deviations, confirming the reliability of the approach. Additionally, a systematic analysis to downgrade acquisition system specifications identifies cost-effective sensor configurations, ensuring the feasibility of industrial implementation. Full article

Mars has been a primary focus of planetary science, with significant advancements over the past two decades across disciplines including geological evolution, surface environment, and atmospheric and space science. However, the rapid growth of the related literature has rendered traditional manual review methods increasingly inadequate. This inadequacy is particularly evident in interdisciplinary research, which is often characterized by dispersed topics and complex semantics. To address this challenge, this study proposes an automated analysis framework based on natural language processing (NLP) to systematically review the Martian research in Earth and space science over the past two decades. The research database contains 151,196 Mars-related sentences extracted from 10,655 publications spanning 2001 to 2024. Using machine learning techniques, the framework clusters Mars-related sentences into semantically coherent groups and applies topic modeling to extract core research themes. It then analyzes their temporal evolution across the Martian solid, surface, atmosphere, and space environments. Finally, through sentiment analysis and semantic matching, it highlights unresolved scientific questions and potential directions for future research. This approach offers a novel perspective on the knowledge structure underlying Mars exploration and demonstrates the potential of NLP for large-scale literature analysis in planetary science. The findings potentially provide a structured foundation for building an interdisciplinary, peer-reviewed Mars knowledge base, which may inform future scientific research and mission planning. Full article

To meet the demands for real-time and accurate fault warning of wind turbine gear transmission systems, this study proposes an innovative intelligent warning method based on the integration of digital twin and multi-source data fusion. A digital twin system architecture is developed, comprising a high-precision geometric model and a dynamic mechanism model, enabling real-time interaction and data fusion between the physical transmission system and its virtual model. At the algorithmic level, a CNN-LSTM-Attention fault prediction model is proposed, which innovatively integrates the spatial feature extraction capabilities of a convolutional neural network (CNN), the temporal modeling advantages of long short-term memory (LSTM), and the key information-focusing characteristics of an attention mechanism. Experimental validation shows that this model outperforms traditional methods in prediction accuracy. Specifically, it achieves average improvements of 0.3945, 0.546 and 0.061 in Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared (R²) metrics, respectively. Building on the above findings, a monitoring and early warning platform for the wind turbine transmission system was developed, integrating digital twin visualization with intelligent prediction functions. This platform enables a fully intelligent process from data acquisition and status evaluation to fault warning, providing an innovative solution for the predictive maintenance of wind turbines. Full article

With the increasing awareness of energy consumption issues, there has been a growing emphasis on energy-saving retrofits for central air-conditioning systems that constitute a significant proportion of energy consumption in buildings. Efficient energy utilization can be achieved by optimizing the modeling of the equipment within the chiller plants of central air-conditioning systems. Traditional modeling approaches have been static and have focused on modeling within narrow time frames when a certain amount of equipment operating data has accumulated, thus prioritizing the precision of the model itself while overlooking the fact that energy-saving retrofits are a long-term process. This study proposes a modeling scheme for the equipment within chiller plants throughout the energy-saving retrofit process. Based on the differences in the amount of available operating data for the equipment and the progress of retrofit implementation, the retrofit process was divided into three stages, each employing different modeling techniques and ensuring smooth transitions between the stages. The equipment within the chiller plants is categorized into two types based on the clarity of their operating characteristics, and two modeling schemes are proposed accordingly. Based on the proposed modeling scheme, chillers and chilled-water pumps were selected to represent the two types of equipment. Real operating data from actual retrofit projects was used to model the equipment and evaluate the accuracy of the model predictions. The results indicate that the models established by the proposed modeling scheme exhibit good accuracy at each stage of the retrofit, with the coefficients of variation (CV) remaining below 6.88%. Furthermore, the prediction accuracy improved as the retrofitting process progressed. The modeling scheme performs better on equipment with simpler and clearer operating characteristics, with a CV as low as 0.67% during normal operation stages. This underscores the potential application of the proposed modeling scheme throughout the energy-saving retrofit process and provides a model foundation for the subsequent optimization of the refrigeration system. Full article

To sustainably power future urban communities, cities require advanced solar energy planning tools that overcome the limitations of traditional approaches, such as data fragmentation and siloed decision-making. SDTs present a transformative opportunity by enabling precision urban modelling, integrated simulations, and iterative decision support. However, their application in solar energy planning remains underexplored. This study introduces SDT4Solar, a novel SDT-based framework designed to integrate city-scale rooftop solar planning through 3D building semantisation, solar modelling, and a unified geospatial database. By leveraging advanced spatial modelling and Internet of Things (IoT) technologies, SDT4Solar facilitates high-resolution 3D solar potential simulations, improving the accuracy and equity of solar infrastructure deployment. We demonstrate the framework through a proof-of-concept implementation in Ballarat East, Victoria, Australia, structured in four key stages: (a) spatial representation of the urban built environment, (b) integration of multi-source datasets into a unified geospatial database, (c) rooftop solar potential modelling using 3D simulation tools, and (d) dynamic visualization and analysis in a testbed environment. Results highlight SDT4Solar’s effectiveness in enabling data-driven, spatially explicit decision-making for rooftop PV deployment. This work advances the role of SDTs in urban energy transitions, demonstrating their potential to optimise efficiency in solar infrastructure planning. Full article

Traditional path planning algorithms often fail to simultaneously ensure operational efficiency, energy constraint compliance, and environmental adaptability in agricultural scenarios, thereby hindering the advancement of precision agriculture. To address these challenges, this study proposes a deep reinforcement learning algorithm, MoE-D3QN, which integrates a Mixture-of-Experts mechanism with a Bi-directional Long Short-Term Memory model. This design enhances the efficiency and robustness of UAV path planning in agricultural environments. Building upon this algorithm, a hierarchical coverage path planning framework is developed. Multi-level task maps are constructed using crop information extracted from Sentinel-2 remote sensing imagery. Additionally, a dynamic energy consumption model and a progressive composite reward function are incorporated to further optimize UAV path planning in complex farmland conditions. Simulation experiments reveal that in the two-level scenario, the MoE-D3QN algorithm achieves a coverage efficiency of 0.8378, representing an improvement of 37.84–63.38% over traditional algorithms and 19.19–63.38% over conventional reinforcement learning methods. The redundancy rate is reduced to 3.23%, which is 38.71–41.94% lower than traditional methods and 4.46–42.77% lower than reinforcement learning counterparts. In the three-level scenario, MoE-D3QN achieves a coverage efficiency of 0.8261, exceeding traditional algorithms by 52.13–71.45% and reinforcement learning approaches by 10.15–50.2%. The redundancy rate is further reduced to 5.26%, which is significantly lower than the 57.89–92.11% observed with traditional methods and the 15.57–18.98% reported for reinforcement learning algorithms. These findings demonstrate that the MoE-D3QN algorithm exhibits high-quality planning performance in complex farmland environments, indicating its strong potential for widespread application in precision agriculture. Full article

Residential green space is an important component of urban green space and one of the major indicators for evaluating the quality of a residential community. Traditional indicators such as the green space ratio only consider the relationship between green space area and total area of the residential community while ignoring the difference in the amount of green space enjoyed by household residents in high-rise and low-rise buildings. Therefore, it is meaningful to estimate household green space and its spatial distribution in residential communities. However, there are frequent difficulties in obtaining specific green space area and household number through ground surveys or consulting with property management units. In this study, taking a composite residential community in Chongqing, China, as the study site, we first employed a five-lens drone to capture its oblique RGB images and generated the DOM (Digital Orthophoto Map). Subsequently, the green space area and distribution in the entire residential community were extracted from the DOM using VDVI (Visible Difference Vegetation Index). The YOLACT (You Only Look At Coefficients) instance segmentation model was used to recognize balconies from the facade images of high-rise buildings to determine their household numbers. Finally, the average green space per household in the entire residential community was calculated to be 67.82 m², and those in the high-rise and low-rise building zones were 51.28 m² and 300 m², respectively. Compared with the green space ratios of 65.5% and 50%, household green space more truly reflected the actual green space occupation in high- and low-rise building zones. Full article