Search Results (51)

This paper presents a novel deep learning framework for traffic crash prediction that leverages graph-based representations to model complex interactions among road users. At its core is a dynamic Graph Attention Network (GAT), which abstracts road users and their interactions as evolving nodes and edges in a spatiotemporal graph. Each node represents an individual road user, characterized by its state as features, such as location and velocity. A node-wise Long Short-Term Memory (LSTM) network is employed to capture the temporal evolution of these features. Edges are dynamically constructed based on spatial and temporal proximity, existing only when distance and time thresholds are met for modeling interaction relevance. The GAT learns attention-weighted representations of these dynamic interactions, which are subsequently used by a classifier to predict the risk of a crash. Experimental results demonstrate that the proposed GAT-based method achieves 86.1% prediction accuracy, highlighting its effectiveness for proactive collision risk assessment and its potential to inform real-time warning systems and preventive safety interventions. Full article

High penetration of renewable energy sources complicates static voltage stability assessment, as conventional line-based indices are typically derived under restrictive assumptions, such as neglecting voltage-angle differences or decoupling active and reactive power effects, which may lead to inaccurate proximity signals under RES-rich operating conditions. The proposed research study develops an enhanced voltage stability index (EVSI) from a two-port π line model that explicitly retains line impedance, active and reactive power terms, and voltage-angle difference between the sending and receiving ends; secure system operation satisfies EVSI < 1. Unlike classical indices, EVSI preserves the coupled physical interactions most relevant to voltage collapse while maintaining a closed-form structure suitable for online monitoring. EVSI is evaluated in a coupled transmission–distribution setting with solar photovoltaic-based distributed generation under varying penetration levels and loadings, using PV-curve nose points as collapse references, and benchmarked against classical indices. Across scenarios, EVSI remains closest to unity at the nose point, accurately tracing the collapse boundary and consistently identifying weak buses, whereas the traditional indices exhibit dispersed values and sensitivity to operating assumptions. The proposed results indicate that EVSI offers a reliable and computationally convenient indicator for online assessment and early warning of voltage instability in renewable-integrated, coupled transmission–distribution networks. Full article

Tree-covered urban green spaces, including streets, parks, and other public areas, are vital for urban sustainability and people’s well-being. However, such trees face threats from the occurrence of extreme weather. In this study, we investigated wind damage to urban trees in the city of Debrecen, Hungary, during two severe windstorms in July 2025. Field surveys were conducted across three distinct urban zones, covering approximately 515,000 m² in total. We assessed 201 damaged and 325 undamaged trees and recorded the species, size, damage type, and contextual landscape features associated with them being damaged or not. Damage type to trees consisted primarily of broken branches, whilst uprooting and trunk breakage were recorded less often. Most tree characteristics (trunk circumference, height, systematic position, nativity) and the proximity and height of buildings upwind of focal trees were significant predictors of their vulnerability to windstorms. In addition, we surveyed 150 residents in person and received comments from 54 people via online questionnaires and explored their perceptions of storm frequency, the causes of storms, and mitigation measures. Most respondents noted increased storm frequency and attributed that to climate change, and they suggested mitigation measures focused on urban tree management and environmental protection. Some people expressed scepticism about the presence of climate change and/or their ability to address such damage on an individual basis. Our study is the first to integrate assessments of storm-related impacts on urban trees with the opinions of residents living in proximity to them. Our findings highlight the need for climate-adaptive and mechanically robust urban forestry planning and offer insights that guide the management of trees in urban areas globally. Specifically, we propose to undertake the following: (1) Prioritise structurally resilient, stress-tolerant tree species adapted to extreme weather conditions when planting new trees. (2) Integrate wind dynamics, microclimatic effects and artificial stabilisation techniques into urban design processes to optimise tree placement and their long-term stability. Urban planners, builders, developers, and homeowners should be informed about these stabilising practices and incorporate the needs of trees early in the design process, rather than as decorative additions. (3) Develop regionally calibrated risk models and early-warning systems to support proactive and data-driven tree management and public safety. (4) Promote climate literacy and public participation to strengthen collective stewardship and resilience of urban trees. Full article

The lake surface water temperature (LSWT) is one of the key indicators for monitoring and predicting changes in lake ecosystems, as it regulates numerous physical and biogeochemical processes. However, current LSWT measurements mainly rely on infrared thermometry and traditional in situ sensors, and lack effective short-term LSWT forecasting and early warning capabilities. To overcome these limitations, we established a high-frequency, real-time, and accurate monitoring and forecasting method for the LSWT based on a novel hyperspectral proximal sensing system (HPSs). An LSWT inversion method was constructed based on a deep neural network (DNN) algorithm with a satisfactory accuracy of R² = 0.99, RMSE = 0.92 °C, MAE = 0.64 °C. An analysis of data collected from October 2021 to December 2023 revealed distinct seasonal fluctuations in the LSWT in the northern region of Lake Taihu, with the LSWT ranging from 2.61 °C to 38.52 °C. The hourly LSWT for the next three days was forecasted based on a long short-term memory (LSTM) model, with the accuracy having an R² = 0.99, an RMSE = 1.01 °C, and an MAE = 0.87 °C. This study complements lake water quality monitoring and early warning systems and supports a deeper understanding of dynamic processes within lake physical systems. Full article

Discovering and selecting relevant geospatial datasets from heterogeneous sources remains difficult in conventional geoportals, where keyword-based search often fails to capture thematic relationships or user intent. This article presents an ontology-based framework that augments geoportals with semantic-aware discovery and selection. The contributions are as follows: (1) the geospatial metadata ontology (GMO), which reuses W3C and OGC ontologies and aligns with ISO 19115 to provide a uniform metadata representation enriched with thematic hierarchies and relations; and (2) GeoFit, a discovery framework that integrates GMO into geoportal workflows. The framework extends conventional functionality by enabling semantic query expansion, faceted exploration of thematic hierarchies, and ranking of datasets according to conceptual proximity and fitness-for-use criteria. These capabilities demonstrate how ontology integration operationalizes domain knowledge in the discovery process and makes dataset selection more interpretable and targeted. Validation demonstrated feasibility in the context of natural hazard Early Warning Systems (EWSs), where the prototype surfaced datasets relevant to different components, organized them into ranked and navigable results, and illustrated portability of the method to applied settings. The study confirms that embedding an ontology layer into geoportals provides semantic capabilities absent from keyword-only interfaces and establishes a foundation for extending discovery functions in heterogeneous geospatial infrastructures. Full article

With the rapid expansion of offshore wind farms (OWFs), ensuring maritime safety in adjacent waters has become an increasingly critical challenge. This study proposes an innovative dynamic risk assessment method that integrates a fusion gravity model into a complex network framework to comprehensively evaluate ship importance in OWF areas. By treating ships and wind farms as network nodes and modeling their interactions using AIS data, the method effectively captures spatiotemporal traffic dynamics and precisely quantifies ship importance. Multiple network indicators, including centrality, clustering coefficient, and vertex strength, are fused to comprehensively assess node criticality. A case study in the Yangtze River Estuary empirically demonstrates that ship importance is not static but dynamically and significantly changes with trajectories, interactions with other vessels, and proximity to OWFs, successfully identifying high-risk ships and sensitive OWF areas. The contribution of this research lies in providing a data-driven, quantifiable, novel framework capable of real-time identification of potential threats in maritime traffic. This approach offers direct and practical insights for traffic control, early warning system development, and optimizing maritime traffic management policies, facilitating a shift from reactive response to proactive prevention. Ultimately, it enhances safety supervision efficiency and decision-making support in complex maritime environments, safeguarding the sustainable development of the offshore wind industry. Full article

The Mw 7.8 Gorkha Earthquake of 25 April 2015 triggered over 25,000 landslides across central Nepal, with 4775 events concentrated in Gorkha District alone. Despite substantial advances in landslide susceptibility mapping, existing studies often overlook the compound role of post-seismic rainfall and lack robust spatial validation. To address this gap, we validated an ensemble machine learning framework for co-seismic landslide susceptibility modeling by integrating seismic, geomorphological, hydrological, and anthropogenic variables, including cumulative post-seismic rainfall. Using a balanced dataset of 4775 landslide and non-landslide instances, we evaluated the performance of Logistic Regression (LR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) models through spatial cross-validation, SHapley Additive exPlanations (SHAP) explainability, and ablation analysis. The RF model outperformed all others, achieving an accuracy of 87.9% and a Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) value of 0.94, while XGBoost closely followed (AUC = 0.93). Ensemble models collectively classified over 95% of observed landslides into High and Very High susceptibility zones, demonstrating strong spatial reliability. SHAP analysis identified elevation, proximity to fault, peak ground acceleration (PGA), slope, and rainfall as dominant predictors. Notably, the inclusion of post-seismic rainfall substantially improved recall and F1 scores in ablation experiments. Spatial cross-validation revealed the superior generalizability of ensemble models under heterogeneous terrain conditions. The findings underscore the value of integrating post-seismic hydrometeorological factors and spatial validation into susceptibility assessments. We recommend adopting ensemble models, particularly RF, for operational hazard mapping in earthquake-prone mountainous regions. Future research should explore the integration of dynamic rainfall thresholds and physics-informed frameworks to enhance early warning systems and climate resilience. Full article

Tunnel construction poses significant safety challenges due to confined spaces, limited visibility, and the dynamic movement of labourers and machinery. This study addresses a critical gap in real-time, bidirectional proximity monitoring by developing and validating a prototype early-warning system that integrates real-time location systems (RTLS) with long-range (LoRa) wireless communication and ultra-wideband (UWB) positioning. The system comprises Arduino nano microcontrollers, organic light-emitting diode (OLED) displays, and piezo buzzers to detect and signal proximity breaches between workers and equipment. Using an action research approach, three pilot case studies were conducted in a simulated tunnel environment to test the system’s effectiveness in both static and dynamic risk scenarios. The results showed that the system accurately tracked proximity and generated timely alerts when safety thresholds were crossed, although minor delays of 5–8 s and slight positional inaccuracies were noted. These findings confirm the system’s capacity to enhance situational awareness and reduce reliance on manual safety protocols. The study contributes to the tunnel safety literature by demonstrating the feasibility of low-cost, real-time monitoring solutions that simultaneously track labour and machinery. The proposed RTLS framework offers practical value for safety managers and informs future research into automated safety systems in complex construction environments. Full article

As the world’s third-longest river supporting 40% of China’s population, the Yangtze River Basin exemplifies the critical challenges of balancing riparian development and ecological resilience for major fluvial systems globally. This study analyzed the spatiotemporal evolution, proximity dynamics to the Yangtze River, and driving mechanisms of the “three types of spaces” (urban, agricultural, and ecological) in 130 counties along the Yangtze River mainstem from 2000 to 2020, utilizing an integrated approach incorporating land use transfer matrices, centroid-based distance metrics and GeoDetector models. Key findings reveal: (1) Urban space exhibited significant irreversible expansion while agricultural space continued to shrink, with ecological space maintaining overall stability but showing high-frequency bidirectional conversion with agricultural areas in localized zones. (2) Spatial proximity analysis demonstrated contrasting patterns—eastern riparian counties showed urban spatial agglomeration towards the river, whereas most mid-western regions experienced urban expansion away from the watercourse, with marked regional disparities in agricultural and ecological spatial changes. (3) Driving mechanism analysis identified topography as the dominant natural factor influencing ecological space evolution, while socioeconomic factors exerted stronger impacts on proximity variations of agricultural and urban spaces, with natural–socioeconomic interactive effects showing the most significant explanatory power. These spatial dynamics reflect universal trade-offs between economic development and ecosystem conservation in large river basins worldwide. We advocate differentiated spatial governance strategies, including rigorous riparian ecological redlines, eco-agricultural models in agricultural retreat zones, and proximity-based real-time monitoring for ecological early warning. The integrated methodology and spatial governance framework offer transferable solutions for sustainable management of major fluvial systems under rapid urbanization pressure. These findings provide scientific evidence and implementable pathways for coordinating socioeconomic development with ecosystem resilience in the Yangtze River Economic Belt. Full article

With the continuous improvement of China’s power grid, safety issues in substation operation and maintenance have become increasingly prominent. However, the existing electrical proximity early-warning devices are inadequate for the complex environments of substations, highlighting the urgent need to develop new electrical proximity early-warning technologies. Based on the safety needs of substation operators, this paper proposes an electrical proximity early-warning method that integrates ‘electric field + distance’. It combines MEMS electric field test technology with ultrasonic ranging technology and designs a double-criterion electrical proximity early-warning device. Based on the COMSOL 6.0 finite-element electric field simulation and the construction safety specification for substation equipment, a multistage electric-field early-warning threshold has been reasonably formulated. A field test conducted at a 220 kV substation demonstrates that this device can issue alerts for various electrical proximity threat levels of the circuit breaker within 0.1 s, which is faster and more accurate than existing commercial electrical proximity early-warning devices. The double-criterion early-warning system minimizes the risk of missed alarms during multi-distance measurements. Additionally, its flexible warning threshold accommodates the increasingly complex operational requirements of substations. Full article

The paper presents a study of an intelligent system for personnel positioning, transport, and equipment monitoring in the mining industry using convolutional neural network (CNN) and OpenPose technology. The proposed framework operates through a three-stage pipeline: OpenPose-based skeleton extraction from surveillance video streams, capturing 18 key body joints at 30fps; multimodal feature fusion, combining skeletal key points and proximity sensor data to achieve environmental context awareness and obtain relevant feature values; and hierarchical pose alert, using attention-enhanced bidirectional LSTM (trained on 5000 annotated fall instances) for fall warning. The experiment conducted demonstrated that the combined use of the aforementioned technologies allows the system to determine the location and behavior of personnel, calculate the distance to hazardous areas in real time, and analyze personnel postures to identify possible risks such as falls or immobility. The system’s capacity to track the location of vehicles and equipment enhances operational efficiency, thereby mitigating the risk of accidents. Additionally, the system provides real-time alerts, identifying abnormal behavior, equipment malfunctions, and safety hazards, thus promoting enhanced mine management efficiency, improved safe working conditions, and a reduction in accidents. Full article

With the development of industry and society, explosives are widely used in social production as an important industrial product and require transportation. Explosives transport vehicles are susceptible to various objective factors during driving, increasing the risk of transportation. At present, new transport vehicles are generally equipped with intelligent driving monitoring systems. However, for old transport vehicles, the cost of installing such systems is relatively high. To enhance the safety of older explosives transport vehicles, this study proposes a cost-effective intelligent monitoring system using consumer-grade IP cameras and edge computing. The system integrates YOLOv8 for real-time vehicle detection and a novel hybrid ranging strategy combining monocular (fast) and binocular (accurate) techniques to measure distances, ensuring rapid warnings and precise proximity monitoring. An optimized stereo matching workflow reduces processing latency by 23.5%, enabling real-time performance on low-cost devices. Experimental results confirm that the system meets safety requirements, offering a practical, application-specific solution for improving driving safety in resource-limited explosive transport environments. Full article

The dynamics of large-scale components of the Earth climate system (tipping elements), particularly the identification of their possible critical transitions and the proximity to the corresponding tipping points, has been attracting considerable attention recently. In this paper, we focus on one specific tipping element, namely ocean anoxia. It has been shown previously that a sufficiently large, ‘over-critical’ increase in the average water temperature can disrupt oxygen production by phytoplankton photosynthesis, hence crossing the tipping point, which would lead to global anoxia. Here, using a conceptual mathematical model of the plankton–oxygen dynamics, we show that this tipping point of global oxygen depletion is going to be preceded by an additional, second tipping point when the Oxygen Minimum Zones (OMZs) start growing. The OMZ growth can, therefore, be regarded as a spatially explicit early warning signal of the global oxygen catastrophe. Interestingly, there is growing empirical evidence that the OMZs have indeed been growing in different parts of the ocean over the last few decades. Thus, this observed OMZ growth may indicate that the second tipping point has already been crossed, and hence, the first tipping point of global ocean anoxia may now be very close. Full article

This research presents the design of a brake fluid pressure warning and control system for autonomous vehicles (AVs) used on university campuses to control brake fluid pressure and measure the proximity of objects or obstacles in front of the vehicles using LiDAR. The goal was to reduce the jerking of the vehicle caused by the conventional braking system, which may cause danger to the user. We initially changed the existing brake system, which uses human braking force, to electric motor braking and tested it in a closed area (a test track) before actual use. This research was divided into two parts: Part 1—using LiDAR to create warnings in case there are obstacles in front of the vehicle and Part 2—controlling brake fluid pressure using a linear motor and a PD controller. Under the test conditions employed, at a speed of 20 km/h, the total load of passengers is 600 kg. The design results regarding the PD controller with the most suitable values of the system that prevent the vehicle from jerking are K_D = 27.9606 and K_P = 32.0490. The test was conducted while an object crossed the vehicle’s path at distances of 5, 10, 15, and 20 m, respectively. It was found that controlling brake fluid pressure by measuring the distance from the object helped reduce the braking time and jerking of the vehicle and could stop the vehicle before experiencing a collision. At a distance of 20 m, the vehicle could be stopped before the crash and was 3.7 m away from the object; at a distance of 15 m, the distance from the object was 3.1 m; and at a distance of 10 m, the distance from the object was 3 m. However, at a distance of 5 m, the brake system could not stop the vehicle, causing collision with the object because the distance from the object for braking was less than the designed distance. This shows that the warning system and the brake fluid pressure control system can operate in accordance with the corresponding conditions correctly, smoothly, and quickly within the specified distance and be applied to other types of vehicles. Full article

Collision accidents involving construction vehicles and workers frequently occur at construction sites. Computer vision (CV) technology presents an efficient solution for collision-risk pre-warning. However, CV-based methods are still relatively rare and need an enhancement of their performance. Therefore, a novel three-stage collision-risk pre-warning model for construction vehicles and workers is proposed in this paper. This model consists of an object-sensing module (OSM), a trajectory prediction module (TPM), and a collision-risk assessment module (CRAM). In the OSM, the YOLOv5 algorithm is applied to identify and locate construction vehicles and workers; meanwhile, the DeepSORT algorithm is applied to the real-time tracking of the construction vehicles and workers. As a result, the historical trajectories of vehicles and workers are sensed. The original coordinates of the data are transformed to common real-world coordinate systems for convenient subsequent data acquisition, comparison, and analysis. Subsequently, the data are provided to a second stage (TPM). In the TPM, the optimized transformer algorithm is used for a real-time trajectory prediction of the construction vehicles and workers. In this paper, we enhance the reliability of the general object detection and trajectory prediction methods in the construction environments. With the assistance afforded by the optimization of the model’s hyperparameters, the prediction horizon is extended, and this gives the workers more time to take preventive measures. Finally, the prediction module indicates the possible trajectories of the vehicles and workers in the future and provides these trajectories to the CRAM. In the CRAM, the worker’s collision-risk level is assessed by a multi-factor-based collision-risk assessment rule, which is innovatively proposed in the present work. The multi-factor-based assessment rule is quantitatively involved in three critical risk factors, i.e., velocity, hazardous zones, and proximity. Experiments are performed within two different construction site scenarios to evaluate the effectiveness of the collision-risk pre-warning model. The research results show that the proposed collision pre-warning model can accurately predict the collision-risk level of workers at construction sites, with good tracking and predicting effect and an efficient collision-risk pre-warning strategy. Compared to the classical models, such as social-GAN and social-LSTM, the transformer-based trajectory prediction model demonstrates a superior accuracy, with an average displacement error of 0.53 m on the construction sites. Additionally, the optimized transformer model is capable of predicting six additional time steps, which equates to approximately 1.8 s. The collision pre-warning model proposed in this paper can help improve the safety of construction vehicles and workers. Full article