Search Results (2,919)

Traditional automated monitoring systems adopted for Intersection Traffic Control still face challenges, including high costs, maintenance difficulties, insufficient coverage, poor multimodal data integration, and limited traffic information analysis. To address these issues, the study proposes a sovereign AI-driven Smart Transportation governance approach, developing a mobile AI solution equipped with multimodal perception, task decomposition, memory, reasoning, and multi-agent collaboration capabilities. The proposed system integrates computer vision, multi-object tracking, natural language processing, Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs) to construct a Pipeline-based Traffic Analysis System (PTAS). The PTAS can produce real-time statistics on pedestrian and vehicle flows at intersections, incorporating potential risk factors such as traffic accidents, construction activities, and weather conditions for multimodal data fusion analysis, thereby providing forward-looking traffic insights. Experimental results demonstrate that the enhanced DuCRG-YOLOv11n pre-trained model, equipped with our proposed new activation function $\beta silu$, can accurately identify various vehicle types in object detection, achieving a frame rate of 68.25 FPS and a precision of 91.4%. Combined with ByteTrack, it can track over 90% of vehicles in medium- to low-density traffic scenarios, obtaining a 0.719 in MOTA and a 0.08735 in MOTP. In traffic flow analysis, the RAG of Vertex AI, combined with Claude Sonnet 4 LLMs, provides a more comprehensive view, precisely interpreting the causes of peak-hour congestion and effectively compensating for missing data through contextual explanations. The proposed method can enhance the efficiency of urban traffic regulation and optimizes decision support in intelligent transportation systems. Full article

This study investigates the characteristics and causes of a low-level wind shear (LLWS) event induced by downward momentum transport at Xining Airport, China on 5 April 2023. By utilizing Doppler Wind Lidar (DWL), Automated Weather Observing System (AWOS), and ERA5 reanalysis data, the detailed structure and synoptic-scale mechanisms of the event were analyzed. The LLWS manifested as a non-convective, meso-γ scale (2–20 km) directional wind shear, characterized by horizontal variations in wind direction. The system moved from northwest to southeast and persisted for approximately three hours. The shear zone was characterized by westerly flow to the west and easterly flow to the east, with their convergence triggering upward motion. The Range Height Indicator (RHI) and Doppler Beam Swinging (DBS) modes of the DWL clearly revealed the features of westerly downward momentum transport. Diagnostic analysis of the synoptic-scale environment reveals that a developing 300-hPa trough steered the merging of the subtropical and polar front jets. This interaction provided a robust source of momentum. The secondary circulation excited in the jet entrance region promoted active vertical motion, facilitating the exchange of momentum and energy between levels. Simultaneously, the development of the upper-level trough led to the intrusion of high potential vorticity (PV) air from the upper levels (100–300 hPa) into the middle troposphere (approximately 500 hPa), which effectively transported high-momentum air downward and dynamically induced convergence in the low-level wind field. Furthermore, the establishment of a deep dry-adiabatic mixed layer in the afternoon provided a favorable thermodynamic environment for momentum transport. These factors collectively led to the occurrence of the LLWS. This study will further deepen the understanding of the formation mechanism of momentum-driven LLWS at plateau airports, and provide a scientific basis for improving the forecasting and warning of such hazardous aviation weather events. Full article

The background error covariance matrix (BE) is a fundamental component of data assimilation (DA) systems. Its impact on both the DA process and subsequent forecast performance depends on model configuration and the types of observations assimilated. However, few studies have specifically examined BE behavior in the context of satellite DA for regional tropical cyclone (TC) prediction. In this study, we develop the BE and evaluate its structure for a TC forecasting system over the western North Pacific. A total of six BEs are modeled using three control variable (CV) schemes (aligned with the CV5, CV6, and CV7 options available in the Weather Research and Forecasting DA system (WRFDA)) with training data from two distinct periods: the TC season and the winter season. Results demonstrate that the BE structure is sensitive to the training data used. The performance of TC-season BEs derived from different CV schemes is assessed for TC track forecasting through the assimilation of microwave sounder satellite brightness temperature data. The evaluation is based on a set of 14 cases from 2018 that exhibited large official track forecast errors. The CV7 BE, which uses the x- and y-direction wind components as CVs, captures finer small-scale momentum error features and yields greater forecast improvement at shorter lead-times (24 h). In contrast, the CV6 BE, which employs stream function (ψ) and unbalanced velocity potential (χ_u) as CVs, incorporates more large-scale momentum error information. The inherent multivariate couplings among analysis variables in this scheme also allow for closer fits to satellite microwave brightness temperature data, which is particularly crucial for forecasting TCs that primarily develop over oceans where conventional observations are scarce. Consequently, it enhances the large-scale environmental field more effectively and delivers superior forecast skill at longer lead times (48 h and 72 h). Full article

In photovoltaic (PV) power generation, the intermittency and uncertainty caused by meteorological factors pose challenges to grid operations. Accurate PV power prediction is crucial for optimizing power dispatching and balancing supply and demand. This paper proposes a PV power prediction model based on Density Peak Clustering Algorithm (DPCA)–Crested Porcupine Optimizer (CPO)–Random Forest (RF)–Gated Recurrent Unit (GRU)–Kolmogorov–Arnold Network (KAN). First, the DPCA is used to accurately classify weather conditions according to meteorological data such as solar radiation, temperature, and humidity. Then, the CPO algorithm is established to optimize the factor screening characteristic variables of the RF. Subsequently, a hybrid GRU model with a KAN layer is introduced for short-term PV power prediction. The Shapley Additive Explanation (SHAP) method values evaluating feature importance and the impact of causal features. Compared with other contrast models, the DPCA-CPO-RF-KAN-GRU model demonstrates better error reduction capabilities under three weather types, with an average fitting accuracy R² reaching 97%. SHAP analysis indicates that the combined average SHAP value of total solar radiation and direct solar radiation contributes more than 70%. Finally, the Kernel Density Estimation (KDE) is utilized to verify that the KAN-GRU model has high robustness in interval prediction, providing strong technical support for ensuring the stability of the power grid and precise decision-making in the electricity market. Full article

Modern port operations face increasing challenges from rapidly changing weather and environmental conditions, requiring accurate short-term forecasting to support safe and efficient maritime activities. This study presents a sensor fusion-based machine learning framework for real-time multi-target nowcasting of wind gust speed, sustained wind speed, and wind direction using heterogeneous data collected at the Port of Livorno from February to November 2025. Using an IoT architecture compliant with the oneM2M standard and deployed at the Port of Livorno, CNIT integrated heterogeneous data from environmental sensors (meteorological stations, anemometers) and vessel-mounted LiDAR systems through feature-level fusion to enhance situational awareness, with gust speed treated as the primary safety-critical variable due to its substantial impact on berthing and crane operations. In addition, a comparative performance analysis of Random Forest, XGBoost, LSTM, Temporal Convolutional Network, Ensemble Neural Network, Transformer models, and a Kalman filter was performed. The results show that XGBoost consistently achieved the highest accuracy across all targets, with near-perfect performance in both single-split testing (R² ≈ 0.999) and five-fold cross-validation (mean R² = 0.9976). Ensemble models exhibited greater robustness than deep learning approaches. The proposed multi-target fusion framework demonstrates strong potential for real-time deployment in Maritime Autonomous Surface Ship (MASS) systems and port decision-support platforms, enabling safer manoeuvring and operational continuity under rapidly varying environmental conditions. Full article

The unique natural environment and climate of tropical island regions present significant challenges to construction. Under these variable natural conditions and complex construction processes, identifying and analyzing potential risks that could lead to vulnerabilities in construction safety systems and clarifying their transmission pathways remains a pressing issue. To fill this research gap, a GV-IB model for vulnerability analysis of construction safety systems in tropical island building projects (CSSTIBPs) was established. This model constructs a vulnerability analysis index system for tropical island construction safety systems based on the Grey Relational Analysis (GRA) and Vulnerability Scoping Diagram (VSD), considering exposure, sensitivity, and adaptability. By combining the artificial fish swarm algorithm with the K2 algorithm and the EM algorithm, an Improved Bayesian Network (IBN) is constructed to analyze and infer the influencing factors and disaster chains of vulnerability in tropical island construction safety systems. The IBN can effectively overcome the dependence on node order and data gaps in traditional Bayesian Network construction methods. The effectiveness of the model is verified by analyzing Hainan Island, China. The research results show that (a) The IBN stability verification showed an Area Under ROC Curve (AUC) of 0.783 > 0.7, indicating high effectiveness in identifying vulnerability factors. (b) Within the vulnerability measurement nodes of the CSSTIBPs, the influence on the system decreases in the following order is exposure (0.41), sensitivity (0.31), and adaptability (0.03). (c) Emergency response time, safety training, hazard identification time, accident response time, and duration of severe weather are key factors affecting the vulnerability of CSSTIBPs. Full article

Nuclear Power Plant (NPP) site preparation in tropical regions faces significant schedule and cost risks due to rainfall, which are often addressed with inadequate and unspecified contingencies. This study develops an integrated framework to address these issues by converting multi-year daily rainfall data into auditable seasonal risk inputs for project simulations. The methodology involves synthesizing rainfall data from multiple stations with quality weighting, mapping rainfall to Lost Time Hours (LTH) using a double logistic function, and applying time–cost co-sampling analysis in Primavera Risk Analysis. Applied to the Indonesian case study, the framework predicts an increase in P80 duration of 36 days, or 10.17%, and an increase in cost of USD 64,809, or 8.41%. This analysis reveals that the raw rainfall index is only weakly correlated with delays and cost overruns at the project level, because the network structure and monthly usage levels filter out the weather signal; this weak correlation and the systematic time–cost decoupling encourage comprehensive network simulations rather than simply accounting for uniform weather allowances. This methodology has potential applications for site preparation activities and other types of infrastructure. However, validation on external datasets and calibration to local climate and operational contexts remain critical future steps. This framework provides a transparent and replicable approach to converting local climate data into project-specific contingency data, improving schedule reliability and cost control for construction projects in tropical regions. Full article

In recent years, with the growing intensity of extreme weather events, imbalances in energy supply and demand, and frequent regional conflicts, the stability of our energy systems faces increasing challenges. Against this backdrop, the green innovation ecosystem can optimize the energy system’s structure and operational efficiency by promoting multi-actor interaction and multi-element synergy, thereby enhancing its resilience. Accordingly, this study aims to reveal how the green innovation ecosystem drives improvements in energy resilience (ER) through factor configurations and to identify the pathways leading to high-ER outcomes. To address this, this study constructs a research framework of the “core layer–environmental layer–supporting layer” for the green innovation ecosystem, and selects seven conditional variables, namely dual green innovation, multidimensional environmental regulation, green finance, and digital infrastructure. Based on official Chinese statistics, panel data from 30 provinces were compiled, and the dynamic qualitative comparative analysis (QCA) method was used to analyze how multiple factors interacted from 2016 to 2022 to achieve high ER from a spatiotemporal perspective. The results show that: (1) There is no single necessary condition for achieving high ER. (2) Dual green innovation and public participation in environmental regulation play a universal role in achieving high ER. They are combined with green finance, market-based environmental regulation, and digital infrastructure, forming three configuration pathways for achieving high ER. (3) No significant time effect is observed. (4) Pronounced spatial heterogeneity exists. The eastern region focuses on the green finance-enabled pathway, the central region has a high coverage of all three pathways, and the western region has relatively weak overall adaptability. Based on these findings, this study argues that enhancing ER depends on the coordinated allocation of multiple factors, and there is no single optimal pathway. Policymakers should adopt a configurational mindset and select appropriate combinations of elements in light of regional development conditions to enhance ER. Full article

Accurate forecasting of meteorological parameters is essential for the reliable operation and performance optimization of photovoltaic (PV) power plants. Among these parameters, ambient temperature and global horizontal irradiance (GHI) have the most direct impact on PV output. This study investigates the integration of machine-learning-based (ML) weather forecasts into PV energy modeling and quantifies how forecast accuracy propagates into PV generation estimation errors. Three commonly used ML algorithms—Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest (RF)—were developed and compared. Antalya (Turkey), representing a Mediterranean climate zone, was selected as the case study location. High-resolution meteorological data from 2018–2023 were used to train and evaluate the forecasting models for prediction horizons from 1 to 10 days. Model performance was assessed using root mean square error (RMSE) and the coefficient of determination (R²). The results indicate that RF provides the highest accuracy for temperature prediction, while ANN demonstrates superior performance for GHI forecasting. The generated forecasts were incorporated into a PV power output simulation using the PVLib library. The analysis reveals that inaccuracies in GHI forecasts have the largest impact on PV energy estimation, whereas temperature forecast errors contribute significantly less. Overall, the study demonstrates the practical benefits of integrating ML-based meteorological forecasting with PV performance modeling and provides guidance on selecting suitable forecasting techniques for renewable energy system planning and optimization. Full article

The Cuitzeo Groundwater Flow System, located in central Mexico within a volcanic rock region, encompasses two of the largest lakes in the country: Lake Cuitzeo and Lake Pátzcuaro. These lakes are sustained by both surface water and groundwater discharge, playing a critical role in local ecosystems and the surrounding population. Groundwater is particularly important for maintaining the lakes’ existence. However, the behavior of the groundwater flow system in this region has not been previously described. This study compiles historical data from 170 groundwater sites within the system from different years and includes temperature (°C), pH, total dissolved solids (TDS), major ions, and geology in detail. The historical data provide a spatial analysis and initial characterization to study the hydrochemistry of the system, identify recharge and discharge zones, assess water-rock interaction processes, and trace the evolution of groundwater. The results highlight distinct chemical behaviors across the different zones of the study area, with the most notable being ion exchange consistent with the weathering of volcanic silicates and interaction with lacustrine sediments. This study is crucial as it offers valuable insights into the hydrochemistry and water levels of the groundwater flow system and highlights areas where additional data are needed to better understand its dynamics. Full article

Accurate rainfall monitoring is essential for mitigating hydrometeorological disasters and understanding hydrological changes under climate change. This study presents a deep learning-based rainfall estimation framework using multispectral GEO-KOMPSAT-2A (GK2A) satellite imagery. The analysis primarily focuses on daytime observations to take advantage of visible channel information, which provides richer representations of cloud characteristics during daylight conditions. The core model, Model-HSP, is built on the Pix2PixCC architecture and trained with Hybrid Surface Precipitation (HSP) data from weather radar. To further enhance accuracy, an ensemble model (Model-ENS) integrates the outputs of Model-HSP and a radar based Model-CMX, leveraging their complementary strengths for improved generalization, robustness, and stability across rainfall regimes. Performance was evaluated over two periods—a one year period from May 2023 to April 2024 and the August 2023 monsoon season—at 2 km and 4 km spatial resolutions, using RMSE and CC as quantitative metrics. Case analyses confirmed the superior capability of Model-ENS in capturing rainfall distribution, intensity, and temporal evolution across diverse weather conditions. These findings show that deep learning greatly enhances GEO satellite rainfall estimation, enabling real-time, high-resolution monitoring even in radar sparse or limited coverage regions, and offering strong potential for global and regional hydrometeorological and climate research applications. Full article

To mitigate the frequent occurrence of rear-end collisions on urban expressways under rainy weather conditions, firstly, accident risk levels were classified using traffic conflict indicators. Secondly, three machine learning models were employed to predict the accident severity across different scenarios. Furthermore, key influencing factors of rear-end collisions were identified and analyzed based on SHAP values. Case studies were conducted by simulating vehicle trajectory data under light, moderate, and heavy rain scenarios, using an open urban expressway dataset and car-following parameters for rainy conditions. Next, the Modified Time-to-Collision (MTTC) metric was calculated. Risk thresholds for low-, medium-, and high-risk levels were established for each rainfall category using percentile-based cumulative distribution analysis. Finally, real-time risk prediction under the three rainfall scenarios was conducted using XGBoost, LightGBM, and Random Forest models. The model performances were evaluated in terms of accuracy, recall, precision, and AUC. Overall, the study finds that the LightGBM model achieves the highest predictive capability, with AUC values exceeding 0.78 under all weather conditions. Moreover, the study concludes that factors ranked by SHAP values reveal that the minimum distance has the greatest influence in light rain scenarios. As rainfall intensity increases, the influences of minimum headway time and average vehicle speed are found to grow, highlighting an interaction pattern characterized by “speed-distance-flow” coupling. Full article

Crude oil contamination occurs frequently in soil; thus, on-site measurement of oil content is critical for controlling petroleum contamination, but it is challenging. Conventional chemical analysis requires complicated sample pretreatment and high-cost facilities, requiring on-site and cost-effective approaches. This study innovated a whole-cell bioreporter assay by combining Acinetobacter-hosted n-alkane and genotoxicity bioreporters to directly and simultaneously evaluate the contamination level and genotoxicities of crude oil in contaminated soils. Ultrasound pretreatment was employed to accelerate the measurement process, and the first-order release kinetic model was used to calculate crude oil content in an easy operation. The detection limit of the bioreporters was satisfactory at 0.1 mg/L, and the quantification range was 0.1–10 mg/L. The developed bioreporter assay effectively assessed the bioavailability and toxicity of crude oil in real contaminated soils and recognized distinct toxicities after soil weathering. Our findings highlight the feasibility of using the whole-cell bioreporter assay to evaluate the bioavailability and toxicity of crude oil, offering supporting data for the selection of remediation strategies. Full article

This exploratory study addresses the problem of limited research on quality assessments of newly emerging multi-use market formats that function as social hubs and their management as privately managed public spaces. Using Āgenskalns Market, a revitalised multi-use market hall in Riga, as a case study, the authors apply an assessment framework based on Yuri Impens’ study on covered food halls, incorporating quality criteria from Vikas Mehta’s Public Space Index and the UN-Habitat’s Site-Specific assessment methodology. Leclercq et al.’s works on privatisation of public spaces are integrated in the analysis of “publicness”. This framework evaluates user and observer perceptions across four dimensions: environmental quality and comfort, accessibility and amenities, social experience, and market offer. Data comprised an online survey of 318 respondents and 21 structured observations conducted during summer in 2024 and 2025. The preliminary results suggest users perceive the market as a well-maintained, aesthetically pleasing, accessible space, while identifying room for improvement regarding restroom facilities, indoor thermal regulation, noise mitigation, outdoor weather protection and parking arrangements. As for meaningful use and promoting sociability, findings highlight that flexible seating areas that allow high degrees of temporary personalisation and appropriation, alongside tailored programming and diverse activities beyond retail and dining, play an important role in attracting and retaining diverse audiences. While pricing concerns were noted for specific product groups, exclusionary effects appear to be counterbalanced by openness and inclusivity of cultural programmes and free events. The findings contribute to broader urban scholarship discussions calling for new typologies that better capture the changing character of public space use. This research suggests that private-public partnerships involving multiple stakeholders can enhance “publicness” by promoting inclusivity and social life through accessible infrastructure, diverse activities and free events, as well as enabling opportunities for temporary appropriation by users. Full article

The proliferation of plastic waste across natural ecosystems has created a global environmental and public health crisis. Monitoring plastic litter using remote sensing remains challenging due to the significant variability in terrain, lighting, and weather conditions. Although earlier approaches, including classical supervised machine learning techniques such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), applied to hyperspectral and multispectral data have shown promise in controlled settings, they often may face challenges in generalizing across diverse environmental conditions encountered in real-world scenarios. In this work, we present a deep learning framework for pixel-wise segmentation of plastic waste in short-wave infrared (900–1700 nm) hyperspectral imagery acquired from an Unmanned Aerial Vehicle (UAV). Our architecture integrates attention gates and residual connections within a U-Net backbone to enhance contextual modeling and spatial-spectral consistency. We introduce a multi-flight dataset spanning over 9 UAV missions across varied environmental settings, consisting of hyperspectral cubes with centimeter-level resolution. Using a leave-one-out cross-validation protocol, our model achieves test accuracy of up to 96.8% (average 90.5%) and a 91.1% F1 score, demonstrating robust generalization to unseen data collected in different environments. Compared to classical models, the deep network captures richer semantic representations, particularly under challenging conditions. This work offers a scalable and deployable tool for automated plastic waste monitoring and represents a significant advancement in remote environmental sensing. Full article