Search Results (65,519)

Sewer systems are essential for sustainable infrastructure management, influencing environmental, social, and economic aspects. However, sewer network capacity is under significant pressure, with many systems overwhelmed by challenges such as climate change, ageing infrastructure, and increasing inflow and infiltration, particularly through groundwater infiltration (GWI). Current research in this area has primarily focused on general sewer performance, with limited attention to high-resolution, spatially explicit assessments of sewer exposure to GWI, highlighting a critical knowledge gap. This study responds to this gap by developing a high-resolution GWI assessment. This is achieved by integrating fuzzy-analytical hierarchy process (AHP) with geographic information systems (GISs) and machine learning (ML) to generate GWI probability maps across the Dawlish region, southwest United Kingdom, complemented by sensitivity analysis to identify the key drivers of sewer network vulnerability. To this end, 16 hydrological–hydrogeological thematic layers were incorporated: elevation, slope, topographic wetness index, rock, alluvium, soil, land cover, made ground, fault proximity, fault length, mass movement, river proximity, flood potential, drainage order, groundwater depth (GWD), and precipitation. A GWI probability index, ranging from 0 to 1, was developed for each 1 m × 1 m area per season. The model domain was then classified into high-, intermediate-, and low-GWI-risk zones using K-means clustering. A consistency ratio of 0.02 validated the AHP approach for pairwise comparisons, while locations of storm overflow (SO) discharges and model comparisons verified the final outputs. SOs predominantly coincided with areas of high GWI probability and high-risk zones. Comparison of AHP-weighted GIS output clustered via K-means with direct K-means clustering of AHP-weighted layers yielded a Kappa value of 0.70, with an 81.44% classification match. Sensitivity analysis identified five key factors influencing GWI scores: GWD, river proximity, flood potential, rock, and alluvium. The findings underscore that proxy-based geospatial and machine learning approaches offer an effective and scalable method for mapping sewer network exposure to GWI. By enabling high-resolution risk assessment, the proposed framework contributes a novel proxy and machine-learning-based screening tool for the management of smart cities. This supports predictive maintenance, optimised infrastructure investment, and proactive management of GWI in sewer networks, thereby reducing costs, mitigating environmental impacts, and protecting public health. In this way, the method contributes not only to improved sewer system performance but also to advancing the sustainability and resilience goals of smart cities. Full article

Urban heat island conditions increase heat exposure and constrain safe outdoor activities. Urban forests can mitigate thermal loads; however, stand morphology can produce divergent microclimates. We aimed to quantify how stand type (open vs. closed), season (spring, summer, fall), and activity intensity (MET 1.0–6.0) jointly modulate thermal comfort and to identify season-specific optimal MET levels in an urban forest in Daejeon, Republic of Korea. We combined site-specific 3D canopy modeling with hourly Predicted Mean Vote (PMV) simulations driven by AMOS tower data (2023–2024). Comfort was defined as |PMV| ≤ 0.5. Analyses included seasonal means, Cliff’s delta, and generalized estimating equation logistic models to estimate the SITE × SEASON × MET interactions and predict comfort probabilities. Across most seasons and MET levels, C1 was more comfortable than C2. However, at MET 1.0 in summer, the pattern was reversed, which may reflect the canopy shading and associated decreases in mean radiant temperature (MRT) of C2. Comfort peaked at MET 2.0–3.0 and declined sharply at ≥4.5 MET. The three-way SITE × SEASON × MET interaction was significant (p < 0.001). The season-specific optimal MET values under our boundary conditions were 3.0 (spring), 2.0–2.5 (summer), and 3.0 (fall). These simulation-based PMV-centered findings represent model-informed tendencies. Nevertheless, they support actionable guidance: prioritize high-closure stands for low-intensity summer use, leverage open stands for low-to-moderate activities in spring and fall, and avoid high-intensity programs during warm periods. These results inform the programming and design of urban-forest healing and recreation by matching stand type and activity intensity to season to maximize comfortable hours. Full article

Urbanization and traffic congestion caused by the surge in car ownership have exacerbated energy consumption and carbon emissions, and dynamic traffic flow prediction and energy-saving route planning have become the key to solving this problem. Dynamic traffic flow prediction accurately captures the spatio-temporal changes of traffic flow through advanced algorithms and models, providing prospective information for traffic management and travel decision-making. Energy-saving route planning optimizes travel routes based on prediction results, reduces the time vehicles spend on congested road sections, thereby reducing fuel consumption and exhaust emissions. However, there are still many shortcomings in the current relevant research, and the existing research is mostly isolated and applies a single model, and there is a lack of systematic comparison of the adaptability, generalization ability and fusion potential of different models in various scenarios, and the advantages of heterogeneous graph neural networks in integrating multi-source heterogeneous data in traffic have not been brought into play. This paper systematically reviews the relevant global studies from 2020 to 2025, focuses on the integration path of dynamic traffic flow prediction methods and energy-saving route planning, and reveals the advantages of LSTM, graph neural network and other models in capturing spatiotemporal features by combing the application of statistical models, machine learning, deep learning and mixed methods in traffic forecasting, and comparing their performance with RMSE, MAPE and other indicators, and points out that the potential of heterogeneous graph neural networks in multi-source heterogeneous data integration has not been fully explored. Aiming at the problem of disconnection between traffic prediction and path planning, an integrated framework is constructed, and the real-time prediction results are integrated into path algorithms such as A* and Dijkstra through multi-objective cost functions to balance distance, time and energy consumption optimization. Finally, the challenges of data quality, algorithm efficiency, and multimodal adaptation are analyzed, and the development direction of standardized evaluation platform and open source toolkit is proposed, providing theoretical support and practical path for the sustainable development of intelligent transportation systems. Full article

This study investigates the severity of injuries sustained by over seven million participants involved in road traffic incidents in Poland between 2015 and 2024, with a view to supporting sustainable mobility and the United Nations Sustainable Development Goals. Road safety is a crucial dimension of sustainable development, directly linked to public health, urban liveability, and the socio-economic costs of transportation systems. Using a harmonised participant-level dataset, this research identifies key demographic, behavioural, and environmental factors associated with injury outcomes. A novel five-level injury severity variable was developed by integrating inconsistent records on fatalities and injuries. Descriptive analyses revealed clear seasonal and weekly patterns, as well as substantial differences by participant type and driving licence status. Pedestrians and passengers faced the highest risk, with fatality rates more than five times higher than those of drivers. An XGBoost classifier was trained to predict injury severity, and SHAP analysis was applied to interpret the model’s outputs at the feature level. Participant role emerged as the most important predictor, followed by driving licence status, vehicle type, lighting conditions, and road geometry. These findings provide actionable insights for sustainable road safety interventions, including stronger protection for pedestrians and passengers, stricter enforcement against unlicensed driving, and infrastructural improvements such as better lighting and safer road design. By combining machine learning with interpretability tools, this study offers an analytical framework that can inform evidence-based policies aimed at reducing crash-related harm and advancing sustainable transport development. Full article

Environmental, Social, and Governance (ESG) ratings are widely used for investment and regulatory decision-making, yet they often suffer from symbolic compliance and information asymmetry. To address these limitations, this study introduces a hybrid ESG risk assessment model that integrates court ruling data with traditional ESG ratings to detect latent sustainability risks. Using a dataset of 213 ESG-related U.S. court rulings from January 2023 to May 2025, we apply natural language processing (TF-IDF, Legal-BERT) and explainable AI (SHAP) techniques to extract structured features from legal texts. We construct and compare classification models—including Random Forest, XGBoost, and a Legal-BERT-based hybrid model—to predict firms’ litigation risk. The hybrid model significantly outperforms the baseline ESG-only model in all key metrics: F1-score (0.81), precision (0.79), recall (0.84), and AUC-ROC (0.87). SHAP analysis reveals that legal features such as regulatory sanctions and governance violations are the most influential predictors. This study demonstrates the empirical value of integrating adjudicated legal evidence into ESG modeling and offers a transparent, verifiable framework to enhance ESG risk evaluation and reduce information asymmetry in sustainability assessments. Full article

Exploiting inherent symmetries in data and models is crucial for accurate renewable energy forecasting. To address limited accuracy improvements under complex temporal dependencies, this study proposes a hybrid Bi-xLSTM-Informer model that incorporates temporal symmetry via bidirectional processing of time-flipped sequences. First, key features are screened using the Boruta algorithm, followed by PCA dimensionality reduction to construct an optimal feature subset with orthogonal transformation properties. Second, a Bi-xLSTM-Informer hybrid forecasting model is constructed. In the xLSTM model, the mLSTM is modified into a bidirectional network structure to capture short-term fluctuation patterns via forward and time-reversed propagation; Informer then analyzes global dependencies via ProbSparse attention. Validated on data from the photovoltaic (PV) Power Plant AI Competition, the experimental results demonstrate that the Bi-xLSTM-Informer model achieves the best prediction performance and the lowest error among all compared models, with an R² of 98.76% and an RMSE of 0.3776. This work proves that explicitly modeling temporal symmetry and feature orthogonality significantly enhances PV forecasting, providing an effective solution for renewable energy utilization. Full article

A learning management system (LMS) plays a crucial role in supporting students’ educational activities by centralized platforms for course delivery, communication, and student support. Recently, many universities have integrated chatbots into their LMS to assist students with various inquiries and tasks. However, existing chatbots often necessitate human interventions to manually respond to complex queries, resulting in limited scalability and efficiency. In this paper, we present a memory-augmented large language model (LLM) framework that enhances the reasoning and contextual continuity of LMS-based chatbots. The proposed framework first embeds user queries and retrieves semantically relevant entries from various LMS resources, including instructional documents and academic frequently asked questions. Retrieved entries are then filtered through a two-stage confidence filtering process that combines similarity thresholds and LLM-based semantic validation. Validated information, along with user queries, is processed by LLM for response generation. To maintain coherence in multi-turn interactions, the chatbot incorporates short-term, long-term, and temporal event memories, which track conversational flow and personalize responses based on user-specific information, such as recent activity history and individual preferences. To evaluate response quality, we employed a multi-layered evaluation strategy combining BERTScore-based quantitative measurement, an LLM-as-a-Judge approach for automated semantic assessment, and a user study under multi-turn scenarios. The evaluation results consistently confirm that the proposed framework improves the consistency, clarity, and usefulness of the responses. These findings highlight the potential of memory-augmented LLMs for scalable and intelligent learning support within university environments. Full article

Background/Objectives: Adolescence is a sensitive developmental window shaped by both vulnerabilities and adaptive potential. From an evolutionary standpoint, mental health difficulties in this period may represent functional responses to environmental stressors rather than mere dysfunctions. Despite increasing interest, integrative models capturing the dynamic interplay of risk and protective factors in adolescent mental health remain limited. This study presents a holistic, multi-level framework grounded in ecological and evolutionary theories to improve understanding and intervention strategies. Methods: A two-round Delphi method was used to develop and validate the framework. Twelve experts in adolescent mental health evaluated a preliminary draft derived from the literature. In Round 1, 12 items were rated across five criteria (YES/NO format), with feedback provided when consensus thresholds were not met. Revisions were made using consensus index scores. In Round 2, the revised draft was assessed across eight broader dimensions. A consensus threshold of 0.75 was used in both rounds. Results: Twelve out of thirteen experts (92%) agreed to join the panel. Round 1 item scores ranged from 0.72 to 0.85, with an average consensus index of 0.78. In Round 2, ratings improved significantly, ranging from 0.82 to 1.0, with an average of 0.95. The Steering Committee incorporated expert feedback by refining the structure, deepening content, updating sources, and clarifying key components. Conclusions: The final framework allows for the clustering of indicators across macro-, medium-, and micro-level domains. It offers a robust foundation for future research and the development of targeted, evolutionarily informed mental health interventions for adolescents. Full article

Meteorological disasters are significant factors that impact agricultural production. Given the vast volume of online agrometeorological disaster information, accurately and automatically extracting essential details—such as the time, location, and extent of damage—is crucial for understanding disaster mechanisms and evolution, as well as for enhancing disaster prevention capabilities. This paper constructs a comprehensive dataset of agrometeorological disasters in China, providing a robust data foundation and strong support for event extraction tasks. Additionally, we propose a novel model named character and word embedding fusion-based GCN network (CWEF-GCN). This integration of character- and word-level information enhances the model’s ability to better understand and represent text, effectively addressing the challenges of multi-events and argument overlaps in the event extraction process. The experimental results on the agrometeorological disaster dataset indicate that the F1 score of the proposed model is 81.66% for trigger classification and 63.31% for argument classification. Following the extraction of batch agricultural meteorological disaster events, this study analyzes the triggering mechanisms, damage patterns, and disaster response strategies across various disaster types using the extracted event. The findings offer actionable decision-making support for research on agricultural disaster prevention and mitigation. Full article

Detecting marine oil spills is vital for protecting the marine environment, ensuring maritime traffic safety, supporting marine development, and enabling effective emergency response. The dual-polarimetric (DP) synthetic aperture radar (SAR) system represents an evolution from single to full polarization (FP), which has become an essential tool for oil spill detection with the growing availability of open-source and shared datasets. Recent research has focused on enhancing DP information structures to better exploit this data. This study introduces improved DP models’ structure with modified the scattering vector coefficients to ensure consistency with the corresponding components of the FP system, enabling comprehensive comparison and analysis with traditional DP structure, includes theoretical and quantitative evaluations of simulated data from FP system, as well as validation using real DP scenarios. The results showed the following: (1) The polarimetric entropy H_L obtained through the improved DP scattering matrix C_L can achieve higher information consistency results closely aligns with FP system and better performance, compared to the typical two DP scattering structures. (2) For multiple polarimetric features from DP scattering matrix (both traditional feature and combination feature), the improved DP scattering matrix C_L can be used for oil spill extraction effectively with prominent results. (3) For oil spill extraction, the polarimetric features-based C_L tend to have relatively high contribution, especially the H_A feature combination, leading to substantial gains in improved classification performance. This approach not only enriches the structural information of the DP system under VV–VH mode but also improves oil spill identification by integrating multi-structured DP features. Furthermore, it offers a practical alternative when FP data are unavailable. Full article

Social networks generate vast amounts of data that can reveal patterns of human behaviour, social attachment, and mental states. This paper explores advanced machine learning techniques to detect and model such patterns, focusing on community structures, influential users, and information diffusion pathways. To address the scale, noise, and heterogeneity of social data, we leverage recent advances in graph theory, natural language processing, and anomaly detection. Our framework combines clustering for community detection, sentiment analysis for emotional state inference, and centrality metrics for influence estimation, while integrating multimodal data—including textual and visual content—for richer behavioural insights. Experimental results demonstrate that the proposed approach effectively extracts actionable knowledge, supporting mental well-being and strengthening digital social ties. Furthermore, we emphasise the role of privacy-preserving methods, such as federated learning, to ensure ethical analysis. These findings lay the groundwork for responsible and effective applications of machine learning in social network analysis. Full article

Long COVID, characterized by persistent symptoms following acute SARS-CoV-2 infection, has emerged as a significant public health challenge with wide-ranging clinical and socioeconomic implications. Developing an effective risk assessment strategy is essential for the early identification and management of individuals susceptible to prolonged symptoms. This study uses a quantitative approach to characterize the dose–response relationships between spike protein concentrations and effects, including Long COVID symptom numbers and the release of proinflammatory mediators. A mathematical model is also developed to describe the time-dependent change in spike protein concentrations post diagnosis in twelve Long COVID patients with a cluster analysis. Based on the spike protein concentration–Long COVID symptom numbers relationship, we estimated a maximum symptom number (~20) that can be used to reflect a persistent predictor. We found that among the crucial biomarkers associated with Long COVID proinflammatory mediator, CXCL8 has the lowest 50% effective dose (0.01 μg mL⁻¹), followed by IL-6 (0.39), IL-1β (0.46), and TNF-α (0.56). This work provides a comprehensive risk assessment strategy with dose–response tools and mathematical modeling developed to estimate potential spike protein concentration. Our study suggests persistent Long COVID guidelines for personalized care strategies and could inform public health policies to support early interventions that reduce long-term disability and healthcare burdens with possible other post-infection syndromes. Full article

As a high-frequency and essential type of special electromechanical equipment, a vertical elevator has a significant societal implication for their safe operation. The load-weighing module, serving as the core component for overload warning, is susceptible to precision degradation due to the nonlinear deformation of rubber buffers installed at the base of the elevator car. This deformation arises from the coupled effects of environmental factors such as temperature, humidity, and material aging, leading to potential safety risks including missed overload alarms and false empty status detections. To address the issue of accuracy deterioration in elevator load-weighing systems, this study proposes an online self-calibration method based on multimodal information fusion. A reference detection model is first constructed to map the relationship between applied load and the corresponding relative compression of the rubber buffers. Subsequently, displacement data from a draw-wire sensor are integrated with target detection model outputs, enabling real-time extraction of dynamic rubber buffers’ deformation characteristics under empty conditions. Based on the above, a displacement-based compensation term is derived to enhance the accuracy of load estimation. This is further supported by a dynamic error compensation mechanism and an online computation framework, allowing the system to self-calibrate without manual intervention. The proposed approach eliminates the dependency on manual tuning inherent in traditional methods and forms a highly robust solution for load monitoring. Field experiments demonstrate the effectiveness of the proposed method and the stability of the prototype system. The results confirm that the synergistic integration of multimodal perception and adaptive calibration technologies effectively resolves the challenge of load-weighing precision degradation under complex operating conditions, offering a novel technical paradigm for elevator safety monitoring. Full article

In response to problems such as large target scale variations, strong background noise, and blurred features leading by low contrast in infrared target detection in near space environments, this paper proposes an efficient detection model, YOLO-MARS, which is based on YOLOv8. The model introduces a Space-to-Depth (SPD) convolution module into the backbone section, which retains the detailed features of smaller targets by downsampling operations without information loss, alleviating the loss of the target feature caused by traditional downsampling. The Grouped Multi-Head Self-Attention (GMHSA) module is added after the backbone’s SPPF module to improve cross-scale global modeling capabilities for target area feature responses while suppressing complex thermal noise background interference. In addition, a Light Adaptive Spatial Feature Fusion (LASFF) detector head is designed to mitigate the scale sensitivity issue of infrared targets (especially smaller targets) in the feature pyramid. It uses a shared weighting mechanism to achieve adaptive fusion of multi-scale features, reducing computational complexity while improving target localization and classification accuracy. To address the extreme scarcity of near space data, we integrated 284 near space images with the HIT-UAV dataset through physical equivalence analysis (atmospheric transmittance, contrast, and signal-to-noise ratio) to construct the NS-HIT dataset. The experimental results show that ${mAP}_{@0.5}$ increases by 5.4% and the number of parameters only increase 10% using YOLO-MARS compared to YOLOv8. YOLO-MARS improves the accuracy of detection significantly while considering the requirements of model complexity, which provides an efficient and reliable solution for applications in near space infrared target detection. Full article

Data-driven models for complex thermal systems face two main challenges: a heavy dependence on high-quality training datasets and a “black-box” nature that makes it difficult to align model predictions with fundamental physical laws. To address these issues, this study introduces a novel physics-informed variational autoencoder (PI-VAE) framework for modeling thermal systems. The framework formalizes the mechanistic relationships among state parameters and establishes mathematical formulations for multi-level physical constraints. These constraints are integrated into the training loss function of the VAE as physical inconsistency losses, steering the model to comply with the system’s underlying physical principles. Additionally, a synthetic sample-generation strategy using latent variable sampling is introduced to improve the representation of physical constraints. The effectiveness of the proposed framework is validated through numerical simulations and an engineering case study. Simulation results indicate that as the complexity of embedded physical constraints increases, the test accuracy of the PI-VAE progressively improves, with R² increasing from 0.902 (standard VAE) to 0.976. In modeling a high-pressure feedwater heater system in a thermal power plant, the PI-VAE model achieves high prediction accuracy while maintaining physical consistency under previously unseen operating conditions, thereby demonstrating superior generalization capability and interpretability. Full article