Search Results (922)

Accurate prediction of bridge deterioration is essential for optimizing inspection schedules, prioritizing maintenance activities, and ensuring infrastructure safety. This study developed machine learning-based predictive models to estimate the deterioration states of bridge decks, superstructures, and substructures using a comprehensive dataset from the Colorado National Highway System spanning 2014 to 2024. Structural, operational, and environmental parameters including freeze–thaw cycles, precipitation, condensation risk, and extreme temperatures were incorporated to capture both design-driven and climate-driven deterioration mechanisms. Decision Tree, Random Forest, and Gradient Boosting classifiers were trained and evaluated using Balanced Accuracy, Matthews Correlation Coefficient, Cohen’s Kappa, and macro-averaged F1-scores, with class imbalance addressed via SMOTETomek resampling. The Gradient Boosting classifier achieved the highest predictive performance, with balanced accuracy exceeding 97% across all components. Feature importance analysis revealed that sufficiency rating, year of construction, and environmental stressors were among the most influential predictors. Incorporating environmental variables improved predictive accuracy by up to 4.5 percentage points, underscoring their critical role in deterioration modeling. These findings demonstrate that integrating environmental factors into machine learning frameworks enhances the reliability of deterioration forecasts and supports the development of climate-aware asset management strategies, enabling transportation agencies to proactively plan maintenance interventions and improve infrastructure resilience. Full article

Policies rarely act on simple circles around project sites. We develop a policy-semantics-to-geometry workflow that converts clause-level rules in ordinances into auditable Policy Spatial Footprints (PSFs) with explicit boundaries, timing markers, and intensity tiers, and we measure exposure in network time on road–rail graphs. Using 1.10 million arm’s-length parcel transactions from five Yangtze River Delta cities (2012–2024) and a catalog of 64 policies across regulatory, transport, and industrial/functional families, we estimate dynamic capitalization under staggered roll-outs while separating direct footprint effects from adjacency diffusion. Direct exposures are associated with policy-relevant uplifts that build over several years and then stabilize; spillovers attenuate within a few minutes of network travel time. Effects are systematically larger in thicker markets and where pre-policy regulatory headroom is greater. The PSF framework yields estimator-consistent maps with provenance and uncertainty tiers, providing a transparent basis for land-value-capture scheduling and equity-aware carve-outs. Full article

Intelligent connected vehicles (ICVs) face challenges in handling intensive onboard computational tasks due to limited computing capacity. Vehicular edge computing networks (VECNs) offer a promising solution by enabling ICVs to offload tasks to mobile edge computing (MEC), alleviating computational load. As transportation systems are dynamic, vehicular tasks and MEC capacities vary over time, making efficient task offloading and resource allocation crucial. We explored a vehicle–road collaborative edge computing network and formulated the task offloading scheduling and resource allocation problem to minimize the sum of time and energy costs. To address the mixed nature of discrete and continuous decision variables and reduce computational complexity, we propose a hybrid hierarchical deep reinforcement learning (HHDRL) algorithm, structured in two layers. The upper layer of HHDRL enhances the double deep Q-network (DDQN) with a self-attention mechanism to improve feature correlation learning and generates discrete actions (communication decisions), while the lower layer employs deep deterministic policy gradient (DDPG) to produce continuous actions (power control, task offloading, and resource allocation decision). This hybrid design enables efficient decomposition of complex action spaces and improves adaptability in dynamic environments. Results from numerical simulations reveal that HHDRL achieves a significant reduction in total computational cost relative to current benchmark algorithms. Furthermore, the robustness of HHDRL to varying environmental conditions was confirmed by uniformly designing random numbers within a specified range for certain simulation parameters. Full article

Railway hazardous chemical transportation, a high-risk activity that endangers personnel, infrastructure, and ecosystems, directly undermines the sustainability of the transportation system and regional development. Traditional risk management algorithms, which rely on empirical rules, result in sluggish emergency responses (with an average response time of 4.8 h), further exacerbating the environmental and economic losses caused by accidents. The standalone DBSCAN algorithm only supports static spatial clustering (with unoptimized hyperparameters); it lacks probabilistic reasoning capabilities for dynamic scenarios and thus fails to support sustainable resource allocation. To address this gap, this study develops a DBSCAN–Bayesian network fusion model that identifies risk hotspots via static spatial clustering—with ε optimized by the K-distance method and MinPts determined through cross-validation—for targeted prevention; meanwhile, the Bayesian network quantifies the dynamic relationships among “hazardous chemical properties-accident scenarios-material requirements” and integrates real-time transportation and environmental data to form a “risk positioning-demand prediction-intelligent allocation” closed loop. Experimental results show that the fusion algorithm outperforms comparative methods in sustainability-linked dimensions: ① Emergency response time is shortened to 2.3 h (a 52.1% improvement), with a 92% compliance rate in high-risk areas (e.g., water sources), thereby reducing ecological damage. ② The material satisfaction rate reaches 92.3% (a 17.6% improvement), and the neutralizer matching accuracy for corrosive leaks is increased by 26 percentage points, which cuts down resource waste and lowers carbon footprints. ③ The coverage rate of high-risk areas reaches 95.6% (a 16.4% improvement over the standalone DBSCAN algorithm), with a 27.5% reduction in dispatch costs and a drop in resource waste from 38% to 11%. This model achieves a leap from static to dynamic decision-making, providing a data-driven paradigm for the sustainable emergency management of railway hazardous chemicals. Its “spatial clustering + probabilistic reasoning” path holds universal value for risk control in complex systems, further boosting the sustainability of infrastructure. Full article

Agent-based models (ABMs) in transport represent a paradigm shift from traditional aggregate and equilibrium-based approaches. By modeling individual behaviors of a heterogeneous population, an ABM offers a more realistic representation of urban phenomena and extends sensitivity to different policy interventions. Despite this, ABM implementation faces several challenges such as limited reproducibility, uneven global implementation, and high technical and financial costs, particularly relevant in the Global South. The proposed framework addresses these gaps by implementing a modular, transparent, publicly shared data-driven approach, reducing hierarchies and relationships definitions while ensuring reproducibility. Utilizing nationally available data to generate a synthetic population, activity plans, multimodal network and agent simulations in MATSim, the framework was applied in the Metropolitan Area of Fortaleza, a region with approximately 4 million people in Brazil. Despite inherent data limitations characteristic of developing contexts, the framework demonstrated performance compatible with strategic planning applications. Traffic assignment validation showed a mean absolute error of 301 vehicles during morning peak hours and 423 vehicles for the 24 h period, which are acceptable for scenario-based policy analysis. Beyond the potential to democratize access to robust urban planning models in similar data-constrained scenarios worldwide, this study presents pathways to foster national dialogue toward improved data collection practices for disaggregated transport model implementation. Full article

The mining industry faces the critical challenge of balancing economic profitability with environmental responsibility. Traditional mine planning models often prioritise financial gains, particularly Net Present Value (NPV), while placing less emphasis on environmental impacts, such as carbon emissions. This research presents a comprehensive multi-objective optimisation model for production scheduling in sublevel stoping operations. The model simultaneously aims to maximise NPV and minimise carbon emissions, providing a more sustainable framework for decision-making. The carbon emission objective comprehensively accounts for energy consumption across all key mining activities, including drilling, blasting, ventilation, transportation, crushing, and backfilling, using a “top-down” accounting method. The multi-objective problem is solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), which generates a set of Pareto-optimal solutions representing the trade-off between the two conflicting goals. The model is applied to a conceptual copper deposit with 200 stopes. The results demonstrate a clear trade-off: schedules with higher NPV inevitably lead to higher carbon emissions, and vice versa. For instance, one solution yields a high NPV of $312.94 million but with 23,602 tonnes of CO₂ emissions. In contrast, another, more environmentally friendly solution reduces emissions by 26.5% to 18,647 tonnes, resulting in only a 1.21% reduction in NPV. This research concludes that integrating environmental objectives into mine planning is not only feasible but essential for promoting sustainable mining practices, offering a practical tool for operators to make informed, balanced decisions. Full article

As intelligent transportation systems continue to advance, on-board surveillance video has become essential for train safety and intelligent scheduling. However, high-resolution video transmission faces bandwidth limitations, and existing deep learning-based super-resolution models find it difficult to meet real-time requirements due to high computational complexity. To address this, this paper proposes an “edge–end” collaborative multi-terminal task inference framework, which improves inference speed by integrating resources of in-vehicle end devices and edge servers. The framework establishes a real-time-priority mathematical model, uses game theory to solve the problem of minimizing multi-terminal task inference latency, and proposes a multi-terminal task model partitioning strategy and an adaptive adjustment mechanism. It can dynamically partition the model according to device performance and network status, prioritizing real-time performance and minimizing the maximum inference delay. Experimental results show that the dynamic model partitioning mechanism can adaptively determine the optimal partition point, effectively reducing the inference delay of each end device in high-speed mobile and bandwidth-constrained scenarios and providing high-quality video data support for safety monitoring and intelligent analysis. Full article

The operation of modern power networks is increasingly exposed to overlapping climate extremes and volatile system conditions, making it essential to adopt scheduling approaches that are resilient as well as economical. In this study, a two-stage stochastic formulation is advanced, where indicators of system adaptability are embedded directly into the optimization process. The objective integrates standard operating expenses—generation, reserve allocation, imports, responsive demand, and fuel resources—with a Conditional Value-at-Risk component that reflects exposure to rare but damaging contingencies, such as extreme heat, severe cold, drought-related hydro scarcity, solar output suppression from wildfire smoke, and supply chain interruptions. Key adaptability dimensions, including storage cycling depth, activation speed of demand response, and resource ramping behavior, are modeled through nonlinear operational constraints. A stylized test system of 30 interconnected areas with a 46 GW demand peak is employed, with more than 2000 climate-informed scenarios compressed to 240 using distribution-preserving reduction techniques. The results indicate that incorporating risk-sensitive policies reduces expected unserved demand by more than 80% during compound disruptions, while the increase in cost remains within 12–15% of baseline planning. Pronounced spatiotemporal differences emerge: evening reserve margins fall below 6% without adaptability provisions, yet risk-adjusted scheduling sustains 10–12% margins. Transmission utilization curves further show that CVaR-based dispatch prevents extreme flows, though modest renewable curtailment arises in outer zones. Moreover, adaptability provisions promote shallower storage cycles, maintain an emergency reserve of 2–3 GWh, and accelerate the mobilization of demand-side response by over 25 min in high-stress cases. These findings confirm that combining stochastic uncertainty modeling with explicit adaptability metrics yields measurable gains in reliability, providing a structured direction for resilient system design under escalating multi-hazard risks. Full article

The Vehicular Internet of Things (V-IoT) has emerged as a cornerstone of next-generation intelligent transportation systems (ITSs), enabling applications ranging from safety-critical collision avoidance and cooperative awareness to infotainment and fleet management. These heterogeneous services impose stringent quality-of-service (QoS) demands for latency, reliability, and fairness while competing for limited and dynamically varying spectrum resources. Conventional schedulers, such as round-robin or static priority queues, lack adaptability, whereas deep reinforcement learning (DRL) solutions, though powerful, remain computationally intensive and unsuitable for real-time roadside unit (RSU) deployment. This paper proposes a lightweight and interpretable reinforcement learning (RL)-based spectrum management framework for Vehicular Internet of Things (V-IoT) networks. Two enhanced Q-Learning variants are introduced: a Value-Prioritized Action Double Q-Learning with Constraints (VPADQ-C) algorithm that enforces reliability and blocking constraints through a Constrained Markov Decision Process (CMDP) with online primal–dual optimization, and a contextual Q-Learning with Upper Confidence Bound (Q-UCB) method that integrates uncertainty-aware exploration and a Success-Rate Prior (SRP) to accelerate convergence. A Risk-Aware Heuristic baseline is also designed as a transparent, low-complexity benchmark to illustrate the interpretability–performance trade-off between rule-based and learning-driven approaches. A comprehensive simulation framework incorporating heterogeneous traffic classes, physical-layer fading, and energy-consumption dynamics is developed to evaluate throughput, delay, blocking probability, fairness, and energy efficiency. The results demonstrate that the proposed methods consistently outperform conventional Q-Learning and Double Q-Learning methods. VPADQ-C achieves the highest energy efficiency (≈$8.425\times {10}^7$ bits/J) and reduces interruption probability by over $60\%$, while Q-UCB achieves the fastest convergence (within ≈190 episodes), lowest blocking probability (≈0.0135), and lowest mean delay (≈0.351 ms). Both schemes maintain fairness near $0.364$, preserve throughput around 28 Mbps, and exhibit sublinear training-time scaling with $\mathcal{O}\left(1\right)$ per-update complexity and $\mathcal{O}\left(N^2\right)$ overall runtime growth. Scalability analysis confirms that the proposed frameworks sustain URLLC-grade latency (<0.2 ms) and reliability under dense vehicular loads, validating their suitability for real-time, large-scale V-IoT deployments. Full article

This case study tackles a real-world problem of a transportation company that is modeled as a scheduling optimization problem. The main goal of the considered problem is to schedule the maximum number of jobs that must be performed by vehicles over a specific planning horizon in order to minimize the total operational costs. Here, each customer request corresponds to a job composed of multiple operations, such as loading, unloading, and mandatory jobs, each associated with a specific location and time window. Once a job is allocated to a vehicle, all its operations must be executed by that same vehicle within their designated time constraints. Due to the imposed limitations, not every job can feasibly be scheduled. To address this challenge, two distinct methodologies are proposed. The first, a Holistic approach, solves the entire problem formulation using a black-box optimizer, serving as a comprehensive benchmark. The second, a Divide-and-Conquer approach, combines a heuristic greedy algorithm with a binary linear programming, decomposing the problem into sequential subproblems. Both approaches are implemented using the solver Hexaly. A comparative analysis is conducted under different scenarios and problem settings to highlight the advantages and drawbacks of each approach. The results show that the Divide-and-Conquer approach significantly improves computational efficiency, reducing time by up to 99% and vehicle usage by around 15–20% compared to the Holistic method. On the other hand, the Holistic method better ensures that mandatory jobs are completed, although at the cost of more resources. Full article

The aviation industry operates as a complex, dynamic system generating vast volumes of data from aircraft sensors, flight schedules, and external sources. Managing this data is critical for mitigating disruptive and costly events such as mechanical failures and flight delays. This paper presents a comprehensive application of predictive analytics and machine learning to enhance aviation safety and operational efficiency. We address two core challenges: predictive maintenance of aircraft engines and forecasting flight delays. For maintenance, we utilise NASA’s C-MAPSS simulation dataset to develop and compare models, including one-dimensional convolutional neural networks (1D CNNs) and long short-term memory networks (LSTMs), for classifying engine health status and predicting the Remaining Useful Life (RUL), achieving classification accuracy up to 97%. For operational efficiency, we analyse historical flight data to build regression models for predicting departure delays, identifying key contributing factors such as airline, origin airport, and scheduled time. Our methodology highlights the critical role of Exploratory Data Analysis (EDA), feature selection, and data preprocessing in managing high-volume, heterogeneous data sources. The results demonstrate the significant potential of integrating these predictive models into aviation Business Intelligence (BI) systems to transition from reactive to proactive decision-making. The study concludes by discussing the integration challenges within existing data architectures and the future potential of these approaches for optimising complex, networked transportation systems. Full article

The rapid adoption of hydrogen fuel cell vehicles (HFCVs) in the Beijing–Tianjin–Hebei (BTH) hub accentuates the mismatch between renewable-based hydrogen supply in Hebei and concentrated demand in Beijing and Tianjin. We develop a mixed-integer linear model that co-configures a hydrogen pipeline network and optimizes hourly flow schedules to minimize annualized cost and CO₂ emissions simultaneously. For 15,000 HFCVs expected in 2025 (137 t d⁻¹ demand), the Pareto-optimal design consists of 13 production plants, 43 pipelines and 38 refueling stations, delivering 50 767 t yr⁻¹ at 68% pipeline utilization. Hebei provides 88% of the hydrogen, 70% of which is consumed in the two megacities. Hourly profiles reveal that 65% of electrolytic output coincides with local wind–solar peaks, whereas refueling surges arise during morning and evening rush hours; the proposed schedule offsets the 4–6 h mismatch without additional storage. Transport distances are 40% < 50 km, 35% 50–200 km, and 25% > 200 km. Raising the green hydrogen share from 10% to 70% increases total system cost from USD 1.56 bn to USD 2.73 bn but cuts annual CO₂ emissions from 142 kt to 51 kt, demonstrating the trade-off between cost and decarbonization. The model quantifies the value of sub-day pipeline scheduling in resolving spatial–temporal imbalances for large-scale low-carbon hydrogen supply. Full article

Against the backdrop of policy-driven transformation in construction industrialization, the EPC general contracting model has emerged as a core pathway for the large-scale development of prefabricated buildings. However, the EPC mode integrates the links of design, procurement, production, and transportation, construction, resulting in a complex coupling correlation among the risk factors of prefabricated construction schedule, which is easy to induce the risk contagion effect and increase the difficulty of risk control of project schedule delay. To address this, this study constructs a hybrid model integrating the “Fuzzy Interpretive Structural Model (FISM)-Coupling Degree Model-Bayesian Network (BN)” to systematically analyze risk contagion mechanisms. Taking an EPC prefabricated building project as an example, FISM is used to reveal the hierarchical structure of risk factors, while the coupling degree model quantifies interaction strengths and maps them into the BN to optimize conditional probability parameters. Through comprehensive hazard analysis, seven key causal risk factors and two critical risk propagation paths are identified. Targeted control measures are designed for the key risk factors, and BN-based simulation is applied to locate critical risk nodes and implement break-chain interventions for the risk paths, resulting in a 23% reduction in the probability of schedule delay. Engineering applications demonstrate that this model can effectively achieve the dynamic identification and blocking of risk paths, providing valuable reference for similar projects and offering informed support for managers in formulating scientific response strategies. Full article

The rapid growth of electric vehicle (EV) charging demand poses significant challenges to distribution networks (DNs), particularly during public holidays when concentrated peaks occur near scenic areas and urban transport hubs. These sudden surges can strain transformer capacity and compromise supply reliability. Fixed soft open points (SOPs) are costly and underutilized, limiting their effectiveness in DNs with multiple transformers and asynchronous peak loads. To address this, from the perspective of power supply companies, this study proposes a mobile soft open point (MSOP)-based approach to enhance the hosting capacity of EV charging stations. The method pre-installs a limited number of fast-access interfaces (FAIs) at candidate transformers and integrates a semi-rolling horizon optimization framework to gradually expand interface availability while scheduling MSOPs daily. An automatic peak period identification algorithm ensures optimization focuses on critical load periods. Case studies on a multi-feeder distribution system coupled with a realistic traffic network demonstrate that the proposed method effectively balances heterogeneous peak loads, matches limited interfaces with MSOPs, and enhances system-level hosting capacity. Compared with fixed SOP deployment, the strategy improves hosting capacity during peak periods while reducing construction costs. The results indicate that MSOPs provide a practical, flexible, and economically efficient solution for power supply companies to manage concentrated holiday charging surges in DNs. Full article

Charging electric vehicles (EVs) and integrating renewable energy sources (RESs) are becoming key aspects of residential energy systems. However, the variability of RES generation, combined with uncontrolled EV charging, poses challenges for reliability, power quality, and supply-demand balancing within communities. The challenges only grow when considering other electrified building loads as well. Accurate forecasting of power demand and renewable generation is essential for efficient and sustainable grid operation, optimal use of RESs, and effective energy trading within communities. Deep learning (DL), including supervised, unsupervised, and reinforcement learning (RL), has emerged as a promising solution for predicting consumer demand, renewable generation, and managing energy flows in residential environments. This paper provides a comprehensive review of the development and application of these methods for forecasting and energy management in residential communities. Evaluation metrics across studies indicate that supervised learning can achieve highly accurate forecasting results, especially when integrated with unsupervised K-means clustering and data decomposition. These methods help uncover patterns and relationships within the data while reducing noise, thereby enhancing prediction accuracy. RL shows significant potential in control applications, particularly for charging strategies. Similarly to how V2G-simulators model individual EV usage and simulate large fleets to generate grid-scale predictions, RL can be applied to various aspects of EV fleet management, including vehicle dispatching, smart scheduling, and charging coordination. Traditional methods are also used across different applications and help utilities with planning. However, these methods have limitations and may not always be completely accurate. Our review suggests that integrating hybrid supervised-unsupervised learning methods with RL can significantly improve the sustainability and resilience of energy systems. This approach can improve demand and generation forecasting while enabling smart charging coordination and scheduling for scalable EV fleets integrated with building electrification measures. Furthermore, the review introduces a unifying conceptual framework that links forecasting, optimization, and policy coupling through hierarchical deep learning layers, enabling scalable coordination of EV charging, renewable generation, and building energy management. Despite methodological advances, real-world deployment of hybrid and deep learning frameworks remains constrained by data-privacy restrictions, interoperability issues, and computational demands, highlighting the need for explainable, privacy-preserving, and standardized modeling approaches. To be effective in practice, these methods require robust data acquisition, optimized forecasting and control models, and integrated consideration of transport, building, and grid domains. Furthermore, deployment must account for data privacy regulations, cybersecurity safeguards, model interpretability, and economic feasibility to ensure resilient, scalable, and socially acceptable solutions. Full article