With the increasing energy use and carbon emissions in the transportation industry, its impact on the greenhouse effect is gradually being recognized. Therefore, this study aims to explore the achievement of carbon emission peak and carbon neutrality in transportation through prediction. The research employs a deep learning model, the CNN-GRU-Attention model, to predict carbon emissions in the transportation industry in Jiangsu, China. We select influencing factors through an extended STIRPAT model coupled with Lasso regression, and construct the CNN-GRU-Attention traffic carbon emission prediction model according to data indicators from 1995 to 2021. The model predicts carbon emissions from the transportation industry in Jiangsu Province between 2022 and 2035 under six distinct scenarios and proposes corresponding emission reduction strategies. The results show that the model in this study has higher prediction accuracy compared with other models, with a mean absolute error (MAE) of 0.061582, root mean square error (RMSE) of 0.085025, and R² of 0.91609 on the test set. Scenario-based predictions reveal that emission peak in the transportation industry in Jiangsu Province can be achieved under the clean development and comprehensive low-carbon scenarios, with technological innovation being the primary driver of low-carbon emission reductions. This study provides a novel approach for forecasting carbon emissions from the transportation industry and explores the implementation path of emission peak through this method.

With the acceleration of urbanisation and the rapid increase in road traffic volume, the scientific prediction of traffic accidents has become crucial for improving road safety and enhancing traffic efficiency. However, traffic accident prediction is a complex and multifaceted problem that requires the comprehensive consideration of multiple factors, including people, vehicles, roads and the environment. This paper provides a detailed analysis of traffic accident prediction based on multi-source data. By thoroughly considering data sources, data processing and prediction methods, this paper introduces the various aspects of traffic accident prediction from different perspectives. It helps readers understand the characteristics of different data and methods, the process of accident prediction and the key technologies involved. At the end of the paper, the main challenges and future directions in road crash prediction research are summarised. For example, the lack of efficient data sharing between different departments and fields poses significant challenges to the integration of multi-source data. In the future, combining deep learning models with time-sensitive data, such as social media and vehicle network data, could effectively improve the accuracy of real-time accident prediction.

The strategic development of reverse logistics networks is crucial for addressing the common challenge of low recovery rates for end-of-life vehicles (ELVs) in China. To minimize the total cost of the reverse logistics network for ELVs, this paper proposes a mixed-integer linear programming (MILP) model. The model considers the recycling volume of different vehicle types, facility processing capacity, and the proportions of parts and materials. Building on this foundation, a fuzzy mixed-integer nonlinear programming (FMINLP) model is developed to account for the inherent uncertainty associated with recycling volumes and facility processing capacities. The model was solved using Lingo, and its effectiveness was validated using Jiangsu Province of China as a case study, followed by a sensitivity analysis. The results indicate that dismantling and machining centers incur the highest processing costs. Variations in recycling volume and facility handling capacity significantly impact total costs and site selection, with the former having a more pronounced effect. Increasing facility processing capacity effectively increases the recovery rate. Moreover, a higher confidence level corresponds to higher total costs and a greater demand for facilities.

In the context of sustainable logistics planning, carbon emission costs have become a critical factor influencing distribution decisions. Meanwhile, the time-dependent characteristics of urban road networks and simultaneous pickup–delivery operations present significant challenges to vehicle routing problems (VRPs). This study addresses a time-dependent vehicle routing problem with simultaneous pickup–delivery and time windows (TDVRPSPDTW). Fuel consumption and carbon emission costs are quantified using a comprehensive emission model, while time-dependent network conditions, simultaneous pickup–delivery demands, and time window constraints are integrated into a unified modeling framework. To solve this NP-hard problem, an improved ant colony optimization (IACO) algorithm is developed by incorporating adaptive large neighborhood search to enhance solution diversity and convergence efficiency. Computational experiments are conducted using internationally recognized VRPSPDTW benchmark datasets and newly constructed TDVRPSPDTW instances, together with sensitivity analyses under varying traffic conditions, time window flexibility, and delivery strategies. The results indicate that the proposed IACO effectively addresses the TDVRPSPDTW. Comparing ant colony optimization with local search (ACO-LS), the IACO achieves a maximum reduction of 11.78% in total distribution cost. Furthermore, relative to the conventional separate pickup–delivery strategy, the simultaneous pickup–delivery mode reduces total distribution cost and carbon emission cost by 49.96% and 53.48%, respectively.

Achieving consensus in group decision-making is both essential and challenging, especially in which non-cooperative behaviors can significantly hinder the process under uncertainty. These behaviors may distort consensus outcomes, leading to increased costs and reduced efficiency. To address this issue, this study proposes a data-driven robust minimum-cost consensus model (MCCM) that accounts for non-cooperative behaviors by leveraging individual adjustment willingness. The model introduces an adjustment willingness function to identify non-cooperative participants during the consensus-reached process (CRP). To handle uncertainty in unit consensus costs, Principal Component Analysis (PCA) and Kernel Density Estimation (KDE) are employed to construct data-driven uncertainty sets. A robust optimization framework is then used to minimize the worst-case consensus cost within these sets, improving the model’s adaptability and reducing the risk of suboptimal decisions. To enhance computational tractability, the model is reformulated into a linear equivalent using the duality theory. Experimental results from a case study on house demolition compensation negotiations in Guiyang demonstrate the model’s effectiveness in identifying and mitigating non-cooperative behaviors. The proposed approach significantly improves consensus efficiency and consistency, while the data-driven robust strategy offers greater flexibility than traditional robust optimization methods. These findings suggest that the model is well-suited for complex real-world group decision-making scenarios under uncertainty.

As global climate change intensifies and fossil fuel resources continue to deplete, transitioning to alternative energy sources has become a vital strategy for sustainable development. Photovoltaic (PV) power generation, recognized for its clean, renewable, and low-carbon characteristics, is advancing rapidly. Against this background, site selection for PV power plant stations has become a crucial decision-making factor in ensuring project success. However, in large-scale group decision-making (LGDM), the complex backgrounds and substantial number of decision-makers (DMs) pose a significant challenge in reaching consensus efficiently. Therefore, this paper proposes a multi-objective optimization consensus model (MOOCM) utilizing dynamic trust networks to solve LGDM problems. First, a hybrid trust network (HTN) is built by integrating preference similarity and trust relationships, and DMs are clustered using the Louvain algorithm based on this hybrid network. Second, a MOOCM is designed with the objectives of minimizing costs, maximizing fairness, and achieving a high consensus level. Then, after consensus is reached, the HTN is updated, and secondary clustering is performed to obtain dynamic weights for DMs. Finally, a PV power plant site selection problem with 20 DMs, four alternatives, and four attributes is used as a case study for validation. In the first clustering, the DMs are divided into four subgroups. After consensus is reached, the HTN is updated and a second clustering is performed, which finally produces three subgroups. At the same time, the proposed method can achieve a group consensus level (GCL) of 0.9597, with Cost = 1.7422 and Fairness = 0.9043. These results verify the effectiveness and practical utility of the proposed method in LGDM.