In the field of freeway traffic safety research, there is an increasing focus in studies on how to reduce the frequency and severity of traffic crashes. Although many studies divide factors into “human-vehicle-road-environment” and other dimensions to construct models whichshowthe characteristic patterns of each factor's influence on crash severity, there is still a lack of research on the interaction effect of road and environment characteristics on the severity of a freeway traffic crash. This research aims to explore the influence of road and environmental factors on the severity of a freeway traffic crash and establish a prediction model towards freeway traffic crash severity. Firstly, the obtained historical traffic crash data variables were screened, and 11 influencing factors were summarized from the perspective of road and environment, and the related variables were discretized. Furthermore, the XGBoost (eXtreme Gradient Boosting) model was established, and the SHAP (SHapley Additive exPlanation) value was introduced to interpret the XGBoost model; the importance ranking of the influence degree of each feature towards the target variables and the visualization of the global influence of each feature towards the target variables were both obtained. Then, the Bayesian network-based freeway traffic crash severity prediction model was constructed via the selected variables and their values, and the learning and prediction accuracy of the model were verified. Finally, based on the data of the case study, the prediction model was applied to predict the crash severity considering the interaction effect of various factors in road and environment dimensions. The results show that the characteristic variables of road side protection facility type (RSP), road section type (LAN), central isolation facility (CIF), lighting condition (LIG), and crash occurrence time (TIM) have significant effects on the traffic crash prediction model; the prediction performance of the model considering the interaction of road and environment is better than that of the model considering the influence of single condition; the prediction accuracy of XGBoost-Bayesian Network Model proposed in this research can reach 89.05%. The identification and prediction of traffic crash risk is a prerequisite for safety improvement, and the model proposed and results obtained in this research can provide a theoretical basis for related departments in freeway safety management.

The last mile problem of E-grocery Distribution comprises one of the most costly and highest polluting components of the supply chain in which companies deliver goods to end customers. To reduce transport cost and fuel emissions, a new element of ground-based delivery services, autonomous delivery vehicles (ADVs), is included in the E-grocery distribution system for improving delivery efficiency. Thus, the objective of this study is to optimize a two-echelon distribution network for efficient E-grocery delivery, where conventional vans serve the delivery in the first echelon and ADVs serve delivery in the second echelon. The problem is formulated as a two-echelon vehicle routing problem with mixed vehicles (2E-VRP-MV) with a nonlinear objective function, in which the total transport and emission costs are optimized. This optimization is based on the flow assignment at each echelon and to realize routing choice for both the van and ADV. A two-step clustering-based hybrid Genetic Algorithm and Particle Swarm Optimization (C-GA-PSO) algorithm is proposed to solve the problem. First, the end customers are clustered to the intermediate depots, named satellites, based on the minimized distance and maximized demand. To enhance the efficiency of resolving the 2E-VRP-MV-model, a hybrid GA-PSO algorithm is adopted to solve the vehicle routing problem. Computational results of up to 21, 32, 50, and 100 customers show the effectiveness of the methods developed here. At last, the impacts of the layout of the depot-customer and customer density on the total cost are analyzed. This study sheds light on the tactical planning of the multi-echelon sustainable E-grocery delivery network.

With advancements in remote sensing technologies, high-resolution imagery has become increasingly accessible, supporting applications in urban planning, environmental monitoring, and precision agriculture. However, semantic segmentation of such imagery remains challenging due to complex spatial structures, fine-grained details, and land cover variations. Existing methods often struggle with ineffective feature representation, suboptimal fusion of global and local information, and high computational costs, limiting segmentation accuracy and efficiency. To address these challenges, we propose the dual-level network (DLNet), an enhanced framework incorporating self-attention and cross-attention mechanisms for improved multi-scale feature extraction and fusion. The self-attention module captures long-range dependencies to enhance contextual understanding, while the cross-attention module facilitates bidirectional interaction between global and local features, improving spatial coherence and segmentation quality. Additionally, DLNet optimizes computational efficiency by balancing feature refinement and memory consumption, making it suitable for large-scale remote sensing applications. Extensive experiments on benchmark datasets, including DeepGlobe and Inria Aerial, demonstrate that DLNet achieves state-of-the-art segmentation accuracy while maintaining computational efficiency. On the DeepGlobe dataset, DLNet achieves a $76.9\%$ mean intersection over union (mIoU), outperforming existing models such as GLNet ($71.6\%$) and EHSNet ($76.3\%$), while requiring lower memory (1443 MB) and maintaining a competitive inference speed of 518.3 ms per image. On the Inria Aerial dataset, DLNet attains an mIoU of $73.6\%$, surpassing GLNet ($71.2\%$) while reducing computational cost and achieving an inference speed of 119.4 ms per image. These results highlight DLNet’s effectiveness in achieving precise and efficient segmentation in high-resolution remote sensing imagery.

Decentralized freight decision has been proved to be one of the inhibitors to achieve a sustainable transport network. One important method also a key challenge is to determine how to coordinate and consolidate the transportation flow to get the best logistics performance. This study presents an intermodal transportation network considering freight consolidation through freight forwarders’ cooperation. We formulate the problem as a minimum intermodal transport cost model, which is a nonlinear, nonconvex and discontinuous function that involves volume economies of scale, distance economies of scale and vehicle size economies of scale. A hybrid genetic algorithm (GA) and particle swarm optimization (PSO) algorithm in combination with a batch strategy are used to solve the problem. Five different transport demand scenarios are tested on a real case on “China Railway Express” (Crexpress). The choices of reasonably corridor and fleet size combination are provided.