The commitment to decarbonization is motivating urban planners to adopt emerging techniques that advance sustainability. Road traffic emissions remain a major source of greenhouse gases and pollutants, requiring precise, near-real-time monitoring for effective mitigation policies. This study introduces the design and demonstration of a digital twin (DT) platform for road traffic emission nowcasting and forecasting. The focus is on establishing a streamlined technical architecture and showcasing how the system can utilize multisource data from the Internet of Things (IoT) sensors and simulation to provide a high spatiotemporal resolution view of emissions. As a proof of concept, the platform leverages traffic camera data as IoT input, highlighting its potential for simultaneous emission and origin destination matrix estimation (ODME). A case study in Kista, Stockholm, illustrates the platform’s capabilities through a 3-dimensional (3D) interactive visualization in Unity. This demonstration serves as a first step toward a fully validated emission monitoring system, providing a scalable and modular framework that can be adapted for related applications, such as congestion analysis and noise monitoring.

Pedestrian crossing intention prediction is crucial for autonomous driving. While existing models have achieved high accuracy, their generalization and robustness remain limited, hindering their performance in real-world scenarios. To overcome these limitations, we introduce the LVLMPed-CoT, a large vision language model (LVLM) that incorporates a chain-of-thought (CoT) mechanism to enhance pedestrian crossing intention prediction. It takes multimodal data as input and employs data distillation along with a two stage fine-tuning strategy to elicit the implicit CoT capability of a lightweight vision-language model for enhanced perception, reasoning, and prediction. The unified LVLMPed-CoT is trained on a joint open-source dataset (JAAD and PIE) and achieves superior or comparable performance to state-of-the-art models on both large-scale public datasets. The ablation study validates the contribution of the CoT prompt design and the two-stage fine-tuning strategy to the model's performance. Further analysis investigates the impact of input data sequence length and image quality on both accuracy and inference time, as well as the interpretability of the enhanced CoT reasoning ability achieved through fine-tuning.

This study proposes an integer linear program model for ride-sharing, electric, autonomous mobility on demand (RE-AMoD) system operations and develops a model predictive control (MPC) algorithm to optimize the decisions of ride matching, vehicle routing, rebalancing, and charging. The system ensures that electric autonomous vehicles provide transportation services for up to two customers to share a ride and that they can be charged automatically during the operating period. The RE-AMoD problem is formulated as a network flow optimization problem considering ride-sharing and charging control. The objective is to minimize the customers’ waiting time while minimizing the system’s energy consumption. An iterative MPC is developed to compute the optimal control policy for real-time control. The case study uses real-world data from San Francisco to validate the model performance by comparing benchmark models in an RE-AMoD simulation platform and investigating the impact of ride-sharing and smart charging strategies on system performance by comparing models with no ride-sharing and heuristic charging strategies. The results show that the smart charging policy is critical for realizing ride-sharing's full advantages in RE-AMoD systems. Allowing the sharing of trips significantly improves system performance in terms of reducing fleet sizes and energy consumption while improving the customer level of service.

The evolution of metropolitan cities and increasing travel demand impose stringent requirements on traffic assignment methods. Multi-agent reinforcement learning (MARL) approaches outperform traditional methods in modeling adaptive routing behavior without requiring explicit system dynamics, making them attractive for real-world deployment. However, existing MARL frameworks face scalability and reliability challenges when managing large-scale networks with substantial and variable demand. This study proposes MARL-OD-DA, a novel framework that redefines agents as origin–destination (OD) pair routers and employs a continuous simplex-constrained action space. This reformulation reduces the agent population from O(N) (number of travelers) to O(|D|) (number of OD pairs), achieving at least two orders of magnitude fewer agents in practice while preserving convexity and enabling efficient adaptation to demand variation, thus significantly improving scalability. In contrast to prior MARL studies constrained to small-sized networks (up to 70 nodes, 2100 travelers) and fixed demand, MARL-OD-DA is validated on medium-sized networks (up to 416 nodes, 1406 OD pairs, and 360,600 travelers) under varying demand scenarios, demonstrating substantial improvements in scalability and applicability. To further enhance reliability, the framework integrates a Dirichlet-based policy, action pruning, and a relative gap-based reward. Theoretical analysis demonstrates that the Dirichlet-based policy reduces gradient bias, stabilizes variance, and enables sparse routing decisions, in contrast to the commonly used softmax-based policy. Experiments on three benchmark networks show that MARL-OD-DA significantly improves assignment quality and convergence speed. On the SiouxFalls network, the trained agents converge within 10 iterations during deployment, reducing the relative gap by 94.99% compared to conventional baselines.

Public transportation networks are highly interconnected, where disruptions like traffic congestion propagate bus delays and impact performance. Identifying delay causes is crucial, yet most studies rely on correlation-based methods rather than causal analysis. Attribution methods like the Shapley value quantify factor contributions but often overlook causal dependencies, leading to potential bias. This study uses a causal discovery model to uncover causal relationships between bus delays and various factors (e.g., operational factors, calendar, and weather). Based on this causal graph, an explainable Artificial Intelligence (AI) method quantifies each factor's contribution to delays, focusing on how these contributions vary at different stops along a route. By integrating scheduled route data and real-time vehicle locations, we analyze factor contributions over time and space, exploring various scenarios along the route. Cross-validation is conducted by comparing the importance ranking of factors with the Seemingly Unrelated Regression Equations (SURE). Results show significant variations in factors contributing to delays along the route. Delays at upstream stops propagate downstream, indicating a cascading effect. Operational factors dominate, accounting for 50%–83% of delays. Notably, delays from the preceding two to three stops have a larger impact than just the immediately preceding one stop, and origin delays strongly affect the first half of the route.

Online demand prediction plays an important role in transport network services from operations, controls to management, and information provision. However, the online prediction models are impacted by streaming data quality issues with noise measurements and missing data. To address these, we develop a robust prediction method for online network-level demand prediction in public transport. It consists of a PCA method to extract eigen demand images and an optimization-based pattern recognition model to predict the weights of eigen demand images by making use of the partially observed real-time data up to the prediction time in a day. The prediction model is robust to data quality issues given that the eigen demand images are stable and the predicted weights of them are optimized using the network level data (less impacted by local data quality issues). In the case study, we validate the accuracy and transferability of the model by comparing it with benchmark models and evaluate the robustness in tolerating data quality issues of the proposed model. The experimental results demonstrate that the proposed Pattern Recognition Prediction based on PCA (PRP-PCA) consistently outperforms other benchmark models in accuracy and transferability. Moreover, the model shows high robustness in accommodating data quality issues. For example, the PRP-PCA model is robust to missing data up to 50% regardless of the noise level. We also discuss the hidden patterns behind the network level demand. The visualization analysis shows that eigen demand images are significantly connected to the network structure and station activity variabilities. Though the demand changes dramatically before and after the pandemic, the eigen demand images are consistent over time in Stockholm.