To improve traffic efficiency, adaptive traffic signal control (ATSC) systems have been widely developed. However, few studies have proactively optimized the air environmental issues in the development of ATSC. To fill this research gap, this study proposes an optimized ATSC algorithm to take into consideration both traffic efficiency and decarbonization. The proposed algorithm is developed based on the deep reinforcement learning (DRL) framework with dual goals (DRL-DG) for traffic control system optimization. A novel network structure combining Convolutional Neural Networks and Long Short-Term Memory Networks is designed to map the intersection traffic state to a Q-value, accelerating the learning process. The reward mechanism involves a multi-objective optimization function, employing the entropy weight method to balance the weights among dual goals. Based on a representative intersection in Changsha, Hunan Province, China, a simulated intersection scenario is constructed to train and test the proposed algorithm. The result shows that the ATSC system optimized by the proposed DRL-DG results in a reduction of more than 71% in vehicle waiting time and 46% in carbon emissions compared to traditional traffic signal control systems. It converges faster and achieves a balanced dual-objective optimization compared to the prevailing DRL-based ATSC.

This study introduces a multi-objective deep reinforcement learning (DRL)-based adaptive transit signal priority control framework designed to enhance safety and efficiency in mixed-autonomy traffic environments. The framework utilizes real-time data from connected and automated vehicles (CAVs) to define states, actions, and rewards, with traffic conflicts serving as the safety reward and vehicle waiting times as the efficiency reward. Transit signal priority strategies are incorporated, assigning weights based on vehicle type and passenger capacity to balance these competing objectives. Simulation modeling, based on a real-world intersection in Changsha, China, evaluated the framework’s performance across multiple CAV penetration rates and weighting configurations. The results revealed that a 5:5 weight ratio for safety and efficiency achieved the best trade-off, minimizing delays and conflicts for all vehicle types. At a 100% CAV penetration rate, delays and conflicts were most balanced, with buses showing an average waiting time of 4.93 s and 0.4 conflicts per vehicle, and CAVs achieving 1.97 s and 0.49 conflicts per vehicle, respectively. In mixed traffic conditions, the framework performed best at a 75% CAV penetration rate, where buses, cars, and CAVs exhibited optimal efficiency and safety. Comparative analysis with fixed-time signal control and other DRL-based methods highlights the framework’s adaptability and robustness, supporting its application in managing mixed traffic and enabling intelligent transportation systems for future smart cities.

New quality productive forces (NQPF), digital economy advancement, and artificial intelligence (AI) technologies are becoming crucial for promoting sustainable urban development. This study proposes a Multi-head Attention Deep & Cross Network (MADCN) framework, combining feature interaction modeling and attention mechanisms, to predict urban carbon emissions and investigate the impacts of technological factors. The framework incorporates an interpretable learning phase using SHapley Additive exPlanations (SHAP) to assess the contributions of different features. A panel dataset covering 275 Chinese cities is utilized to test the MADCN model. Experimental results demonstrate that the MADCN model achieves superior predictive performance compared to traditional machine learning and deep learning baselines, with a Mean Squared Error (MSE) of 406,151.063, a Mean Absolute Error (MAE) of 612.304, and an R-squared value of 0.991 on the test set. SHAP analysis highlights that population, city size, urbanization rate, and GDP are among the most influential factors on carbon emissions, while NQPF, digital economy index, and AI technology level also show meaningful but relatively moderate effects. Advancing NQPF, strengthening the digital economy, and accelerating AI technology development can significantly contribute to reducing urban carbon emissions. Policymakers should prioritize integrating technological innovation into carbon reduction strategies, particularly by promoting intelligent infrastructure and enhancing digitalization across sectors, to effectively achieve dual-carbon goals.