Intelligent Traffic Management Strategies for Weather-Sensitive Highways Under Adverse Conditions

This study aims to develop intelligent traffic management strategies to mitigate the adverse impacts of inclement weather on high-impact road segments. A comprehensive framework is proposed, integrating weather-responsive variable speed limit (VSL) control, adaptive signal control, and incident management. A weather-traffic interaction model is established using multivariate regression, revealing that precipitation, visibility, and temperature significantly affect traffic flow, Precipitation is found to have a substantial effect when hourly rainfall intensity exceeds 10 mm/h(β = −0.15, p < 0.01). Visibility below 200 m is associated with a marked decrease in operating speeds(β = −0.22, p < 0.01). Temperature drops below 5 ℃ also exhibit a statistically significant influence on traffic flow(β = −0.08, p < 0.05). A VSL optimization model is developed, incorporating weather factors and traffic dynamics. Simulation experiments show that weather-responsive VSL reduces crash risk by 25.6% and improves travel time reliability by 18.3% compared to static speed limits. An adaptive signal control strategy is designed using reinforcement learning, optimizing timing plans based on real-time weather and traffic data. Simulation results indicate that adaptive control reduces average intersection delay by 23.5% and increases network throughput by 12.1% under adverse weather, outperforming fixed-time control. An integrated incident management framework is proposed, leveraging deep learning for weather-related incident detection (accuracy: 92.4%) and dynamic programming for response optimization. Case studies demonstrate a 30.2% reduction in incident duration and 26.8% decrease in total delay. Sensitivity analysis confirms the robustness of the proposed strategies under various weather scenarios. This study contributes a data-driven, proactive approach to enhance traffic safety, efficiency, and resilience under adverse weather conditions on high-impact road segments.