Bingyou Dai, Xuesong Wang*, Qiming Guo, Lu Yang, Yu Bai
Abstract: Intersections are a critical focus in bicycle safety research, as approximately one-thirds of bicycle-related crashes occur at these locations. Although protected bike lanes (PBL) at intersections, such as Lateral Shift and Bend-out treatments have been implemented, there is limited crash-based research on their safety performance. Furthermore, the prevailing use of before-after study designs for safety evaluation makes this approach susceptible to selection bias. To address this issue, this study proposes a causal inference framework that combines the advanced generalized causal random forest (GRF) and multimodal large language model (LLM). The LLM is used to extract contextual features from street view images, improving control over unobserved confounding bias. The GRF model is used for effectiveness evaluation by addressing selection bias through residual-based orthogonalization of treatment and outcome. The framework was applied to evaluate the safety impacts of Bend-out and Lateral Shift treatments at intersections. The results indicate that Lateral Shift treatments tend to increase crashes, while Bend-out treatments reduce both total and bicycle crashes. Analysis of road user behavior reveals that for Lateral Shift treatments, the low rate of drivers yielding to cyclists is a major issue. Furthermore, riding in the wrong direction is a potential risk for both Lateral Shift and Bend-out treatments.
引用：Bingyou Dai, Xuesong Wang*, Qiming Guo, Lu Yang, Yu Bai. Safety evaluation of protected bike Lane treatments at Intersections: A causal framework. Accident Analysis & Prevention, Volume 220, September 2025, 108132.