The present study investigated the impact of real-time weather (air temperature, relative humidity, precipitation, wind speed, and solar radiation) on crash injury severity. Recent crash data (January 2016 to April 2021) on Interstate-75 in the state of Kentucky were merged with real-time weather information (retrieved from Kentucky Mesonet stations) at the 1-hour level. The severity index “SI” (i.e., the ratio of percent severe crashes to percent exposure of a specific weather state during the crash period) was introduced to evaluate the impact of different real-time weather states on fatal and severe injury crashes. Furthermore, the standard mixed logit (MXL), correlated mixed logit (CMXL), and correlated mixed logit with heterogeneity in means (CMXLHM) models were fitted and compared to identify the risk factors contributing to crash injury severity while accounting for unobserved heterogeneity. The results showed that the CMXLHM model was statistically superior to the CMXL and MXL models based on various goodness-of-fit measures (e.g., Akaike information criterion “AIC” and McFadden pseudo R-squared). Results from the SI analysis and CMXLHM model showed that real-time weather-related factors (e.g., air temperature ≥ 70 F and relative humidity ≥ 90 %) were significantly associated with higher severe injury likelihood. Further, driving under the influence (DUI), young drivers, and vehicle travel speed were associated with greater injury severities. On the other hand, presence of horizontal curve, passenger cars, and hourly traffic volume were associated with lower injury severity likelihood. The study outcomes can help in incident management by suggesting specific real-time weather-related states to feed to dynamic message signs (DMS) to enhance travelers’ safety along the interstates.

中文翻译：

---

使用具有均值异质性的相关随机参数 Logit 模型，实时天气状况对肯塔基州碰撞伤害严重程度的影响

本研究调查了实时天气（气温、相对湿度、降水、风速和太阳辐射）对碰撞伤害严重程度的影响。肯塔基州 75 号州际公路最近发生的事故数据（2016 年 1 月至 2021 年 4 月）与 1 小时级别的实时天气信息（从肯塔基州 Mesonet 站检索）合并。引入严重性指数“SI”（即严重事故百分比与事故期间特定天气状态暴露百分比的比率）来评估不同实时天气状态对致命和重伤事故的影响。此外，对标准混合对数 (MXL)、相关混合对数 (CMXL) 和均值异质性相关混合对数 (CMXLHM) 模型进行拟合和比较，以确定导致碰撞伤害严重程度的风险因素，同时考虑到未观察到的异质性。结果表明，基于各种拟合优度测量（例如，Akaike 信息准则“AIC”和 McFadden 伪 R 平方），CMXLHM 模型在统计上优于 CMXL 和 MXL 模型。SI 分析和 CMXLHM 模型的结果表明，实时天气相关因素（例如气温 ≥ 70 F 和相对湿度 ≥ 90 %）与较高的严重伤害可能性显着相关。此外，酒后驾驶（DUI）、年轻驾驶员和车辆行驶速度与更严重的伤害有关。另一方面，水平弯道、客车和每小时交通量的存在与较低的伤害严重程度可能性相关。研究结果可以通过建议特定的实时天气相关状态来反馈给动态信息标志（DMS），从而提高州际公路上旅行者的安全，从而有助于事件管理。