Abstract This study investigates the effects of different variables including meteorology, trip characteristics (such as time of day), driving characteristics (such as the frequency of extended idling), and driver characteristics (such as driving experience) on trip-level emission factors (EFs). Drivers in the Greater Toronto and Hamilton Area (GTHA) were recruited to collect in-vehicle GPS data over a one-week study period from March to July 2018. Data from 1113 driving trips were collected, including characteristics of the trips and the drivers (51 independent variables). Trip emissions were estimated in addition to a driving eco-score indicator (on a hundred point scale) based on log-transformed emissions of greenhouse gases (GHG) in CO2eq and fine particulate matter (PM2.5). A machine learning approach, the Extreme Gradient Boosting (XGBoost), was used to develop prediction models for CO2eq and PM2.5 emissions at a trip level. The coefficient of determination (R2) and root-mean-square-error (RMSE) of eco-score models were respectively 0.84 (std. dev. 0.05), and 10.26 (std. dev. 1.24) for CO2eq, and 0.85 (std. dev. 0.03), and 10.64 (std. dev. 0.79) for PM2.5. The novel Shapley additive explanation (SHAP) measures were employed to reveal the importance of various features affecting trip emissions. For CO2eq, driving behavior such as the frequency of extended idling was found to have the most significant impact on the trip emission intensity. Additionally, driving experience was the most significant discrete feature affecting the eco-score. For PM2.5, the most significant feature was driver age, which was highly correlated with vehicle model year. Finally, commuter drivers were found to have lower CO2eq and PM2.5 emission intensities, owing to their familiarity with route and traffic conditions.

中文翻译：

---

一种捕捉驾驶行为和驾驶员特征对行程排放的影响的机器学习方法

摘要 本研究调查了不同变量的影响，包括气象、出行特征（如一天中的时间）、驾驶特征（如长时间怠速的频率）和驾驶员特征（如驾驶经验）对出行水平排放因子的影响（ EF）。在 2018 年 3 月至 7 月的为期一周的研究期间，招募了大多伦多和汉密尔顿地区 (GTHA) 的司机收集车载 GPS 数据。收集了 1113 次驾驶旅行的数据，包括旅行和司机的特征（ 51 个自变量）。除了基于 CO2eq 和细颗粒物 (PM2.5) 中温室气体 (GHG) 的对数转换排放量的驱动生态评分指标（以 100 分制）之外，还估算了出行排放量。一种机器学习方法，极限梯度提升（XGBoost），用于开发旅行级别的 CO2eq 和 PM2.5 排放预测模型。生态评分模型的决定系数 (R2) 和均方根误差 (RMSE) 对于 CO2eq 分别为 0.84 (std. dev. 0.05) 和 10.26 (std. dev. 1.24) 和 0.85 (std. dev. 1.24) . dev. 0.03) 和 PM2.5 的 10.64 (std. dev. 0.79)。采用新颖的沙普利加法解释 (SHAP) 措施来揭示影响出行排放的各种特征的重要性。对于 CO2eq，发现延长怠速频率等驾驶行为对行程排放强度的影响最为显着。此外，驾驶体验是影响生态评分的最重要的离散特征。对于 PM2.5，最显着的特征是驾驶员年龄，这与车型年份高度相关。最后，