
Impact of urban built environment on ride-hailing carbon emissions based on XGBoost model
Chaoying YIN, Yaoxia GE, Wendong CHEN, Xiaoquan WANG, Chunfu SHAO
Impact of urban built environment on ride-hailing carbon emissions based on XGBoost model
To investigate the interaction between the built environment and ride-hailing carbon emissions, this study uses ride-hailing order operation data from Nanjing. The built environment indicators are characterized based on factors such as population size, land use, distance to the city center, and housing prices. An Extreme Gradient Boosting (XGBoost) model is established, incorporating built environment factors at both the origin and destination of trips. The model aims to identify key factors affecting ride-hailing carbon emissions and reveal the nonlinear relationships and variable interactions between them. Additionally, the regression results of the XGBoost model are compared with those of the traditional Gradient Boosting Decision Tree (GBDT) model to verify the former’s advantage in regression fitting. The results indicate that the XGBoost model outperforms the traditional GBDT model, with R-squared, mean absolute error, and root mean square error values of 0.541, 0.364, and 0.275, respectively. The distance between ride-hailing trip origins and destinations and the city center contributes significantly, with contribution rates of 20.544% and 29.127%, respectively. Furthermore, the distance from the metro station to the origin and destination exhibits opposing feedback mechanisms on carbon emissions, indicating an asymmetric impact of metro station proximity on emissions. The nonlinear relationship between the distance from the origin to the city center and ride-hailing carbon emissions follows a U-shaped distribution, with significant threshold effects at 7 km and 20 km. Additionally, there are notable interaction effects between the distance from the city center and road density at the trip origin on ride-hailing carbon emissions.
urban transportation / nonlinear effect / XGBoost model / ride-hailing carbon emissions / built environment {{custom_keyword}} /
Tab.1 Descriptive statistics of variables表 1 变量描述性统计 |
类别 | 变量名称 | 变量描述 | 位置 | 平均值 | 最小值 | 最大值 |
---|---|---|---|---|---|---|
密度 | 人口数量 | 研究单元内人口数量 | 起点 | 6 019.121 | 0 | 40 559.102 |
终点 | 6 018.387 | 0 | 40 559.102 | |||
设计 | 道路密度/(km/km2) | 研究单元内路网长度与面积比值 | 起点 | 2.964 | 0 | 9.807 |
终点 | 2.947 | 0 | 10.044 | |||
多样性 | 土地利用混合度 | 研究单元内7类POI混合熵 | 起点 | 0.803 | 0 | 1.000 |
终点 | 0.799 | 0 | 1.000 | |||
可达性 | 距市中心距离/km | 距市中心欧式距离 | 起点 | 6.910 | 0.075 | 37.285 |
终点 | 6.900 | 0.023 | 36.477 | |||
到公共交通距离 | 距公交站点距离/km | 距邻近公交站点欧式距离 | 起点 | 0.232 | 0.002 | 1.746 |
终点 | 0.241 | 0.002 | 3.232 | |||
距地铁站点距离/km | 距邻近地铁站点欧式距离 | 起点 | 0.657 | 0.008 | 5.117 | |
终点 | 0.664 | 0.006 | 5.104 | |||
经济因素 | 房价/万元 | 研究单元内住宅房价平均值 | 起点 | 3.782 | 0.917 | 8.886 |
终点 | 3.807 | 0.964 | 8.885 |
Tab.2 COPERT emission model parameter table表2 COPERT排放模型参数表[14] |
参数 | CO | NOx | HC | CO |
---|---|---|---|---|
| 5.497×10-12 | 3.856×10-5 | 3.549×10-6 | 3.32×10-1 |
| -3.342×10-2 | -8.580×10-3 | -1.393×10-4 | -1.76×10 |
| 5.110 | 5.773×10-1 | 4.738×10-2 | 1.45×103 |
| -1.044×10-7 | 1.307×10-12 | -9.908×10-14 | 1.76×10-11 |
| 1.872×10-3 | 2.702×10-18 | -6.442×10-15 | 8.01×10-4 |
| -5.288×10-1 | -1.308×10-13 | 7.726×10-13 | 9.13×10-2 |
| 3.751×10 | 5.431 | 4.015 | 3.51 |
Tab.3 Calculation results of carbon emissions from fuel vehicles表 3 油车排放计算结果 |
污染物 | 总和/kg | 均值/kg |
---|---|---|
CO | 72.190 | 1.563×10-3 |
NOX | 22.790 | 0.493×10-3 |
HC | 4.496 | 0.097×10-3 |
CO2 | 6.474×104 | 1.401 |
总碳排放 | 6.484×104 | 1.404 |
Tab.4 Parameter settings and model comparison results表4 参数设置和模型对比结果 |
参数 | XGBoost模型 | GBDT模型 |
---|---|---|
learning_rate | 0.2 | 0.1 |
max_depth | 5 | 3 |
n_estimators | 200 | 100 |
R 2 | 0.541 | 0.436 |
MAE | 0.364 | 0.425 |
RMSE | 0.275 | 0.580 |
Tab.5 Influence degree of independent variables表5 自变量影响程度 |
类别 | 自变量 | 起点 | 终点 | 重要度 总计% | ||
---|---|---|---|---|---|---|
重要度% | 排序 | 重要度% | 排序 | |||
密度 | 人口数量 | 4.511 | 6 | 5.028 | 5 | 9.539 |
设计 | 道路密度 | 2.392 | 13 | 2.877 | 10 | 5.269 |
多样性 | 土地利用 混合度 | 2.610 | 12 | 2.258 | 14 | 4.868 |
可达性 | 距市中心 距离 | 20.544 | 2 | 29.127 | 1 | 49.671 |
到公共交通距离 | 距公交站点距离 | 3.203 | 8 | 4.036 | 7 | 7.239 |
距地铁站点距离 | 2.996 | 9 | 2.743 | 11 | 5.739 | |
经济因素 | 房价 | 5.951 | 4 | 11.725 | 3 | 17.676 |
Fig.2 Nonlinear impact of variables on ride-hailing carbon emissions图2 各变量对网约车碳排放的非线性影响 |
1 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
马健霄, 赵飞燕, 尹超英, 等. 建成环境和出租车需求对网约车出行需求影响的时空间分异模式[J]. 交通运输系统工程与信息, 2023, 23(5): 136-145.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
尹超英, 周建, 林丽, 等. 城市建成环境影响下通勤时间和距离联合建模研究[J]. 北京交通大学学报, 2021, 45(3): 24-29.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
杨文越, 曹小曙. 多尺度交通出行碳排放影响因素研究进展[J]. 地理科学进展, 2019, 38(11): 1814-1828.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
王靖添, 马晓明. 中国交通运输碳排放影响因素研究: 基于双层次计量模型分析[J]. 北京大学学报(自然科学版), 2021, 57(6): 1133-1142.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
韩印, 李媛媛, 李文翔, 等. 基于轨迹数据的网约车排放时空特征分析[J]. 交通运输系统工程与信息, 2022, 22(1): 234-242.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
Oak Ridge National Laboratory. LandScan global population database[EB/OL]. (2023-01-06) [2024-08-22].
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
Gaode Developer Platform. Web service API [EB/OL]. (2016-02-18) [2024-08-22].
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
The OpenStreetMap Foundation. OpenStreetMap [EB/OL]. (2004-07-01) [2024-08-22]
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
吴静娴, 唐桂孔, 李文翔. 建成环境对共享单车分时骑行量的非线性作用研究: 以上海市为例[J]. 交通运输系统工程与信息, 2024, 24(1): 290-298.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
21 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
22 |
许奇, 李雯茜, 陈越, 等. 建成环境对城市轨道交通起讫点客流的非线性影响及阈值效应[J]. 交通运输系统工程与信息, 2023, 23(4): 290-297.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
23 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
24 |
AAS K,
{{custom_citation.content}}
{{custom_citation.annotation}}
|
25 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
26 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |