城市轨道交通站点周边建成环境对地铁客流量的影响研究——以深圳市为例
Impact of Built Environment of Urban Rail Transit Stations on Metro Passenger Flow: A Case Study of Shenzhen
黄建欣
广东省科学院广州地理研究所 规划师，硕士
龚蔚霞
广东省科学院广州地理研究所主任，正高级工程师，博士，硕士生导师
张金林
广东省科学院广州地理研究所 助理工程师
汤咏诗
广东省科学院广州地理研究所 助理工程师
吴 巍
河北工程大学建筑与艺术学院 讲师，博士
摘要: 传统线性模型无法显示指标的非线性结果，难以体现各指标的相对重要性和影响阈值。利用深圳轨道交通刷卡数据，构建梯度提升决策树（GBDT）模型，探索建成环境对不同时间段客流量的非线性关系，以期为城市尤其是超大特大城市的交通规划、站点开发、站点周边建成环境优化提供参考。结果表明：不同建成环境对不同时间段客流量的相对重要性不一致，建筑容积率、居住用地比例、商业商务用地比例、距CBD距离对站点客流量均有相对较高且稳健的影响；建成环境与客流量存在明显的非线性关系和阈值；当土地利用混合度在0.60以上和距CBD距离超过17 km时，全天客流量呈现明显的下降趋势；建成环境对不同时间段客流量的影响机制不完全相同；城中村对地铁客流量的促进效果十分显著。
Abstract: Traditional linear models cannot display the nonlinear results of indicators, making it difficult to reflect the relative importance and impact threshold of each indicator. This study uses Shenzhen rail transit smart card date to construct a gradient boosting decision tree (GBDT) model to explore the non-linear relationship between the built environment and passenger flow in different time periods, hoping to provide references for transportation planning, station development, and optimization of built environment around stations in cities, especially mega cities. The results show that: ① Different built environments have different relative importance to passenger flow in different time periods. Building floor area ratio, proportion of residential land, proportion of commercial land, and distance from CBD all have relatively high and robust effects on site passenger flow. ② There is a significant nonlinear relationship and threshold between the built environment and passenger flow. ③ When the land use mixing degree is above 0.60 and the distance from CBD exceeds 17 km, the daily passenger flow shows a significant downward trend. ④ The impact mechanism of the built environment on the passenger flow in different time periods is not completely the same. ⑤ The promotion effect of urban villages on subway passenger flow is very significant.
关键词：城市轨道交通；建成环境；客流量；梯度提升决策树；非线性影响
Keyword: urban rail transit; built environment; passenger flow; gradient boosting decision tree; non-linear influencing
中图分类号：TU984
文献标识码: A
张赫，张建勋，王睿，等. 小城市建成环境对居民出行交通碳排放的影响机理[J]. 城市问题，2020（7）：4-10.
ZHANG He, ZHANG Jianxun, WANG Rui, et al. Built environment factors influencing CO2 emissions from residential trips in small Chinese cities[J]. Urban Problems, 2020(7): 4-10.
CERVERO R, KOCKELMAN K. Travel demand and the 3Ds: density, diversity, and design[J]. Transportation Research Part D: Transport and Environment, 1997, 2(3): 199-219.
EWING R, CERVERO R. Travel and the built environment: a synthesis[J]. Transportation Research Record: Journal of the Transportation Research Board, 2001, 1780(1): 87-114.
张文佳，鲁大铭. 影响时空行为的建成环境测度与实证研究综述[J]. 城市发展研究，2019，26（12）：9-16.
ZHANG Wenjia, LU Daming. Measuring built environment for spatiotemporal behavior studies: a review[J]. Urban Development Studies, 2019, 26(12): 9-16.
孙斌栋，但波. 上海城市建成环境对居民通勤方式选择的影响[J]. 地理学报，2015，70（10）：1664-1674.
SUN Bindong, DAN Bo. Impact of urban built environment on residential choice of commuting mode in Shanghai[J]. Acta Geographica Sinica, 2015, 70(10): 1664-1674.
盛来芳，宋彦. 城市土地利用对轨道交通运营的影响——以纽约地铁为例[J]. 城市交通，2012，10（2）：33-39.
SHENG Laifang, SONG Yan. Impact of urban land use development on the rail transit operation: a case study of New York City subway[J]. Urban Transport of China, 2012, 10(2): 33-39.
ZHAO J, DENG W, SONG Y, et al. What influences metro station ridership in China? Insights from Nanjing[J]. Cities, 2013, 35: 114-124.
仝德，高静，龚咏喜. 城中村对深圳市职住空间融合的影响——基于手机信令数据的研究[J]. 北京大学学报（自然科学版），2020，56（6）：1091-1101.
TONG De, GAO Jing, GONG Yongxi. Impact of urban village on job-housing balance in Shenzhen: a study using mobile phone signaling data[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(6): 1091-1101.
CHAVA J, PETER N, REENA T. Gentrification of station areas and its impact on transit ridership[J]. Case Studies on Transport, 2018, 6(1): 1-10.
任鹏，彭建东，杨红，等. 武汉市轨道交通站点周边地区职住平衡与建成环境的关系研究[J]. 地球信息科学学报，2021，23（7）：1231-1245.
REN Peng, PENG Jiandong, YANG Hong, et al. Relationship between jobs-housing balance and built environment in areas around urban rail transit stations of Wuhan[J]. Journal of Geo-information Science, 2021, 23(7): 1231-1245.
李清嘉，彭建东，杨红. 武汉市不同站域建成环境与轨道交通站点客流特征关系分析[J]. 地球信息科学学报，2021，23（7）：1246-1258.
LI Qingjia, PENG Jiandong, YANG Hong. Research on relationship analysis between passenger flow characteristics of rail transit stations and built environment of different station areas in Wuhan[J]. Journal of Geo-information Science, 2021, 23(7): 1246-1258.
仝照民，安睿，刘耀林. 建成环境对居民通勤方式选择的影响——以武汉市城中村为例[J]. 地理科学进展，2021，40（12）：2048-2060.
TONG Zhaomin, AN Rui, LIU Yaolin. Impact of the built environment on residents' commuting mode choices: a case study of urban village in Wuhan City[J]. Progress in Geography, 2021, 40(12): 2048-2060.
崔叙，喻冰洁，杨林川，等. 城市轨道交通出行的时空特征及影响因素非线性机制——基于梯度提升决策树的成都实证[J]. 经济地理，2021，41（7）：61-72.
CUI Xu, YU Bingjie, YANG Linchuan, et al. Spatio-temporal characteristics and non-linear influencing factors of urban rail transit: the case of Chengdu using the gradient boosting decision tree[J]. Economic Geography, 2021, 41(7): 61-72.
周扬，邵天元，钱才云. 南京市城市轨道交通站点周边地区建成环境对居民活动的影响——基于梯度提升决策树与SHAP解释模型的分析[J]. 科学技术与工程，2023，23（17）：7509-7519.
ZHOU Yang, SHAO Tianyuan, QIAN Caiyun. Influence of built environment on residents' activities in Nanjing urban rail transit station areas: an analysis based on gradient boosting decision tree and SHAP interpretation model[J]. Science Technology and Engineering, 2023, 23(17): 7509-7519.
DING C, CAO X, LIU C. How does the station-area built environment influence Metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds[J]. Journal of Transport Geography, 2019, 77: 70-78.
申犁帆，王烨，张纯，等. 轨道站点合理步行可达范围建成环境与轨道通勤的关系研究——以北京市44个轨道站点为例[J]. 地理学报，2018，73（12）：2423-2439.
SHEN Lifan, WANG Ye, ZHANG Chun, et al. Relationship between built environment of rational pedestrian catchment areas and URT commuting ridership: evidence from 44 URT stations in Beijing[J]. Acta Geographica Sinica, 2018, 73(12): 2423-2439.
GONG P, CHEN B, LI X, et al. Mapping essential urban land use categories in China (EULUC-China): preliminary results for 2018[J]. Science Bulletin, 2020, 65(3): 182-187.
FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. The Annals of Statistics, 2001, 29(5): 1189-1232.
丁聪，倪少权，吕红霞. 基于梯度提升的城市轨道交通客流量预测分析[J]. 城市轨道交通研究，2018，21（9）：60-63.
DING Cong, NI Shaoquan, LYU Hongxia. Forecast and analysis of urban rail transit passenger flow based on gradient boosting[J]. Urban Mass Transit, 2018, 21(9): 60-63.
夏陈红，翟国方. 基于GBDT机器学习算法的国土空间演变动力机制研究——以长江三角洲为例[J]. 城市发展研究，2022，29（11）：12-19.
XIA Chenhong, ZHAI Guofang. Research on dynamic mechanism of territorial space evolution in Yangtze River Delta based on GBDT machine learning algorithm[J]. Urban Development Studies, 2022, 29(11): 12-19.
杨红，申犁帆，胡议文，等. 老年人地铁出行时空特征及与建成环境非线性关系——以武汉市为例[J]. 地理科学进展，2023，42（3）：491-504.
YANG Hong, SHEN Lifan, HU Yiwen, et al. Spatial and temporal characteristics of elderly people's metro travel behavior and its non-linear relationship with the built environment: a case study of Wuhan City[J]. Progress in Geography, 2023, 42(3): 491-504.
SUN B D, ERMAGUN A, DAN B. Built environmental impacts on commuting mode choice and distance: evidence from Shanghai[J]. Transportation Research Part D: Transport and Environment, 2017, 52: 441-453.
本刊编辑部. “空间治理体系下的控制性详细规划改革与创新”学术笔谈会[J]. 城市规划学刊，2019（3）：1-10.
The Editorial Department. Academic symposium on "regulatory detailed planning reform and innovation under the space governance system"[J]. Urban Planning Forum, 2019(3): 1-10.
