基于多尺度地理加权回归模型的城市道路骑行流量分析

黄颙昊; 杨新苗; 岳锦涛

doi:10.16511/j.cnki.qhdxxb.2022.26.014

PDF(10426 KB)

清华大学学报（自然科学版） ›› 2022, Vol. 62 ›› Issue (7) : 1132-1141. DOI: 10.16511/j.cnki.qhdxxb.2022.26.014

论文

基于多尺度地理加权回归模型的城市道路骑行流量分析

黄颙昊¹, 杨新苗¹, 岳锦涛²

作者信息 +

Urban street bicycle flow analysis based on multi-scale geographically weighted regression model

HUANG Yonghao¹, YANG Xinmiao¹, YUE Jintao²

Author information +

文章历史 +

摘要

居民对城市慢行交通的服务品质需求不断提高，然而传统的慢行系统研究多关注大尺度和既有道路，无法充分满足城市街区慢行系统发展需求。以此为背景，该文提出了基于空间设计网络分析（spatial design network analysis，sDNA）的多尺度地理加权回归模型（multi-scale geographically weighted regression，MGWR），考虑土地开发利用情况、道路路网结构和周边公共交通状况对路段自行车流量的影响，对城市道路骑行流量进行分析。通过对京张铁路沿线区域内共享单车出行数据分析，结果表明：该模型相较于经典地理加权回归模型和多元线性回归模型，有更好的回归效果，拟合优度R²分别提高0.087和0.113。最后，借助该模型数据分析影响骑行流量的主要因素及其作用尺度范围，拓展了基于定量分析方法的慢行交通规划维度。

Abstract

Residents are demanding better conditions for urban non-motorized traffic. However, the classical forecasting model for non-motorized traffic has mainly focused on large city areas and existing roads, which cannot fully meet planning demands for the construction or extension of urban bicycle paths. This study used an improved multi-scale geographically weighted regression (MGWR) model to predict the flow of non-motorized traffic. The MGWR model includes the influence of land development and utilization, road network structure, and the nearby public transport on the bicycle flows. The area along the Beijing to Zhangjiakou Railway was used as an example for a case study using bike sharing data in this region. The results show that the MGWR model has better predictive ability with the geographically weighted regression model R² increased by 0.087 and the multiple linear regression with R² increased by 0.113. Finally, this paper gives an approach for non-motorized traffic planning and management based on key factors affecting non-motorized traffic with appropriate ranges of the independent variables.

导出引用

黄颙昊, 杨新苗, 岳锦涛. 基于多尺度地理加权回归模型的城市道路骑行流量分析[J]. 清华大学学报（自然科学版）. 2022, 62(7): 1132-1141 https://doi.org/10.16511/j.cnki.qhdxxb.2022.26.014

HUANG Yonghao, YANG Xinmiao, YUE Jintao. Urban street bicycle flow analysis based on multi-scale geographically weighted regression model[J]. Journal of Tsinghua University(Science and Technology). 2022, 62(7): 1132-1141 https://doi.org/10.16511/j.cnki.qhdxxb.2022.26.014

参考文献

[1] 中国城市规划设计研究院. 2020年度全国主要城市通勤监测报告[R/OL].[2022-04-18]. http://www.chinautc.com/20200520.pdf. China Academy of Urban Planning and Design. 2020 annual report on major cities' daily commute monitoring in China[R/OL].[2022-04-18]. http://www.chinautc.com/20200520.pdf. (in Chinese)
[2] 姜超. 基于人本化分析的北京慢行空间研究[D]. 北京:北京工业大学, 2016. JIANG C. The research on pedestrian and bicycle space design in Beijing based on people-oriented analysis[D]. Beijing:Beijing University of Technology, 2016. (in Chinese)
[3] LIN Z J, FAN W. Modeling bicycle volume using crowdsourced data from Strava smartphone application[J]. International Journal of Transportation Science and Technology, 2020, 9(4):334-343.
[4] ZIMMERMANN M, MAI T, FREJINGER E. Bike route choice modeling using GPS data without choice sets of paths[J]. Transportation Research Part C:Emerging Technologies, 2017, 75:183-196.
[5] PAZDAN S. The impact of weather on bicycle risk exposure[J]. Archives of Transport, 2020, 56(4):89-105.
[6] 林堉楠, 徐媛, 杨家文. 轨道交通车站周边建成环境对骑行的影响:基于深圳市ofo数据的实证研究[J]. 城市交通, 2020, 18(1):83-94, 58. LIN Y N, XU Y, YANG J W. Built environment on linking bicycle to rail transit:Case study based on ofo data in Shenzhen[J]. Urban Transport of China, 2020, 18(1):83-94, 58. (in Chinese)
[7] CHEN P, ZHOU J P, SUN F Y. Built environment determinants of bicycle volume:A longitudinal analysis[J]. Journal of Transport and Land Use, 2017, 10(1):655-674.
[8] SHEN Y, ZHANG X H, ZHAO J H. Understanding the usage of dockless bike sharing in Singapore[J]. International Journal of Sustainable Transportation, 2018, 12(9):686-700.
[9] YANG H T, ZHANG Y B, ZHONG L Z, et al. Exploring spatial variation of bike sharing trip production and attraction:A study based on Chicago's Divvy system[J]. Applied Geography, 2020, 115:102130.
[10] YANG F, DING F, QU X, et al. Estimating urban shared-bike trips with location-based social networking data[J]. Sustainability, 2019, 11(11):3220.
[11] 胡元. 城市道路慢行交通需求预测研究[D]. 成都:西南交通大学, 2019. HU Y. Research on the non-motorized traffic demand forecasting of the urban road[D]. Chengdu:Southwest Jiaotong University, 2019. (in Chinese)
[12] 许淼, 刘宏飞, 初凯. 基于AM-LSTM模型的共享单车时空需求预测[J]. 湖南大学学报(自然科学版), 2020, 47(12):77-85. XU M, LIU H F, CHU K. Spatiotemporal demand prediction of bike-sharing based on AM-LSTM model[J]. Journal of Hunan University (Natural Sciences), 2020, 47(12):77-85. (in Chinese)
[13] YANG Z D, HU J, SHU Y C, et al. Mobility modeling and prediction in bike-sharing systems[C]//Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services. Singapore:ACM, 2016:165-178.
[14] GAO X H, LEE G M. Moment-based rental prediction for bicycle-sharing transportation systems using a hybrid genetic algorithm and machine learning[J]. Computers & Industrial Engineering, 2019, 128:60-69.
[15] 王凌苏. 共享单车交通量预测与停放点选址研究[D]. 北京:北京交通大学, 2020. WANG L S. Traffic flow prediction and rental location of bike-sharing system[D]. Beijing:Beijing Jiaotong University, 2020. (in Chinese)
[16] 段进, 杨滔, 盛强, 等. 空间句法教程[M]. 北京:中国建筑工业出版社, 2019. DUAN J, YANG T, SHENG Q, et al. Introduction to space syntax[M]. Beijing:China Architecture & Building Press, 2019. (in Chinese)
[17] ZHANG L Z, CHIARADIA A, ZHUANG Y. A configurational accessibility study of road and metro network in Shanghai, China[M]//Recent Developments in Chinese Urban Planning. Guangzhou:Springer, 2015:219-245.
[18] COOPER C H V. Using spatial network analysis to model pedal cycle flows, risk and mode choice[J]. Journal of Transport Geography, 2017, 58:157-165.
[19] MCCAHILL C, GARRICK N W. The applicability of space syntax to bicycle facility planning[J]. Transportation Research Record, 2008, 2074(1):46-51.
[20] 宋小冬, 陶颖, 潘洁雯, 等. 城市街道网络分析方法比较研究:以Space Syntax、sDNA和UNA为例[J]. 城市规划学刊, 2020(2):19-24. SONG X D, TAO Y, PAN J W, et al. A comparison of analytical methods for urban street network:Taking space syntax, sDNA and UNA as examples[J]. Urban Planning Forum, 2020(2):19-24. (in Chinese)
[21] COOPER C. Spatial Design Network Analysis (sDNA) version 4.1 Manual[EB/OL].[2021-03-04]. https://sdna.cardiff.ac.uk/sdna/wp-content/downloads/documentation/manual/sDNA_manual_v4_1_0.
[22] BRUNSDON C, FOTHERINGHAM A S, CHARLTON M E. Geographically weighted regression:A method for exploring spatial nonstationarity[J]. Geographical Analysis, 1996, 28(4):281-298.
[23] 叶显严. 基于地理加权回归的城市出租车客流影响因素分析及建模[D]. 成都:西南交通大学. 2017. YE X Y. The model and facter analysis of effect on the urban taxi ridership based on geographically weighted regression[D]. Chengdu:Southwest Jiaotong University, 2017. (in Chinese)
[24] FOTHERINGHAM A S, YANG W B, KANG W. Multiscale geographically weighted regression (MGWR)[J]. Annals of the American Association of Geographers, 2017, 107(6):1247-1265.
[25] 宋青, 李晓磊, 李猛. 基于OpenStreetMap的城市自行车网建模与多判据路径规划[J]. 交通运输系统工程与信息, 2017, 17(3):143-149. SONG Q, LI X L, LI M. OpenStreetMap-based modeling and multi-criteria routing of urban cycleway network[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(3):143-149. (in Chinese)
[26] 杨逍遥, 王建军, 李国栋, 等. 基于GWR模型的共享单车空间分布影响因素分析[J]. 交通运输研究, 2021, 7(1):81-94. YANG X Y, WANG J J, LI G D, et al. Factors impacting spatial distribution of bike sharing based on GWR model[J]. Transport Research, 2021, 7(1):81-94. (in Chinese)

PDF(10426 KB)

Accesses

Citation

Detail

段落导航

收稿日期	出版日期
2021-10-29	2022-07-15
发布日期
2022-06-16

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

访问统计