土地利用视角下考虑气温和空气污染的城市公共自行车使用需求预测

doi:10.3976/j.issn.1002-4026.2025090

山东科学

• 交通运输 •

土地利用视角下考虑气温和空气污染的城市公共自行车使用需求预测

王振锋，梅玉爽，王艳红，朱才华*

收稿日期：2025-09-02 修回日期：2025-10-21

基金项目: 河南省自然科学基金(252300420042,242300420029)；湖南省自然科学基金（2024JJ8349）

作者简介：王振锋（1982—），男，博士，教授，研究方向为公路交通规划与管理。E-mail：zfking@henau.edu.cn

*通信作者，朱才华（1995—），男，博士，讲师，研究方向为智能交通管控/客流预测。E-mail：zhucaihua@henau.edu.cn 电话：15738388679

河南农业大学机电工程学院，河南郑州 450002

收稿日期:2025-09-02 接受日期:2025-10-21 上线日期:2026-05-15
通信作者: 朱才华 E-mail:zhucaihua@henau.edu.cn
作者简介:王振锋（1982—），男，博士，教授，研究方向为公路交通规划与管理。E-mail：zfking@henau.edu.cn
基金资助:
河南省自然科学基金(252300420042,242300420029)；湖南省自然科学基金（2024JJ8349）

Demand forecasting for urban public bicycle usage considering temperature and air pollution from a land use perspective

WANG Zhenfeng，MEI Yushuang，WANG Yanhong，ZHU Caihua^*

School of Electrical and Mechanical Engineering， Henan Agricultural University， Zhengzhou 450002, China

Received:2025-09-02 Accepted:2025-10-21 Online:2026-05-15
Contact: ZHU Caihua E-mail:zhucaihua@henau.edu.cn

摘要/Abstract

摘要： 提出了一种融合K-shape时空聚类与改进地理加权回归的混合预测模型，以解决公共自行车使用需求的空间异质性及气象因素的非线性影响问题。考虑借还需求的时序相似性，基于K-shape算法实现站点聚类，同时引入空气质量指数(AQI)和表征非线性效应的气温二次项用于改进地理加权回归模型，有效降低了由气象环境引起的预测误差。基于西安市公共自行车系统运营数据的分析表明：站点可划分为工作区站点、居住区站点、休闲区站点和混合区站点四类集群；气温与使用需求呈倒U型关系，其中工作区站点需求对极端温度更为敏感；空气质量指数对所有站点使用需求均产生抑制效应。研究成果可用于预测不同环境条件下的需求生成率，为优化公共自行车系统调度管理提供决策依据。

关键词: 城市公共自行车, 土地利用, 地理加权回归模型, K-shape聚类, 倒U型效应

Abstract: A hybrid prediction model integrating K-shape spatiotemporal clustering with improved geographically weighted regression is proposed to address the spatial heterogeneity in public bicycle usage demand and the nonlinear effects of meteorological factors. The K-shape algorithm aggregates station features by considering the temporal similarity of borrowing and returning demand patterns. The air quality index (AQI) and a quadratic temperature term characterizing nonlinear effects were incorporated into the improved geographically weighted regression model to reduce prediction errors caused by meteorological conditions. Analysis of operational data from Xi'an’s public bicycle system using the proposed model indicated that stations can be categorized into four distinct clusters: workplace stations, residential stations, recreational stations, and mixed-use stations. Temperature and public bicycle usage demand exhibited an inverted U-shaped relationship, with the demand at workplace stations being the most sensitive to extreme temperatures among all categories of stations. The AQI exerted a suppressive effect on usage demand at all stations. The research findings can be used to predict demand generation rates under various environmental conditions and provide a reference for optimizing the scheduling and management of public bicycle systems.

Key words: urban public bicycles, land use, geographically weighted regression model, K-shape clustering, inverted U-shaped effect

中图分类号:

U491.1

王振锋, 梅玉爽, 王艳红, 朱才华. 土地利用视角下考虑气温和空气污染的城市公共自行车使用需求预测[J]. 山东科学, 0, (): 1-.

WANG Zhenfeng, MEI Yushuang, WANG Yanhong, ZHU Caihua. Demand forecasting for urban public bicycle usage considering temperature and air pollution from a land use perspective[J]. Shandong Science, 0, (): 1-.

参考文献

[1] ZHANG X N, YAN X H, YAN B R, et al. Spatiotemporal heterogeneity of bicycle ridership based on GTWR model[J]. PLoS One, 2025, 20(4): e0320186. DOI:10.1371/journal.pone.0320186.

[2] 王静妍, 张勇. 有桩自行车共享系统吞吐率的近似模型及算法[J]. 山东科学, 2023, 36(6): 74-85. DOI:10.3976/j.issn.1002-4026.2023.06.010.

[3] 杨安安, 韩星玉, 田旷, 等. 基于Stacking集成学习的机场线短时客流预测研究[J]. 山东科学, 2024, 37(4): 112-120. DOI:10.3976/j.issn.1002-4026.20230123.

[4] CHEN A H L, LIANG Y C, CHANG W J, et al. RFM model and K-means clustering analysis of transit traveller profiles: A case study[J]. Journal of Advanced Transportation, 2022, 2022(1): 1108105. DOI:10.1155/2022/1108105.

[5] 罗希, 贾涛. 基于k-Shape的公共自行车系统时空聚类分析[J]. 测绘地理信息, 2023, 48(4): 122-125. DOI:10.14188/j.2095-6045.2021034.

[6] OSKARBSKI J, BIRR K, ŻARSKI K. Bicycle traffic model for sustainable urban mobility planning[J]. Energies, 2021, 14(18): 5970. DOI:10.3390/en14185970.

[7] PAZDAN S, KIEC M, D’AGOSTINO C. Impact of environment on bicycle travel demand—Assessment using bikeshare system data[J]. Sustainable Cities and Society, 2021, 67: 102724. DOI:10.1016/j.scs.2021.102724.

[8] HE M J, MA X W, WANG J B, et al. Geographically weighted multinomial logit models for modelling the spatial heterogeneity in the bike-sharing renting-returning imbalance: A case study on Nanjing, China[J]. Sustainable Cities and Society, 2022, 83: 103967. DOI:10.1016/j.scs.2022.103967.

[9] DU M Y, LI Z C, LI X F, et al. Understanding the spatial variation of integrated use of ride-hailing services with the metro[J]. Journal of Advanced Transportation, 2024, 2024(1): 9210901. DOI:10.1155/atr/9210901.

[10] 王涛, 戢晓峰. 基于GWR的建成环境对公共自行车出行模式的影响分析[J]. 合肥工业大学学报(自然科学版), 2023, 46(7): 963-971. DOI:10.3969/j.issn.1003-5060.2023.07.016.

[11] ZHU C H, SUN X L, LI Y R, et al. A hybrid neural network for urban rail transit short-term flow prediction[J]. The Journal of Supercomputing, 2024, 80(16): 24297-24323. DOI:10.1007/s11227-024-06331-2.

[12] 黄勇, 赵航, 许旺土, 等. 建成环境与高收入群体出行模式关系研究[J]. 公路交通科技, 2022, 39(1): 106-113. DOI:10.3969/j.issn.1002-0268.2022.01.014.

[13] JUNG J, JUNG D. Analysis of factors affecting the extra journey time of public bicycles[J]. Sustainability, 2023, 15(18): 13804. DOI:10.3390/su151813804.

[14] HU B B, ZHONG Z F, ZHANG Y L, et al. Understanding the influencing factors of bicycle-sharing demand based on residents’ trips[J]. Physica A: Statistical Mechanics and Its Applications, 2022, 586: 126472. DOI:10.1016/j.physa.2021.126472.

[15] FAN Y C, PALACIOS J, ARCAYA M, et al. Health perception and commuting choice: A survey experiment measuring behavioral trade-offs between physical activity benefits and pollution exposure risks[J]. Environmental Research Letters, 2021, 16(5): 054026. DOI:10.1088/1748-9326/abecfd.

[16] GIANNELLA C R. Instability results for Euclidean distance, nearest neighbor search on high dimensional Gaussian data[J]. Information Processing Letters, 2021, 169: 106115. DOI:10.1016/j.ipl.2021.106115.

[17] 朱才华, 李岩, 孙晓黎, 等. 考虑土地利用的城市公共自行车需求预测[J]. 华南理工大学学报(自然科学版), 2022, 50(3): 9-20. DOI:10.12141/j.issn.1000-565X.210083.

[18] 陈红, 陈恒瑞, 史转转, 等. 公共自行车使用时空特性挖掘及租还需求预测[J]. 交通运输系统工程与信息, 2021, 21(2): 238-244. DOI:10.16097/j.cnki.1009-6744.2021.02.034.

[19] 申彦, 谭昕. 基于地理加权回归模型的共享电动汽车租赁需求影响因素分析[J]. 物流科技, 2024, 47(24): 57-62. DOI:10.13714/j.cnki.1002-3100.2024.24.012.

[20] SUKHOV A, OLSSON L E, FRIMAN M. Necessary and sufficient conditions for attractive public Transport: Combined use of PLS-SEM and NCA[J]. Transportation Research Part A: Policy and Practice, 2022, 158: 239-250. DOI:10.1016/j.tra.2022.03.012.

[21] ZHONG S P, WANG Z, WANG Q Z, et al. Exploring the spatially heterogeneous effects of urban built environment on road travel time variability[J]. Journal of Transportation Engineering, Part A: Systems, 2021, 147: 04020142. DOI:10.1061/jtepbs.0000469.

[22] WANG C. Non-stationary modeling of road-curve crash frequency with geographically weighted regression [D]. West Lafayette: Purdue University, 2021.

[23] 张上要, 宋雄, 顷宏利, 等. 基于VIF-GBRT-MC模型的日径流预测[J]. 中国农村水利水电, 2024(9): 204-210. DOI:10.12396/znsd.240538.

[24] LEMMERZ T, HERLÉ S, BLANKENBACH J. Geostatistics on real-time geodata streams—An extended spatiotemporal moran’s I index with distributed stream processing technologies[J]. ISPRS International Journal of Geo-Information, 2023, 12(3): 87. DOI:10.3390/ijgi12030087.

[25] 黎鹏. 基于天气因素的共享单车骑行量预测——以摩拜为例[D]. 成都: 电子科技大学, 2020. DOI:10.27005/d.cnki.gdzku.2020.003789.

[26] ZHAO P J, YUAN D D, ZHANG Y X. The public bicycle as a feeder mode for metro commuters in the megacity Beijing: Travel behavior, route environment, and socioeconomic factors[J]. Journal of Urban Planning and Development, 2022, 148: 04021064. DOI:10.1061/(asce)up.1943-5444.0000785.

[27] WANG X, XUE R, LU M, et al. Riders under the heat: Exploring the impact of extreme heat on the integration of bike-sharing and public transportation in Shenzhen, China[J]. ISPRS International Journal of Geo-Information, 2024, 13(12): 438. DOI:10.3390/ijgi13120438.

土地利用视角下考虑气温和空气污染的城市公共自行车使用需求预测

Demand forecasting for urban public bicycle usage considering temperature and air pollution from a land use perspective

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	吕欣怡，王慧，袁兴中，孙小银，孙晓芳，孙晋芳. 兖州矿区土地利用变化对生态系统服务价值的影响[J]. 山东科学, 2018, 31(1): 88-.
[2]	武红智. 济南市土地利用与覆被变化特征分析[J]. J4, 2010, 23(5): 78-80.