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

Abstract

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

CLC Number:

U491.1

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-.

References

[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.

Metrics

Comments

Recommended 0

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), which permits third parties to freely share (i.e., copy and redistribute the material in any medium or format) and adapt (i.e., remix, transform, or build upon the material) the articles published in this journal, provided that appropriate credit is given, a link to the license is provided, and any changes made are indicated. The material may not be used for commercial purposes. For details of the CC BY-NC 4.0 license, please visit: https://creativecommons.org/licenses/by-nc/4.0

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

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Metrics

Comments

Recommended 0