In order to explore the spatio-temporal impact mechanism of the nighttime ride-hailing travel demand, this study examines the impact of built environment on ride-hailing demand and its spatial heterogeneity from the local dimension during 20:00-01:00 (the early night) and 01:00-06:00 (the late night), based on the multi-scale geographically weighted regression model. The results indicate that the fitting effect of MGWR model is better than that of geographically weighted regression and ordinary least squares models, and the effect of explanatory variables on the nighttime ride-hailing demand shows significant spatial heterogeneity. During the early night, around the transportation hubs, the bus station has a positive impact on the ride-hailing demand; during the late night, in the north area, the bus station has a strong positive impact on the ride-hailing demand. In the northern and central regions, population density has a positive impact on the ride-hailing demand in both periods, and this impact gradually decreases from the north to the south area. Commercial residence in the northern and central areas shows a positive correlation with the ride-hailing demand during the early night, while this positive effect gradually weakens from the east to the west during the late night. The findings could help deepen the understanding of ride-hailing demand patterns under varying spatio-temporal conditions, and provide scientific basis for optimizing operational strategies and resource allocation.
当前,关于城市居民夜间活动及群体出行行为模式的研究大多集中于城市规划、人文地理以及社会学等领域,研究维度主要聚焦于采用问卷调查和多源数据解析居民夜间活动需求的影响因素及其作用机制。就问卷调查研究范式而言,柴彦威等[5]指出夜间消费活动主要集中在购物、餐饮及娱乐休闲等方面,不同类型的夜间活动呈现出显著的空间分异。王晖等[6]发现增加夜间商户的服务种类和提升夜间出行的便利性能显著增加居民的夜间消费意愿。邵敏等[7]发现年龄、游玩时间、陪伴情况和陪伴对象对夜间出行活动的目的决策产生显著影响。程龙等[8]证实夜间步行距离与年龄、灯光强度、兴趣点(Point of interest,POI)多样性呈正相关,与住宅、交通设施及建筑密度呈负相关。在使用多源数据解析居民夜间出行活动方面,陈宏飞等[9]通过分析西安市用户的微博数据,揭示了居民夜间出行活动在不同时段的分布规律及其时空演变特征。张天洁等[10]基于百度热力、大众点评、POI、豆瓣同城等多源数据辨识城市夜间活力的高值及低洼区域,并在此基础上探讨其动静态耦合特征。程小云等[4]构建了空间计量模型和多尺度地理加权回归模型探讨多种因素对夜间出行需求影响的空间效应。研究结果表明,美食和停车设施密度对夜间出行需求具有显著影响。
针对网约车夜间出行的研究,Tirachini等[11]发现90%的新增Uber行程发生在夜间,且大多数行程的用户是低收入群体。He[12]发现在夜间0~6点时段,周末的网约车司机数量多于工作日,这与周末午夜夜生活更多相关。Hughes等[13]建立了空间误差回归模型研究网约车等待时间与社会经济指标之间的关系。结果表明,在对人口密度和收入差异调整后,区域中少数族裔比例越高,夜间等待时间越长,白天等待时间越短。Wang等[14]使用最小二乘回归(Ordinary least squares,OLS)和地理加权回归(Geographically weighted regression,GWR)模型探究网约车出行与建成环境之间的关系,结果表明,零售店、餐厅以及体育和娱乐服务对晚高峰和深夜时段的出行吸引影响更大。
MaoZhong-gen, LongYan-ni, YeXu. Research progress on night-time economy[J]. Economic Perspectives, 2020(2): 103-116.
[3]
DuJ, RakhaH A, BreuerH. An in-depth spatiotemporal analysis of ride-hailing travel: the Chicago case study[J]. Case Studies on Transport Policy, 2022, 10(1): 118-129.
[4]
QiaoS, YehA. Is ride-hailing a valuable means of transport in newly developed areas under TOD-oriented urbanization in China? Evidence from Chengdu city[J]. Journal of Transport Geography, 2021, 96: No.103183.
ChengXiao-yun, ZhangXue-yu, ShiCheng, et al. Analysis of spatial effect and its heterogeneity on night-time travel based on multi-source data[J]. China Journal of Highway and Transport, 2021, 34(12): 288-301.
ChaiYan-wei, ShangYan-ran. The study on the temporal-spatial characteristics of the consumer activities of Shenzhen residents at night[J]. Geographical Research, 2005, 24(5): 803-810.
WangHui, WangJin-li. The empirical study on night consumption tendency of Beijing residents:Based on Ⅳ-logit regression model[J]. Urban Problems, 2021(2): 75-83.
ShaoMin, WuXu-zhong, HuYi-ming. Study on decision-making of night tourism behavior of residents in medium-sized cities: a case study of Wuhu city in Anhui province[J]. The Journal of Shandong Agriculture and Engineering University, 2020, 37(12): 49-53.
ChengLong, HeZhou-qian, HeZhong-yu, et al. The influence of built environment and lighting on night walking: a case study of Nanjing[J]. Shanghai Urban Planning Review, 2022(4): 109-116.
ChenHong-fei, LiJun-yi, QinChao, et al. Study on spatio-temporal distribution of residents' nocturnal activities of Xi'an based on micro-blog[J]. Human Geography, 2015, 30(3): 57-63.
ZhangTian-jie, SuJing. Research on the spatiotemporal characteristics and planning strategies of "Night Tianjin" vitality based on multi-source data[J]. Modern Urban Research, 2023(12): 59-66.
[19]
TirachiniA, Gomez-LoboA. Does ride-hailing increase or decrease vehicle kilometers traveled (VKT)? A simulation approach for Santiago de Chile[J]. International Journal of Sustainable Transportation, 2020, 14(3): 187-204.
[20]
HeZ. Portraying ride-hailing mobility using multi-day trip order data: a case study of Beijing, China[J]. Transportation Research Part A: Policy and Practice, 2021, 146: 152-169.
[21]
HughesR, MackenzieD. Transportation network company wait times in Greater Seattle, and relationship to socioeconomic indicators[J]. Journal of Transport Geography, 2016, 56: 36-44.
[22]
WangS, NolandR B. Variation in ride-hailing trips in Chengdu, China[J]. Transportation Research Part D: Transport and Environment, 2021, 90: No.102596.
[23]
LiuF, GaoF, YangL, et al. Exploring the spatially heterogeneous effect of the built environment on ride-hailing travel demand: a geographically weighted quantile regression model[J]. Travel Behaviour and Society, 2022, 29: 22-33.
LongXue-qin, ZhaoHuan, ZhouMeng, et al. Spatiotemporal heterogeneity of the impact of built environment in Chengdu on online car-hailing passengers' pick-up points[J]. Scientia Geographica Sinica, 2022, 42(12): 2076-2084.
PanYi-yong, XuJia-cong, YouYi-wen, et al. Multi-scale spatial heterogeneity analysis of influencing factors of ride-hailing travel demand[J]. Journal of Jilin University (Engineering and Technology Edition),2025,55(5) : 1567-1575.
[28]
WuC, KimI, ChungH. The effects of built environment spatial variation on bike-sharing usage: a case study of Suzhou, China[J]. Cities, 2021, 110: No.103063.
[29]
Rey‐DevesaP, BenítezC, PrudencioJ, et al. Volcanic early warning using Shannon entropy: multiple cases of study[J]. Journal of Geophysical Research: Solid Earth, 2023, 128(6): No.e2023JB026684.
[30]
ThompsonE S, SaveynP, DeclercqM, et al. Characterisation of heterogeneity and spatial autocorrelation in phase separating mixtures using Moran's I[J]. Journal of Colloid and Interface Science, 2018, 513: 180-187.
[31]
VandenbulckeG, DujardinC, ThomasI, et al. Cycle commuting in Belgium: spatial determinants and 're-cycling' strategies[J]. Transportation Research Part A: Policy and Practice, 2011, 45(2): 118-137.
[32]
PanY, ChenS, NiuS, et al. Investigating the impacts of built environment on traffic states incorporating spatial heterogeneity[J]. Journal of Transport Geography, 2020, 83: No.102663.
[33]
MoranP A. Notes on continuous stochastic phenomena[J]. Biometrika, 1950, 37(1/2): 17-23.
[34]
WheelerD, TiefelsdorfM. Multicollinearity and correlation among local regression coefficients in geographically weighted regression[J]. Journal of Geographical Systems, 2005, 7(2): 161-187.
[35]
HayesA F, CaiL. Using heteroskedasticity-consistent standard error estimators in OLS regression: an introduction and software implementation[J]. Behavior Research Methods, 2007, 39: 709-722.
[36]
ZhangB, ChenS, MaY, et al. Analysis on spatiotemporal urban mobility based on online car-hailing data[J]. Journal of Transport Geography, 2020, 82: No.102568.
[37]
BrunsdonC, FotheringhamA S, CharltonM E. Geographically weighted regression: a method for exploring spatial nonstationarity[J]. Geographical Analysis, 1996, 28(4): 281-298.
MaShu-hong, LiaoGuo-mei, HuangYan, et al. Heterogeneity of built environment on commuter passenger flow of subway in traffic analysis zones[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(7): 1913-1922.
[40]
FotheringhamA S, YangW, KangW. Multiscale geographically weighted regression (MGWR)[J]. Annals of the American Association of Geographers, 2017, 107(6): 1247-1265.