机器学习与社区生活圈规划：应用框架与议题*
Machine Learning and Urban Community Life Circle Planning: Application Framework and Research Topics
张文佳
北京大学深圳研究生院 城市规划与设计学院 助理教授，博士生导师
柴彦威（通信作者）
北京大学城市与环境学院 教授，博士生导师
罗雪瑶
北京大学深圳研究生院 城市规划与设计学院 硕士研究生
李春江
北京大学城市与环境学院 博士研究生
摘要: 社区生活圈规划已成为学术研究与规划实践的热点议题和我国国土空间规划体系创新的重要组成部分。首先，从社区生活圈的概念和内涵界定、空间范围划分方法与设施评价和优化等3个方面对现有规划研究进行综述，并提出社区生活圈规划研究在理论、技术方法和实证方面所面临的挑战。对于居民日常行为的关注是社区生活圈规划的主要特点，因此梳理机器学习方法应用于时空行为研究的前沿与热点主题，包括时空行为预测、时空行为模式挖掘与时空行为和建成环境的非线性关系等。其次，提出机器学习方法在社区生活圈规划研究中的应用框架，以及在社区生活圈物质空间、社区交往生活圈和安全生活圈3个方面的创新议题。最后，以“基于时空行为需求预测的社区生活圈划分方法”及“基于非线性阈值效应的社区生活圈设施配置规划”两个研究案例阐释机器学习方法在社区生活圈物质空间规划研究的应用。
Abstract: Community life circle planning has become the frontier and hot spot of academic research and planning practice, and it is also an important part of the innovation of China's territory spatial planning system. We first review the existing community life circle planning research from three aspects: the definition and connotation, the spatial scope delineation methods, and the evaluation and optimization of facilities. We conclude the theoretical, methodological and empirical challenges facing by current research. One of the main features of community life circle planning is the focus on residential daily lives. Therefore, we summarize the frontier and hot topics of the application of machine learning methods in the studies of spatiotemporal behavior, including spatiotemporal behavior prediction, space-time behavior patterns mining, and the non-linear relationships of space-time behavior and built environment. Then, we propose the framework of the application of machine learning techniques in community life circle planning research and the innovation topics, including community life circle physical space, community social interaction life circle and community safe life circle. Finally, we take two examples to illustrate the innovative application of machine learning methods in community life circle planning research, which are "community life circle delineation method based on space-time behavior demand prediction" and "community life circle facility planning based on non-linear threshold effect".
关键词：社区生活圈；机器学习；时空行为；决策树；非线性效应
Keyword: community life circle; machine learning; space-time behavior; decision tree; non-linear effect
中图分类号：TU981
文献标识码: A
资金资助
国家自然科学基金青年项目 “机器学习算法辅助下城市居民多尺度移动行为决策过程与空间优化研究” 41801158
柴彦威，李春江. 城市生活圈规划：从研究到实践[J]. 城市规划，2019，43（5）：9-16，60.
CHAI Yanwei, LI Chunjiang. Urban life cycle planning: from research to practice[J]. City Planning Review, 2019, 43(5): 9-16, 60.
柴彦威，张雪，孙道胜. 基于时空间行为的城市生活圈规划研究——以北京市为例[J]. 城市规划学刊，2015（3）：61-69.
CHAI Yanwei, ZHANG Xue, SUN Daosheng. A study on life circle based on space time behavioural analysis: a case study of Beijing[J]. Urban Planning Forum, 2015(3): 61-69.
程蓉. 以提品质促实施为导向的上海15分钟社区生活圈的规划和实践[J]. 上海城市规划，2018（2）：84-88.
CHENG Rong. Planning and practice of a 15-minute community living circle in Shanghai guided by promoting implementation[J]. Shanghai Urban Planning Review, 2018(2): 84-88.
刘云刚，侯璐璐. 基于生活圈的城乡管治理论研究[J]. 上海城市规划，2016（2）：1-7.
LIU Yungang, HOU Lulu. Study on urban-rural governance based on a life circle approach[J]. Shanghai Urban Planning Review, 2016(2): 1-7.
赵宝静，奚文沁，吴秋晴，等. 塑造韧性社区共同体：生活圈的规划思考与策略[J]. 上海城市规划，2020（2）：141-149.
ZHAO Baojing, XI Wenqin, WU Qiuqing, et al. Shaping a resilient community: planning methods for the community life circle[J]. Shanghai Urban Planning Review, 2020(2): 141-149.
王兰，李潇天，杨晓明. 健康融入15分钟社区生活圈：突发公共卫生事件下的社区应对[J]. 规划师，2020，36（6）：102-106，120.
WANG Lan, LI Xiaotian, YANG Xiaoming. Health in 15-minute life sphere: community response to public health emergency[J]. Planners, 2020, 36(6): 102-106, 120.
上海市规划和自然资源局. 上海市15分钟社区生活圈规划导则[S]. 2016.
Shanghai Urban Planning and Natural Resources Bureau. Shanghai planning guidance of 15-minute community-life circle[S]. 2016.
韩增林，李源，刘天宝，等. 社区生活圈公共服务设施配置的空间分异分析——以大连市沙河口区为例[J]. 地理科学进展，2019，38（11）：1-11.
HAN Zenglin, LI Yuan, LIU Tianbao, et al. Spatial differentiation analysis of public service facility configuration in community living circle: a case study of Dalian Shahekou District[J]. Progress in Geography, 2019, 38(11): 1-11.
郭嵘，李元，黄梦石. 哈尔滨15分钟社区生活圈划定及步行网络优化策略[J]. 规划师，2019，35（4）：18-24.
GUO Rong, LI Yuan, HUANG Mengshi. Research on optimization strategy of walking network in 15-minute community life circle of Harbin[J]. Planners, 2019, 35(4): 18-24.
崔真真，黄晓春，何莲娜，等. 基于POI数据的城市生活便利度指数研究[J]. 地理信息世界，2016，23（3）：27-33.
CUI Zhenzhen, HUANG Xiaochun, HE Lianna, et al. Study on urban life convenience index based on POI data[J]. Geomatics World, 2016, 23(3): 27-33.
萧敬豪，周岱霖，胡嘉佩. 基于决策树原理的社区生活圈测度与评价方法——以广州市番禺区为例[J]. 规划师，2018，34（3）：91-96.
XIAO Jinghao, ZHOU Dailin, HU Jiapei. Evaluation method of community life-cycle based on decision tree theory: Panyu District of Guangzhou[J]. Planners, 2018, 34(3): 91-96.
孙道胜，柴彦威，张艳. 社区生活圈的界定与测度：以北京清河地区为例[J]. 城市发展研究，2016，23（9）：1-9.
SUN Daosheng, CHAI Yanwei, ZHANG Yan. The definition and measurement of community life circle: a case study of Qinghe Area in Beijing[J]. Urban Development Studies, 2016, 23(9): 1-9.
柴彦威，李春江，夏万渠，等. 城市社区生活圈划定模型——以北京市清河街道为例[J]. 城市发展研究，2019，26（9）：1-9.
CHAI Yanwei, LI Chunjiang, XIA Wanqu, et al. Study on the delineation model of urban community life circle: based on Qinghe District in Haidian District, Beijing[J]. Urban Development Studies, 2019, 26(9): 1-9.
王德，傅英姿. 手机信令数据助力上海市社区生活圈规划[J]. 上海城市规划，2019（6）：23-29.
WANG De, FU Yingzi. Mobile signaling data helps Shanghai community life circle planning[J]. Shanghai Urban Planning Review, 2019(6): 23-29.
吴夏安，徐磊青，仲亮. 《城市居住区规划设计标准》中15分钟生活圈关键指标讨论[J]. 规划师，2020，36（8）：33-40.
WU Xiaan, XU Leiqing, ZHONG Liang. Key indicators of 15-minute life circle in the Standard for Urban Residential Area Planning and Design[J]. Planners, 2020, 36(8): 33-40.
孙道胜，柴彦威. 城市社区生活圈体系及公共服务设施空间优化——以北京市清河街道为例[J]. 城市发展研究，2017，24（9）：7-14，25.
SUN Daosheng, CHAI Yanwei. Study on the urban community life sphere system and the optimization of public service facilities: a case study of Qinghe Area in Beijing[J]. Urban Development Studies, 2017, 24(9): 7-14, 25.
杜伊，金云峰. 社区生活圈的公共开放空间绩效研究——以上海市中心城区为例[J]. 现代城市研究，2018（5）：101-108.
DU Yi, JIN Yunfeng. Performance evaluation of public open spacein community life circle level: a case study of downtown of Shanghai[J]. Modern Urban Research, 2018(5): 101-108.
魏伟，洪梦谣，谢波. 基于供需匹配的武汉市15分钟生活圈划定与空间优化[J]. 规划师，2019，35（4）：11-17.
WEI Wei, HONG Mengyao, XIE Bo. Demand-supply matching oriented 15-minute community life circle demarcation and spatial optimization[J]. Planners, 2019, 35(4): 11-17.
周岱霖，黄慧明. 供需关联视角下的社区生活圈服务设施配置研究——以广州为例[J]. 城市发展研究，2019，26（12）：1-5，18.
ZHOU Dailin, HUANG Huiming. Community life cycle public facility configuration study based on demand-supply correlation: a case study of Guangzhou[J]. Urban Development Studies, 2019, 26(12): 1-5, 18.
周弦. 15分钟社区生活圈视角的单元规划公共服务设施布局评估：以上海市黄浦区为例[J]. 城市规划学刊，2020（1）：57-64.
ZHOU Xian. Assessment of public service facility layout of unit planning from the perspective of 15-minute life circle: a case study of Huangpu District, Shanghai[J]. Urban Planning Forum, 2020(1): 57-64.
WENG M, DING N, LI J, et al. The 15-minute walkable neighborhoods: measurement, social inequalities and implications for building healthy communities in urban China[J]. Journal of Transport & Health, 2019, 13: 259-273.
赵万民，方国臣，王华. 生活圈视角下的住区适老化步行空间体系构建[J]. 规划师，2019，35（17）：69-78.
ZHAO Wanmin, FANG Guochen, WANG Hua. Creating a senior friendly pedestrian space system from life circle viewpoint[J]. Planners, 2019, 35(17): 69-78.
ZHANG F, LI D, AHRENTZEN S, et al. Assessing spatial disparities of accessibility to community-based service resources for Chinese older adults based on travel behavior: a city-wide study of Nanjing, China[J]. Habitat International, 2019, 88: 101984.
柴彦威，李春江，张艳. 社区生活圈的新时间地理学研究框架[J]. 地理科学进展，2020，39（12）：1961-1971.
CHAI Yanwei, LI Chunjiang, ZHANG Yan. A new time-geography research framework of community life circle[J]. Progress in Geography, 2020, 39(12): 1961-1971.
陆锋，刘康，陈洁. 大数据时代的人类移动性研究[J]. 地球信息科学学报，2014，16（5）：665-672.
LU Feng, LIU Kang, CHEN Jie. Research on human mobility in big data era[J]. Journal of Geo-Information Science, 2014, 16(5): 665-672.
MCFADDEN D. Conditional logit analysis of qualitative choice behavior[M]. Pittsburgh: Academic Press, 1973.
XIE C, LU J, PARKANY E. Work travel mode choice modeling with data mining: decision trees and neural networks[J]. Transportation Research Record, 2003, 1854(1): 50-61.
OMRANI H, CHARIF O, GERBER P, et al. Prediction of individual travel mode with evidential neural network model[J]. Transportation Research Record, 2013, 2399(1): 1-8.
LHÉRITIER A, BOCAMAZO M, DELAHAYE T, et al. Airline itinerary choice modeling using machine learning[J]. Journal of Choice Modelling, 2019, 31: 198-209.
WANG F, ROSS C L. Machine learning travel mode choices: comparing the performance of an extreme gradient boosting model with a multinomial logit model[J]. Transportation Research Record, 2018, 2672(47): 35-45.
ZHANG Y, XIE Y. Travel mode choice modeling with support vector machines[J]. Transportation Research Record, 2008, 2076(1): 141-150.
ZHAO X, YAN X, YU A, et al. Prediction and behavioral analysis of travel mode choice: a comparison of machine learning and logit models[J]. Travel Behaviour and Society, 2020, 20: 22-35.
LINDNER A, PITOMBO C S, CUNHA A L. Estimating motorized travel mode choice using classifiers: an application for high-dimensional multicollinear data[J]. Travel Behaviour and Society, 2017, 6: 100-109.
KOUSHIK A N, MANOJ M, NEZAMUDDIN N. Machine learning applications in activity-travel behaviour research: a review[J]. Transport Reviews, 2020, 40(3): 288-311.
ASHBROOK D, STARNER T. Using GPS to learn significant locations and predict movement across multiple users[J]. Personal Ubiquitous Computing, 2003, 7(5): 275-286.
PATTERSON D J, LIAO L, FOX D, et al. Inferring high-level behavior from low-level sensors[C]//Proceedings of the International Conference on Ubiquitous Computing. Heidelberg: Springer, 2003.
LIAO L, PATTERSON D J, FOX D, et al. Learning and inferring transportation routines[J]. Artificial Intelligence, 2007, 171(5-6): 311-331.
SIMMONS R, BROWNING B, ZHANG Y, et al. Learning to predict driver route and destination intent[C]//Proceedings of the 2006 IEEE Intelligent Transportation Systems Conference. New York: IEEE, 2006.
MANASSEH C, SENGUPTA R. Predicting driver destination using machine learning techniques [C]//Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013). New York: IEEE, 2013.
SHOU Z, DI X. Similarity analysis of frequent sequential activity pattern mining[J]. Transportation Research Part C: Emerging Technologies, 2018, 96: 122-143.
HUANG Q, WONG D W S. Modeling and visualizing regular human mobility patterns with uncertainty: an example using Twitter data[J]. Annals of the Association of American Geographers, 2015, 105(6): 1179-1197.
WANG Y, YALCIN A, VANDEWEERD C. An entropy-based approach to the study of human mobility and behavior in private homes[J]. PLoS one, 2020, 15(12): e0243503.
ZHANG W, THILL J-C. Detecting and visualizing cohesive activity-travel patterns: a network analysis approach[J]. Computers, Environment and Urban Systems, 2017, 66: 117-129.
DING C, CAO X J, NÆSS P. Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo[J]. Transportation Research Part A: Policy and Practice, 2018, 110: 107-117.
TAO T, WU X, CAO J, et al. Exploring the nonlinear relationship between the built environment and active travel in the twin cities[J]. Journal of Planning Education and Research, 2020, 82: 102560.
DING C, CAO X, DONG M, et al. Non-linear relationships between built environment characteristics and electric-bike ownership in Zhongshan, China[J]. Transportation Research Part D: Transport and Environment, 2019, 75: 286-296.
ZHANG W, ZHAO Y, CAO X J, et al. Nonlinear effect of accessibility on car ownership in Beijing: pedestrian-scale neighborhood planning[J]. Transportation Research Part D: Transport and Environment, 2020, 86: 102445.
PARK Y M, KWAN M-P. Beyond residential segregation: a spatiotemporal approach to examining multi-contextual segregation[J]. Computers, Environment and Urban Systems, 2018, 71: 98-108.
李彦熙，柴彦威，塔娜. 从防灾生活圈到安全生活圈——日本经验与中国思考[J/OL]. 国际城市规划：1-14 [2021-07-09]. http://kns.cnki.net/kcms/detail/11.5583.TU.20210312.1448.005.html.
LI Yanxi, CHAI Yanwei, TA Na. From disaster precaution life circle to safety life circle: experience and inspiration from Japan[J/OL]. Urban Planning International: 1-14 [2021-07-09]. http://kns.cnki.net/kcms/detail/11.5583.TU.20210312.1448.005.html.
LI C, XIA W, CHAI Y. Delineation of an urban community life circle based on a machine learning estimation of spatiotemporal behavioral demand[J]. Chinese Geographical Science, 2021, 31(1): 27-40.
EWING R, CERVERO R. Travel and the built environment: a meta-analysis[J]. Journal of the American Planning Association, 2010, 76(3): 265-294.
