| 171 | 0 | 56 |
| 下载次数 | 被引频次 | 阅读次数 |
从宏观视角对建成环境指标进行测度，既难以充分挖掘人群对街道空间的感知，也难以有效促进街道活力。以成都市小街区建设为例，撷取街道形态、内容和情感3个维度的特征指标，通过XGBoost机器学习方法结合SHAP可解释模型，探究小街区街道感知与街道活力的非线性关系。结果表明：（1）街道形态感知是促进小街区街道活力的主导因素；（2）街道感知因素对活力水平存在非线性影响且阈值效应明显；（3）街道功能密度和高宽比显著影响街道活力，且在交互作用中占主导地位。旨在为以精细化提升街道活力为导向的小街区建设提供研讨。
Abstract：It is difficult to fully tap people's perception of street space and effectively promote the enhancement of street vitality by measuring built environment indicators from a macro perspective. Taking the construction of small blocks in Chengdu as an example, the characteristics of street form, content, and emotion were extracted, and the nonlinear relationship between street perception and street vitality was explored through XGBoost machine learning method combined with SHAP interpretable model. The results show that:(1) Street shape perception is the dominant factor to promote the street vitality of small blocks;(2) The street perception factor has nonlinear influence on the vitality level and the threshold effect is obvious;(3) Street functional density and aspect ratio significantly affect street vitality, and play a dominant role in the interaction. This paper aims to provide reference for the construction of small blocks guided by the refinement and enhancement of street vitality for discussion.
[1]袁奇峰,李如如,潘卓鸿.小街区空间公共性有效供给机制研究:以广州珠江新城居住街坊为例[J].规划师,2022,38(9):79-87.
[2]沈莉芳,陈诚.“小街区规制”:“街区制”的成都实践[J].规划师,2017,33(7):26-30.
[3]王润娴,毛键源.活力街区的改造模式和实施路径研究:以巴塞罗那“超级街区”计划为例[J].国际城市规划,2024,39(1):117-126.
[4]WU W S, MA Z Y, GUO J H, et al. Evaluating the Effects of Built Environment on Street Vitality at the City Level:An Empirical Research Based on Spatial Panel Durbin Model[J]. International Journal of Environmental Research and Public Health, 2022,19(3):1664.
[5]汪成刚,王波,王琪智,等.城市活力与建成环境的非线性关系和阈值效应研究:以广州市中心城区为例[J].地理科学进展,2023,42(1):79-88.
[6]龙瀛,周垠.街道活力的量化评价及影响因素分析:以成都为例[J].新建筑,2016(1):52-57.
[7]高巍,贾梦涵,赵玫,等.街道空间研究进展与量化测度方法综述[J].城市规划,2022,46(3):106-114.
[8]塔娜,曾屿恬,朱秋宇,等.基于大数据的上海中心城区建成环境与城市活力关系分析[J].地理科学,2020,40(1):60-68.
[9]叶宇,张昭希,张啸虎,等.人本尺度的街道空间品质测度:结合街景数据和新分析技术的大规模、高精度评价框架[J].国际城市规划,2019,34(1):18-27.
[10]司睿,林姚宇,肖作鹏,等.基于街景数据的建成环境与街道活力时空分析:以深圳福田区为例[J].地理科学,2021,41(9):1536-1545.
[11]WU C, YE Y, GAO F Z, et al. Using Street View Images to Examine the Association Between Human Perceptions of Locale and Urban Vitality in Shenzhen, China[J]. Sustainable Cities and Society, 2023, 88:104291.
[12]MA Z. Deep Exploration of Street View Features for Identifying Urban Vitality:A Case Study of Qingdao City[J].International Journal of Applied Earth Observation and Geoinformation, 2023,123:103476.
[13]曹越皓,杨培峰,庄凯月.基于机器学习的历史空间感知测度研究[J].规划师,2021,37(23):67-73.
[14]王林森,郑重,周素红,等.基于街景感知的城市空间品质对空间活力的影响作用研究[J].规划师,2022,38(3):68-75.
[15]MA S, WANG B Y, LIU W, et al. Assessment of Street Space Quality and Subjective Well-being Mismatch and Its Impact,Using Multi-source Big Data[J].Cities, 2024,147:104797.
[16]杨东峰,王晓萌,韩瑞娜.建成环境对街道活力的非线性影响和交互效应:以沈阳为例[J].城市规划学刊,2023(5):93-102.
[17]狄迪,蒋映红,叶丹,等.新城市科学支持下的城市街道空间品质综合评价:以上海市中心城区为例[J].规划师,2021,37(16):5-12.
[18]CHENG J K, HU L Y, ZHANG J Y, et al. Understanding the Synergistic Effects of Walking Accessibility and the Built Environment on Street Vitality in High-Speed Railway Station Areas[J]. Sustainability, 2024,16(13):5524.
[19]WANG Z Y, WANG X Z, LIU Y D, et al. Identification of 71 Factors Influencing Urban Vitality and Examination of Their Spatial Dependence:A Comprehensive Validation Applying Multiple Machine-learning Models[J]. Sustainable Cities and Society, 2024,108:105491.
[20]达传胜.“密路网、小街区”模式下城市街区活力提升策略研究[D].西安:西安建筑科技大学,2020.
[21]钮心毅,吴莞姝,李萌.基于LBS定位数据的建成环境对街道活力的影响及其时空特征研究[J].国际城市规划,2019,34(1):28-37.
[22]郭鑫,陈宏飞,杨喜平.建成环境对城市不同年龄群体活力的时空异质性影响研究[J].地理与地理信息科学,2022,38(1):63-70,78.
[23]闵忠荣,丁帆.基于百度热力图的街道活力时空分布特征分析:以江西省南昌市历史城区为例[J].城市发展研究,2020,27(2):31-36.
[24]陈锦棠,邓明亮,梁斌注,等.建成街道活力时空特征及提质策略研究:以广州市建设新村为例[J].规划师,2021,37(16):13-21.
[25]方智果,王冉冉,刘聪,等.基于多源数据的街道环境对个体安全感的影响研究[J].上海城市规划,2023(2):109-115.
[26]TANG J X, LONG Y. Measuring Visual Quality of Street Space and Its Temporal Variation:Methodology and Its Application in the Hutong Area in Beijing[J]. Landscape and Urban Planning, 2019,191:103436.
[27]YAO Y, LIANG Z, YUAN Z, et al.A Human-machine Adversarial Scoring Framework for Urban Perception Assessment Using Street-view Images[J]. International Journal of Geographical Information Science, 2019,33(12):2363-2384.
[28]YAO Y, WANG J L, HONG Y, et al. Discovering the Homogeneous Geographic Domain of Human Perceptions from Street View Images[J]. Landscape and Urban Planning, 2021,212:104125.
[29]胡一可,张天霖,王磊,等.景观服务视角下城市街区感知测度及空间分布特征[J].风景园林,2022,29(10):45-52.
[30]CHEN T Q,GUESTRIN C. XGBoost:A Scalable Tree Boosting System[C]//Kdd'16:Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. 2016:785-794.
[31]何静娟.基于XGBoost机器学习的上海市城市热环境影响机制与尺度效应研究[D].杭州:浙江农林大学,2024.
[32]王梓蒙,刘艳芳,罗璇,等.基于多源数据的城市活力与建成环境非线性关系研究:以双休日武汉市主城区为例[J].地理科学进展, 2023,42(4):716-729.
[33]JACOBS J. The Death and Life of American cities[M]. New York:Random House, 1961.
[34]吴莞姝,马子迎,郭金函,等.建成环境对街道活力的非线性效应:基于XGBoost模型的多源大数据分析[J].中国园林,2022,38(12):82-87.
基本信息:
DOI：10.19940/j.cnki.1008-0422.2025.12.010
中图分类号:TP181;TP391.41;TU984.113
引用信息:
[1]汪晓春,张继刚.基于XGBoost-SHAP模型的街道感知测度与活力影响研究——以成都小尺度街区为例[J].中外建筑,2025,No.296(12):53-59.DOI:10.19940/j.cnki.1008-0422.2025.12.010.
2024-12-25
2024
2025-02-05
2025
2
2025-12-28
2025-12-28