大数据模型驱动下滨水空间活力影响机制研究 ——以义乌市为例
作者:
作者单位:

作者简介:

通讯作者:

基金项目:

义乌市住房和城乡建设局委托项目“义乌市公园体系规划(2023–2035年)”(编号:23174)


Research on the Influencing Mechanisms of Waterfront Space Vitality Driven by Big Data Modeling: A Case Study of Yiwu City
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    义乌市素有“商贸之都”美誉,随着城市化进程不断加快,其江沿岸功能已由单一生产功能转型为集生产、生活、生态功能于一体的“三生空间”,市民休闲娱乐需求愈加突显。为助力义乌加快城市更新,实现从“增量扩张”到“存量优化”的转型,以义乌市滨水空间为对象,以时空活力特征为切入点,从人群用户画像、空间形态指标、生态环境要素和城市人文经济4个评价维度着手,拆解不同指标要素值并分析空间分布形态特征,建立23项滨水空间活力影响因子评价指标体系;基于位置服务的全龄段人群数据、手机信令和社交媒体打卡等多源大数据,结合最小二乘法筛选影响因子,应用地理加权回归模型分析空间异质性及基于机器深度学习的随机森林模型进行因子重要性排序,通过机器学习模型对SHAP因子重要性可视化,系统解析滨水空间活力的时空分异规律及其驱动影响机制。分析结果表明交通站点密度、功能混合度、岸线可达性和开发强度,这些核心驱动因子在滨水空间活力表现上呈现正相关结果,景点丰富度和房价呈现负相关结果,并在不同区域呈现空间异质性。大数据模型驱动下的活力影响机制研究成果,能够为未来城市滨水空间规划提供实证支持与建议,针对城市滨水空间规划设计提出建议,以期为未来城市滨水空间活力提升提供理论支持。

    Abstract:

    Yiwu City, known as the “City of Commerce”, has experienced rapid urbanization, transforming its riverside areas from solely production-focused functions to a “three-dimensional space” that integrates production, living, and ecological functions. This shift has led to increasing demand for recreational and leisure spaces. To support Yiwu’s urban renewal and its shift from “incremental expansion” to “stock optimization”, this study focuses on the city’s waterfront areas. It examines four key factors: user demographics, spatial layout, ecological environment, and urban human-economic factors, breaking down these elements to analyze spatial distribution and vitality. A 23-item evaluation index system for waterfront vitality is established. Using big data sources such as Location-Based Services (LBS), mobile signals, and social media check-ins, combined with Ordinary Least Squares (OLS) for factor selection and Geographically Weighted Regression (GWR) to assess spatial differences, the study also uses a Random Forest model based on deep learning for factor importance ranking. The Shapley Additive Explanations (SHAP) model visualizes these results. The analysis reveals that factors such as transportation node density, functional diversity, shoreline accessibility, and development intensity are positively correlated with waterfront vitality. In contrast, the richness of tourist attractions and property prices are negatively correlated. The study also finds spatial variation across different regions. These findings provide empirical support and recommendations for future waterfront planning, as well as theoretical insights for enhancing urban waterfront vitality.

    参考文献
    相似文献
    引证文献
引用本文

金玥,陈楚文. 大数据模型驱动下滨水空间活力影响机制研究 ——以义乌市为例 [J]. 园林, 2025, 42 (7): 68-78. 复制

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2025-07-11
  • 出版日期: