地理科学进展

地理科学进展 ›› 2023, Vol. 42 ›› Issue (1): 12-26.doi: 10.18306/dlkxjz.2023.01.002

• 研究论文 • 上一篇    下一篇

基于随机森林模型的黄河流域城市建设用地结构时空演化及其驱动机制研究

郭远智1(), 李许红1,2,*()   

  1. 1.中国科学院地理科学与资源研究所，中国科学院区域可持续发展分析与模拟重点实验室，北京 100101
    2.中国科学院大学，北京 100049
  • 收稿日期:2022-06-22 修回日期:2022-09-27 出版日期:2023-01-28 发布日期:2023-03-28
  • 通讯作者: *李许红(2000— )，男，河南南阳人，博士生，主要从事土地利用与区域可持续发展、乡村地域系统及乡村振兴研究。E-mail: lixuhong2479@igsnrr.ac.cn
  • 作者简介:郭远智(1990— )，男，江西南康人，博士，副研究员，主要从事城乡转型与区域可持续发展研究。E-mail: guoyz.16b@igsnrr.ac.cn
  • 基金资助:
    国家自然科学基金项目(42001203)

Spatiotemporal changes of urban construction land structure and driving mechanism in the Yellow River Basin based on random forest model

GUO Yuanzhi1(), LI Xuhong1,2,*()   

  1. 1. Key Laboratory of Regional Sustainable Development Modeling, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2022-06-22 Revised:2022-09-27 Online:2023-01-28 Published:2023-03-28
  • Supported by:
    National Natural Science Foundation of China(42001203)

RichHTML

PDF (PC)

赞

摘要：

城市是区域人口、产业等要素集聚的主要空间载体，系统揭示黄河流域城市建设用地结构演化及其驱动机制对于深入推进黄河流域生态保护和高质量发展战略落实具有重要意义。基于黄河流域2007—2019年城市建设用地数据，论文运用信息熵模型分析了黄河流域城市建设用地结构的时空演化特征，并用随机森林模型探讨其驱动机制。结果表明：① 2007—2019年，黄河流域城市建设用地面积快速增长，年均增速达5.34%，但城市建设用地结构信息熵不断降低，经历了“高位无序—相对稳定—低位有序”的变化过程；② 黄河上、中、下游城市建设用地规模增速依次加大，年均增速分别达到3.91%、5.06%、6.22%；中游地区城市建设用地结构信息熵下降最多，上游地区和下游地区降幅相近；③ 黄河流域各类建设用地主要配置在省会及经济发达城市；黄河流域城市用地结构信息熵存在空间异质性，省会城市及经济发达城市建设用地结构信息熵存在降低趋势，而欠发达城市的信息熵逐步增大；④ 城市用地规模和城市人口规模对城市建设用地结构演化的作用最强，产业结构升级和财政支出规模的作用强度次之，经济发展水平和政策支持力度的作用较小，上中下游影响因子的作用强度存在异质性；⑤ 城市用地规模、城市人口规模、财政支出规模与城市建设用地结构信息熵呈正向变动关系，经济发展水平和产业结构升级与城市建设用地结构信息熵呈负向变动关系，政策支持力度则与城市建设用地结构信息熵呈现出“倒U”型关系。

关键词: 城市建设用地, 信息熵, 随机森林模型, 高质量发展, 黄河流域

Abstract:

Cities are the main spatial carriers for the agglomeration of regional population, industry and other factors, and systematically revealing the evolution of urban construction land structure and its driving mechanism is of great significance for further promoting the implementation of ecological conservation and high-quality development strategy of the Yellow River Basin. Based on the urban construction land data of the Yellow River Basin from 2007 to 2019, the spatiotemporal change characteristics and differentiation patterns of the construction land structure in the basin were analyzed by using the information entropy model, and the formation mechanism of the driving factors was examined by using the random forest model. The results show that: 1) From 2007 to 2019, the area of urban construction land in the Yellow River Basin continued to grow, with an average annual growth rate of 5.34%, but the information entropy of urban construction land structure decreased, and experienced a change process of high-level disorder, relatively stable, and low-level orderly. 2) The growth rate of urban construction land use in the upper, middle, and lower reaches of the Yellow River increased successively, with the annual growth rate reaching 3.91%, 5.06% and 6.22% respectively. The information entropy of urban construction land use structure in the middle reaches of the Yellow River decreased the most, and the decline rates in the upper reaches and lower reaches were similar. 3) All types of construction land in the basin are mainly distributed in provincial capitals and cities in economically developed areas, and there is a clear spatial heterogeneity in the information entropy of urban construction land use structure in the region. The information entropy of urban construction land use structure in provincial capital cities and economically developed cities showed a decreasing trend, while the information entropy of less developed cities gradually increased. 4) The scale of urban land use and the size of urban population have the strongest effect on the change of urban construction land use structure, followed by the intensity of industrial structure upgrading and scale of fiscal expenditure. The role of economic development level and policy support is small, and the intensity of impact of upstream, middle reaches, and downstream influencing factors is heterogeneous. 5) The scale of urban land use, the size of urban population, and the scale of fiscal expenditure showed a positive change relationship with the information entropy of urban construction land use structure, the level of economic development and industrial structure upgrading showed a negative change relationship with the information entropy of urban construction land use structure, and the policy support showed an inverted U-shaped change relationship with the information entropy of urban construction land use structure.

Key words: urban construction land, information entropy, random forest model, high-quality development, Yellow River Basin