地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (6): 1150-1162.doi: 10.12082/dqxxkx.2022.210524

• 地理空间分析综合应用 • 上一篇    下一篇

基于随机森林模型的环渤海地区人口空间化模拟

高雪梅, 杨续超(), 陈柏儒, 林琳   

  1. 浙江大学海洋学院,舟山 316021
  • 收稿日期:2021-08-31 修回日期:2022-01-05 出版日期:2022-06-25 发布日期:2022-08-25
  • 通讯作者: *杨续超(1980— ),男,河南信阳人,教授,主要从事全球变化与灾害风险管理等研究工作。 E-mail: yangxuchao@zju.edu.cn
  • 作者简介:高雪梅(1989— ),女,新疆乌鲁木齐人,硕士生,研究方向为风暴潮灾害风险评估。E-mail: gaoxuemei-11-02@163.com
  • 基金资助:
    国家自然科学基金面上项目(41971019);国家对地观测科学数据中心开放基金项目(NODAOP2020018)

Spatialization of Population in the Bohai Rim Region Using Random Forest Model

GAO Xuemei, YANG Xuchao(), CHEN Bairu, LIN Lin   

  1. Ocean College, Zhejiang University, Zhoushan 316021, China
  • Received:2021-08-31 Revised:2022-01-05 Online:2022-06-25 Published:2022-08-25
  • Contact: YANG Xuchao
  • Supported by:
    National Natural Science Foundation of China(41971019);Open Research Fund of National Earth Observation Data Center(NODAOP2020018)

摘要:

人口空间化数据能够将人口分布更精细地反映在地理空间中,可以为科学研究和政策制定提供更加精细的数据源。本文选取多源遥感数据和兴趣点作为影响环渤海地区人口分布的自变量因子,利用随机森林模型对环渤海地区进行分区密度制图,生成该地区2010年和2020年30 m人口空间化数据,并将结果与WorldPop数据集以及其他地区30 m研究成果进行对比。结果表明:① 本文模拟结果精度整体高于WorldPop数据集10%以上;② 相较于WorldPop数据集,本文人口数据能细致地描述环渤海人口分布的空间异质性;③ 与其他地区30 m研究成果相比,模拟精度也有所提升;④ 遥感建成区数据和兴趣点是环渤海地区人口分布的最重要指示性指标;⑤ 在环渤海地区人口估计方面,社会因素与人口分布有更高的相关性,映射人口分布的主要因素因地区而异。

关键词: 环渤海地区, 随机森林, 影响因素, 人口空间化, 多源数据, 兴趣点数据

Abstract:

The spatialization of population at a fine resolution can reflect the explicit size and detailed distribution of the population. It can provide fine-scale data sources for scientific research and policy making. As a national key area of urbanization development in China's main functional zoning and the intensive area of optimizing the development strategy layout, the Bohai Rim Region is one of the areas with relatively high population density and developed economy in China. In this study, the random forest model was applied to multi-source data and points of interest to estimate the population distribution in impervious areas with a spatial resolution of 30 m in the Bohai region. The estimated results were compared with those of the World Pop dataset and other regional studies with the same spatial resolution. Based on the results, the importance of input variables was analyzed. The results showed that the overall accuracy of the simulation predicted in this study was 10% higher than that of the World Pop dataset. Compared with the World Pop population data, the 30-m resolution of our result provided detailed information of population distributions in the Bohai Rim Region. ?Compared with research results in other regions at the same resolution, the accuracy was partially improved. Built-up areas and points-of-interest were the most important indicators of population distribution in the Bohai Rim. Social factors had a higher correlation with population distribution. The main factors affecting the population distribution varied from region to region.

Key words: Bohai Rim region, random forest, influencing factors, population spatialization, multi-source data, point of interest