Mapping the Time-Series of Essential Urban Land Use Categories in China: A Multi-Source Data Integration Approach

被引:0
|
作者
Tian, Tian [1 ]
Yu, Le [1 ,2 ,3 ]
Tu, Ying [4 ]
Chen, Bin [5 ,6 ,7 ]
Gong, Peng [2 ,6 ,8 ]
机构
[1] Tsinghua Univ, Inst Global Change Studies, Dept Earth Syst Sci, Minist Educ Key Lab Earth Syst Modeling, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Dept Earth Syst Sci, Minist Educ, Ecol Field Stn East Asian Migratory Birds, Beijing 100084, Peoples R China
[3] Tsinghua Univ, Xian Inst Surveying, Mapping Joint Res Ctr Next Generat Smart Mapping, Dept Earth Syst Sci, Beijing 100084, Peoples R China
[4] Cornell Univ, Dept Global Dev, Ithaca, NY 14850 USA
[5] Univ Hong Kong, Fac Architecture, Div Landscape Architecture, Future Urban & Sustainable Environm FUSE Lab, Hong Kong 999077, Peoples R China
[6] Univ Hong Kong, Urban Syst Inst, Hong Kong 999077, Peoples R China
[7] Univ Hong Kong, Musketeers Fdn Inst Data Sci, Hong Kong 999077, Peoples R China
[8] Univ Hong Kong, Dept Geog, Hong Kong 999077, Peoples R China
基金
中国国家自然科学基金;
关键词
urban land use; random forest; mapping; local climate zone; image segmentation; point of interest; LOCAL CLIMATE ZONES; POINTS-OF-INTEREST; COVER CLASSIFICATION; SPATIAL-RESOLUTION; NIGHTTIME LIGHT; REAL-TIME; FROM-GLC; CITY; SATELLITE; IMAGERY;
D O I
10.3390/rs16173125
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate, detailed, and long-term urban land use mapping is crucial for urban planning, environmental assessment, and health evaluation. Despite previous efforts, mapping essential urban land use categories (EULUCs) across multiple periods remains challenging, primarily due to the scarcity of enduring consistent socio-geographical data, such as the widely used Point of Interest (POI) data. Addressing this issue, this study presents an experimental method for mapping the time-series of EULUCs in Dalian city, China, utilizing Local Climate Zone (LCZ) data as a substitute for POI data. Leveraging multi-source geospatial big data and the random forest classifier, we delineate urban land use distributions at the parcel level for the years 2000, 2005, 2010, 2015, 2018, and 2020. The results demonstrate that the generated EULUC maps achieve promising classification performance, with an overall accuracy of 78% for Level 1 and 71% for Level 2 categories. Features derived from nighttime light data, LCZ, Sentinel-2 satellite imagery, and topographic data play leading roles in our land use classification process. The importance of LCZ data is second only to nighttime light data, achieving comparable classification accuracy to that when using POI data. Our subsequent correlation analysis reveals a significant correlation between POI and LCZ data (p = 0.4), which validates the rationale of the proposed framework. These findings offer valuable insights for long-term urban land use mapping, which can facilitate effective urban planning and resource management in the near future.
引用
收藏
页数:23
相关论文
共 50 条
  • [41] Dealing with missing modalities at test time for land cover mapping: A case study on multi-source optical data
    Gbodjo, Yawogan Jean Eudes
    Ienco, Dino
    2022 IEEE 21ST MEDITERRANEAN ELECTROTECHNICAL CONFERENCE (IEEE MELECON 2022), 2022, : 621 - 626
  • [42] Time-series metrics applied to land use and land cover mapping with focus on landslide detection
    Tardelli Uehara, Tatiana Dias
    Korting, Thales Sehn
    Soares, Anderson dos Reis
    Quevedo, Renata Pacheco
    JOURNAL OF APPLIED REMOTE SENSING, 2022, 16 (03)
  • [43] Automatic training sample collection utilizing multi-source land cover products and time-series Sentinel-2 images
    Wang, Yanzhao
    Sun, Yonghua
    Cao, Xuyue
    Wang, Yihan
    Zhang, Wangkuan
    Cheng, Xinglu
    Wang, Ruozeng
    Zong, Jinkun
    GISCIENCE & REMOTE SENSING, 2024, 61 (01)
  • [44] Uncovering the Nature of Urban Land Use Composition Using Multi-Source Open Big Data with Ensemble Learning
    Tu, Ying
    Chen, Bin
    Lang, Wei
    Chen, Tingting
    Li, Miao
    Zhang, Tao
    Xu, Bing
    REMOTE SENSING, 2021, 13 (21)
  • [45] Susceptibility evaluation and mapping of China’s landslides based on multi-source data
    Chun Liu
    Weiyue Li
    Hangbin Wu
    Ping Lu
    Kai Sang
    Weiwei Sun
    Wen Chen
    Yang Hong
    Rongxing Li
    Natural Hazards, 2013, 69 : 1477 - 1495
  • [46] Susceptibility evaluation and mapping of China's landslides based on multi-source data
    Liu, Chun
    Li, Weiyue
    Wu, Hangbin
    Lu, Ping
    Sang, Kai
    Sun, Weiwei
    Chen, Wen
    Hong, Yang
    Li, Rongxing
    NATURAL HAZARDS, 2013, 69 (03) : 1477 - 1495
  • [47] Integrating multi-source data to improve water erosion mapping in Tibet, China
    Yang, Yuanyuan
    Zhao, Ruiying
    Shi, Zhou
    Rossel, Raphael A. Viscarra
    Wan, Dan
    Liang, Zongzheng
    CATENA, 2018, 169 : 31 - 45
  • [48] Machine learning techniques and interpretability for maize yield estimation using Time-Series images of MODIS and Multi-Source data
    Lyu, Yujiao
    Wang, Pengxin
    Bai, Xueyuan
    Li, Xuecao
    Ye, Xin
    Hu, Yuchen
    Zhang, Jie
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 222
  • [49] Spatio-Temporal Urban Change Mapping With Time-Series SAR Data
    Che, Meiqin
    Vizziello, Anna
    Gamba, Paolo
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 7222 - 7234
  • [50] Land Cover Classification with Multi-source Data Using Evidential Reasoning Approach
    LI Huapeng1
    2. Graduate University of Chinese Academy of Sciences
    3. School of Computer and Information Science
    Chinese Geographical Science, 2011, 21 (03) : 312 - 321