Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China

Urban green space (UGS) is crucial for the vitality and sustainability of the urban environment. However, the current UGS extraction methods based on satellite images still face the problem of high sample costs and phenological interference, which leads to insufficient efficiency and accuracy in UGS...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhuoqun Chai, Keyao Wen, Hao Fu, Mengxi Liu, Qian Shi
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Science of Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666017225000215
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850116615899709440
author Zhuoqun Chai
Keyao Wen
Hao Fu
Mengxi Liu
Qian Shi
author_facet Zhuoqun Chai
Keyao Wen
Hao Fu
Mengxi Liu
Qian Shi
author_sort Zhuoqun Chai
collection DOAJ
description Urban green space (UGS) is crucial for the vitality and sustainability of the urban environment. However, the current UGS extraction methods based on satellite images still face the problem of high sample costs and phenological interference, which leads to insufficient efficiency and accuracy in UGS results. In response, this study proposes a robust method for UGS mapping from time-series Sentinel-2 data by automatic sample generation and seasonal consistency modification. Specifically, temporal training samples were selected automatically through anomaly detection and probability filtering. Based on the annual UGS maps obtained by random forest classifier, the seasonal consistency modification approach considering phenological information and category interference is introduced to improve the accuracy of UGS mapping. The UGS maps of Shanghai from 2017 to 2022 extracted by the proposed method demonstrate an overall accuracy of 91.4% and a Kappa coefficient of 81.19%. This indicates that the proposed method can significantly enhance the efficiency and accuracy of extracting time-series UGS maps from Sentinel-2 data. The dynamic results also highlight the spatiotemporal patterns of UGS in Shanghai from 2017 to 2022, offering valuable insights for sustainable urban development.
format Article
id doaj-art-5fd98b00f921433d8a443e9200a1d673
institution OA Journals
issn 2666-0172
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Science of Remote Sensing
spelling doaj-art-5fd98b00f921433d8a443e9200a1d6732025-08-20T02:36:16ZengElsevierScience of Remote Sensing2666-01722025-06-011110021510.1016/j.srs.2025.100215Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, ChinaZhuoqun Chai0Keyao Wen1Hao Fu2Mengxi Liu3Qian Shi4School of Geography and Planning, And Guangdong Key Laboratory for Urbanization and Geo-simulation, Sun Yat-sen University, Guangzhou, 510275, ChinaSchool of Geography and Planning, And Guangdong Key Laboratory for Urbanization and Geo-simulation, Sun Yat-sen University, Guangzhou, 510275, ChinaSchool of Geography and Planning, And Guangdong Key Laboratory for Urbanization and Geo-simulation, Sun Yat-sen University, Guangzhou, 510275, ChinaCorresponding author.; School of Geography and Planning, And Guangdong Key Laboratory for Urbanization and Geo-simulation, Sun Yat-sen University, Guangzhou, 510275, ChinaSchool of Geography and Planning, And Guangdong Key Laboratory for Urbanization and Geo-simulation, Sun Yat-sen University, Guangzhou, 510275, ChinaUrban green space (UGS) is crucial for the vitality and sustainability of the urban environment. However, the current UGS extraction methods based on satellite images still face the problem of high sample costs and phenological interference, which leads to insufficient efficiency and accuracy in UGS results. In response, this study proposes a robust method for UGS mapping from time-series Sentinel-2 data by automatic sample generation and seasonal consistency modification. Specifically, temporal training samples were selected automatically through anomaly detection and probability filtering. Based on the annual UGS maps obtained by random forest classifier, the seasonal consistency modification approach considering phenological information and category interference is introduced to improve the accuracy of UGS mapping. The UGS maps of Shanghai from 2017 to 2022 extracted by the proposed method demonstrate an overall accuracy of 91.4% and a Kappa coefficient of 81.19%. This indicates that the proposed method can significantly enhance the efficiency and accuracy of extracting time-series UGS maps from Sentinel-2 data. The dynamic results also highlight the spatiotemporal patterns of UGS in Shanghai from 2017 to 2022, offering valuable insights for sustainable urban development.http://www.sciencedirect.com/science/article/pii/S2666017225000215Urban green spaceSentinel-2 dataSample generationSpatiotemporal analysisShanghai
spellingShingle Zhuoqun Chai
Keyao Wen
Hao Fu
Mengxi Liu
Qian Shi
Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
Science of Remote Sensing
Urban green space
Sentinel-2 data
Sample generation
Spatiotemporal analysis
Shanghai
title Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
title_full Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
title_fullStr Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
title_full_unstemmed Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
title_short Time-series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on Sentinel-2 data: A case study of Shanghai, China
title_sort time series urban green space mapping and analysis through automatic sample generation and seasonal consistency modification on sentinel 2 data a case study of shanghai china
topic Urban green space
Sentinel-2 data
Sample generation
Spatiotemporal analysis
Shanghai
url http://www.sciencedirect.com/science/article/pii/S2666017225000215
work_keys_str_mv AT zhuoqunchai timeseriesurbangreenspacemappingandanalysisthroughautomaticsamplegenerationandseasonalconsistencymodificationonsentinel2dataacasestudyofshanghaichina
AT keyaowen timeseriesurbangreenspacemappingandanalysisthroughautomaticsamplegenerationandseasonalconsistencymodificationonsentinel2dataacasestudyofshanghaichina
AT haofu timeseriesurbangreenspacemappingandanalysisthroughautomaticsamplegenerationandseasonalconsistencymodificationonsentinel2dataacasestudyofshanghaichina
AT mengxiliu timeseriesurbangreenspacemappingandanalysisthroughautomaticsamplegenerationandseasonalconsistencymodificationonsentinel2dataacasestudyofshanghaichina
AT qianshi timeseriesurbangreenspacemappingandanalysisthroughautomaticsamplegenerationandseasonalconsistencymodificationonsentinel2dataacasestudyofshanghaichina