Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method

Urban green spaces (UGSs) are critical for landscape, ecological, and climate studies. However, the generation of long-term annual UGSs maps is often constrained by the lack of sufficient, high-quality training samples for training classifiers. In this study, we introduce an automatic training sampl...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengyao Wang, Pan Li, Chunyu Wang, Wei Chen, Zhongen Niu, Na Zeng, Xingxing Han, Xinchao Sun
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/8/1426
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144497189519360
author Mengyao Wang
Pan Li
Chunyu Wang
Wei Chen
Zhongen Niu
Na Zeng
Xingxing Han
Xinchao Sun
author_facet Mengyao Wang
Pan Li
Chunyu Wang
Wei Chen
Zhongen Niu
Na Zeng
Xingxing Han
Xinchao Sun
author_sort Mengyao Wang
collection DOAJ
description Urban green spaces (UGSs) are critical for landscape, ecological, and climate studies. However, the generation of long-term annual UGSs maps is often constrained by the lack of sufficient, high-quality training samples for training classifiers. In this study, we introduce an automatic training sample migration method based on visually interpreted reference data and long-term Landsat imagery, implemented on the Google Earth Engine (GEE) platform, to produce annual UGSs maps for Tianjin from 1984 to 2022. Migrating training samples to each year significantly improved classification performance, especially for UGSs and water bodies. UGSs coverage in sample areas increased from 5% to 38%, resulting in more reliable trend detection. Our spatiotemporal analysis revealed that green coverage in the study area reached up to 40%, dominated by tree cover that is significantly underestimated in existing global and regional land cover products. Distinct temporal patterns emerged between the old built-up area (OBUA) and new built-up area (NBUA). Early UGS decline was largely driven by NBUAs, while post-2007 greening involved both OBUAs and NBUAs, as captured by classification maps and vegetation indices. Our study proposes a scalable and practical framework for long-term land cover mapping in rapidly urbanizing regions, with enhanced potential as higher-resolution data becomes increasingly accessible.
format Article
id doaj-art-a1dba5d094534a77a32d3b90784e8740
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-a1dba5d094534a77a32d3b90784e87402025-08-20T02:28:20ZengMDPI AGRemote Sensing2072-42922025-04-01178142610.3390/rs17081426Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration MethodMengyao Wang0Pan Li1Chunyu Wang2Wei Chen3Zhongen Niu4Na Zeng5Xingxing Han6Xinchao Sun7Institute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaCollege of Hydraulic and Civil Engineering, Ludong University, Yantai 264025, ChinaSchool of Environment and Resources, Zhejiang A & F University, Hangzhou 311300, ChinaInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, ChinaUrban green spaces (UGSs) are critical for landscape, ecological, and climate studies. However, the generation of long-term annual UGSs maps is often constrained by the lack of sufficient, high-quality training samples for training classifiers. In this study, we introduce an automatic training sample migration method based on visually interpreted reference data and long-term Landsat imagery, implemented on the Google Earth Engine (GEE) platform, to produce annual UGSs maps for Tianjin from 1984 to 2022. Migrating training samples to each year significantly improved classification performance, especially for UGSs and water bodies. UGSs coverage in sample areas increased from 5% to 38%, resulting in more reliable trend detection. Our spatiotemporal analysis revealed that green coverage in the study area reached up to 40%, dominated by tree cover that is significantly underestimated in existing global and regional land cover products. Distinct temporal patterns emerged between the old built-up area (OBUA) and new built-up area (NBUA). Early UGS decline was largely driven by NBUAs, while post-2007 greening involved both OBUAs and NBUAs, as captured by classification maps and vegetation indices. Our study proposes a scalable and practical framework for long-term land cover mapping in rapidly urbanizing regions, with enhanced potential as higher-resolution data becomes increasingly accessible.https://www.mdpi.com/2072-4292/17/8/1426urban green spacesland cover mappingtraining samplespatiotemporal dynamics
spellingShingle Mengyao Wang
Pan Li
Chunyu Wang
Wei Chen
Zhongen Niu
Na Zeng
Xingxing Han
Xinchao Sun
Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
Remote Sensing
urban green spaces
land cover mapping
training sample
spatiotemporal dynamics
title Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
title_full Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
title_fullStr Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
title_full_unstemmed Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
title_short Detecting Long-Term Spatiotemporal Dynamics of Urban Green Spaces with Training Sample Migration Method
title_sort detecting long term spatiotemporal dynamics of urban green spaces with training sample migration method
topic urban green spaces
land cover mapping
training sample
spatiotemporal dynamics
url https://www.mdpi.com/2072-4292/17/8/1426
work_keys_str_mv AT mengyaowang detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT panli detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT chunyuwang detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT weichen detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT zhongenniu detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT nazeng detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT xingxinghan detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod
AT xinchaosun detectinglongtermspatiotemporaldynamicsofurbangreenspaceswithtrainingsamplemigrationmethod