A 10 m resolution urban green space map for major Latin American cities from Sentinel-2 remote sensing images and OpenStreetMap

Mapping is fundamental to studies on urban green space (UGS). Despite a growing archive of land cover maps (where UGS is included) at global and regional scales, mapping efforts dedicated to UGS are still limited. As UGS is often a part of the heterogenous urban landscape, low-resolution land cover...

Full description

Saved in:
Bibliographic Details
Published in:Scientific data 2022-09, Vol.9 (1), p.586-9, Article 586
Main Authors: Ju, Yang, Dronova, Iryna, Delclòs-Alió, Xavier
Format: Article
Language:English
Subjects:
704/844/685
706/1145
706/134
706/2808
Data Descriptor
Humanities and Social Sciences
Mapping
multidisciplinary
Public health
Quality control
Remote sensing
Science
Science (multidisciplinary)
Urban planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mapping is fundamental to studies on urban green space (UGS). Despite a growing archive of land cover maps (where UGS is included) at global and regional scales, mapping efforts dedicated to UGS are still limited. As UGS is often a part of the heterogenous urban landscape, low-resolution land cover maps from remote sensing images tend to confuse UGS with other land covers. Here we produced the first 10 m resolution UGS map for the main urban clusters across 371 major Latin American cities as of 2017. Our approach applied a supervised classification of Sentinel-2 satellite images and UGS samples derived from OpenStreetMap (OSM). The overall accuracy of this UGS map in 11 randomly selected cities was 0.87. We further improved mapping quality through a visual inspection and additional quality control of the samples. The resulting UGS map enables studies to measure area, spatial configuration, and human exposures to UGS, facilitating studies on the relationship between UGS and human exposures to environmental hazards, public health outcomes, urban ecology, and urban planning. Measurement(s) urban green space Technology Type(s) remote sensing • volunteered geographic information • supervised machine learning Sample Characteristic - Environment city Sample Characteristic - Location Argentina • Brazil • Chile • Colombia • Costa Rica • El Salvador • Guatemala • Mexico • Nicaragua • Panama • Peru
ISSN:2052-4463
2052-4463
DOI:10.1038/s41597-022-01701-y