Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions

This study presents an automated methodology to generate training data for surface water mapping from a single Sentinel-2 granule at 10 m (4 band, VIS/NIR) or 20 m (9 band, VIS/NIR/SWIR) resolution without the need for ancillary training data layers. The 20 m method incorporates an ensemble of three...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kristofer Lasko, Megan C. Maloney, Sarah J. Becker, Andrew W. H. Griffin, Susan L. Lyon, Sean P. Griffin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	surface water water index band ratios machine learning random forest multispectral Science Q
Acceso en línea:	https://doaj.org/article/6161a5bed89240a9842e572dcc904218
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6161a5bed89240a9842e572dcc904218
record_format	dspace
spelling	oai:doaj.org-article:6161a5bed89240a9842e572dcc9042182021-11-25T18:53:59ZAutomated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions10.3390/rs132245312072-4292https://doaj.org/article/6161a5bed89240a9842e572dcc9042182021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4531https://doaj.org/toc/2072-4292This study presents an automated methodology to generate training data for surface water mapping from a single Sentinel-2 granule at 10 m (4 band, VIS/NIR) or 20 m (9 band, VIS/NIR/SWIR) resolution without the need for ancillary training data layers. The 20 m method incorporates an ensemble of three spectral indexes with optimal band thresholds, whereas the 10 m method achieves similar results using fewer bands and a single spectral index. A spectrally balanced and randomly generated set of training data based on the index values and optimal thresholds is used to fit machine learning classifiers. Statistical validation compares the 20 m ensemble-only method to the 20 m ensemble method with a random forest classifier. Results show the 20 m ensemble-only method had an overall accuracy of 89.5% (±1.7%), whereas the ensemble method combined with the random forest classifier performed better, with a ~4.8% higher overall accuracy: 20 m method (94.3% (±1.3%)) with optimal spectral index and SWIR thresholds of −0.03 and 800, respectively, and 10 m method (93.4% (±1.5%)) with optimal spectral index and NIR thresholds of −0.01 and 800, respectively. Comparison of other supervised classifiers trained automatically with the framework typically resulted in less than 1% accuracy improvement compared with the random forest, suggesting that training data quality is more important than classifier type. This straightforward framework enables accurate surface water classification across diverse geographies, making it ideal for development into a decision support tool for water resource managers.Kristofer LaskoMegan C. MaloneySarah J. BeckerAndrew W. H. GriffinSusan L. LyonSean P. GriffinMDPI AGarticlesurface waterwater indexband ratiosmachine learningrandom forestmultispectralScienceQENRemote Sensing, Vol 13, Iss 4531, p 4531 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	surface water water index band ratios machine learning random forest multispectral Science Q
spellingShingle	surface water water index band ratios machine learning random forest multispectral Science Q Kristofer Lasko Megan C. Maloney Sarah J. Becker Andrew W. H. Griffin Susan L. Lyon Sean P. Griffin Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
description	This study presents an automated methodology to generate training data for surface water mapping from a single Sentinel-2 granule at 10 m (4 band, VIS/NIR) or 20 m (9 band, VIS/NIR/SWIR) resolution without the need for ancillary training data layers. The 20 m method incorporates an ensemble of three spectral indexes with optimal band thresholds, whereas the 10 m method achieves similar results using fewer bands and a single spectral index. A spectrally balanced and randomly generated set of training data based on the index values and optimal thresholds is used to fit machine learning classifiers. Statistical validation compares the 20 m ensemble-only method to the 20 m ensemble method with a random forest classifier. Results show the 20 m ensemble-only method had an overall accuracy of 89.5% (±1.7%), whereas the ensemble method combined with the random forest classifier performed better, with a ~4.8% higher overall accuracy: 20 m method (94.3% (±1.3%)) with optimal spectral index and SWIR thresholds of −0.03 and 800, respectively, and 10 m method (93.4% (±1.5%)) with optimal spectral index and NIR thresholds of −0.01 and 800, respectively. Comparison of other supervised classifiers trained automatically with the framework typically resulted in less than 1% accuracy improvement compared with the random forest, suggesting that training data quality is more important than classifier type. This straightforward framework enables accurate surface water classification across diverse geographies, making it ideal for development into a decision support tool for water resource managers.
format	article
author	Kristofer Lasko Megan C. Maloney Sarah J. Becker Andrew W. H. Griffin Susan L. Lyon Sean P. Griffin
author_facet	Kristofer Lasko Megan C. Maloney Sarah J. Becker Andrew W. H. Griffin Susan L. Lyon Sean P. Griffin
author_sort	Kristofer Lasko
title	Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
title_short	Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
title_full	Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
title_fullStr	Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
title_full_unstemmed	Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions
title_sort	automated training data generation from spectral indexes for mapping surface water extent with sentinel-2 satellite imagery at 10 m and 20 m resolutions
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6161a5bed89240a9842e572dcc904218
work_keys_str_mv	AT kristoferlasko automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions AT megancmaloney automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions AT sarahjbecker automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions AT andrewwhgriffin automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions AT susanllyon automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions AT seanpgriffin automatedtrainingdatagenerationfromspectralindexesformappingsurfacewaterextentwithsentinel2satelliteimageryat10mand20mresolutions
_version_	1718410590996660224

Automated Training Data Generation from Spectral Indexes for Mapping Surface Water Extent with Sentinel-2 Satellite Imagery at 10 m and 20 m Resolutions

Ejemplares similares