Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination

The present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxo...

Full description

Bibliographic Details
Main Authors: Cristina Tarantino, Luigi Forte, Palma Blonda, Saverio Vicario, Valeria Tomaselli, Carl Beierkuhnlein, Maria Adamo
Format: Article
Language:English
Published: MDPI AG 2021-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/13/2/277
_version_ 1827600963709435904
author Cristina Tarantino
Luigi Forte
Palma Blonda
Saverio Vicario
Valeria Tomaselli
Carl Beierkuhnlein
Maria Adamo
author_facet Cristina Tarantino
Luigi Forte
Palma Blonda
Saverio Vicario
Valeria Tomaselli
Carl Beierkuhnlein
Maria Adamo
author_sort Cristina Tarantino
collection DOAJ
description The present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxonomies). For this purpose, an intra-annual time-series of 30 Sentinel-2 images, embedding phenology information, were investigated for 2018. The methodology adopted was based on a two-stage workflow employing a Support Vector Machine classifier. In the first stage only four Sentinel-2 multi-season images were analyzed, to provide an updated land cover map from where the grassland layer was extracted. The layer obtained was then used for masking the input features to the second stage. The latter stage discriminated the four grassland habitats by analyzing several input features configurations. These included multiple spectral indices selected from the time-series and the Digital Terrain Model. The results obtained from the different input configurations selected were compared to evaluate if the phenology information from time-series could improve grassland habitats discrimination. The highest F1 values (95.25% and 80.27%) were achieved for 6210/E1.263 and 6220/E1.434, respectively, whereas the results remained stable (97,33%) for 62A0/E1.55 and quite low (75,97%) for X/E1.61-E1.C2-E1.C4. However, since for all the four habitats analyzed no single configuration resulted effective, a Majority Vote algorithm was applied to achieve a reduction in classification uncertainty.
first_indexed 2024-03-09T04:45:32Z
format Article
id doaj.art-0535ce3f41ca4f6d9d7847f53f3b74ad
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-09T04:45:32Z
publishDate 2021-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-0535ce3f41ca4f6d9d7847f53f3b74ad2023-12-03T13:15:36ZengMDPI AGRemote Sensing2072-42922021-01-0113227710.3390/rs13020277Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat DiscriminationCristina Tarantino0Luigi Forte1Palma Blonda2Saverio Vicario3Valeria Tomaselli4Carl Beierkuhnlein5Maria Adamo6Interateneo Physics Department, National Research Council of Italy, Institute of Atmospheric Pollution Research (CNR-IIA), 70126 Bari, ItalyDepartment of Biology, University of Bari, Via Orabona 4, 70125 Bari, ItalyInterateneo Physics Department, National Research Council of Italy, Institute of Atmospheric Pollution Research (CNR-IIA), 70126 Bari, ItalyInterateneo Physics Department, National Research Council of Italy, Institute of Atmospheric Pollution Research (CNR-IIA), 70126 Bari, ItalyDepartment of Biology, University of Bari, Via Orabona 4, 70125 Bari, ItalyDepartment of Biogeography, University of Bayreuth, 95440 Bayreuth, GermanyInterateneo Physics Department, National Research Council of Italy, Institute of Atmospheric Pollution Research (CNR-IIA), 70126 Bari, ItalyThe present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxonomies). For this purpose, an intra-annual time-series of 30 Sentinel-2 images, embedding phenology information, were investigated for 2018. The methodology adopted was based on a two-stage workflow employing a Support Vector Machine classifier. In the first stage only four Sentinel-2 multi-season images were analyzed, to provide an updated land cover map from where the grassland layer was extracted. The layer obtained was then used for masking the input features to the second stage. The latter stage discriminated the four grassland habitats by analyzing several input features configurations. These included multiple spectral indices selected from the time-series and the Digital Terrain Model. The results obtained from the different input configurations selected were compared to evaluate if the phenology information from time-series could improve grassland habitats discrimination. The highest F1 values (95.25% and 80.27%) were achieved for 6210/E1.263 and 6220/E1.434, respectively, whereas the results remained stable (97,33%) for 62A0/E1.55 and quite low (75,97%) for X/E1.61-E1.C2-E1.C4. However, since for all the four habitats analyzed no single configuration resulted effective, a Majority Vote algorithm was applied to achieve a reduction in classification uncertainty.https://www.mdpi.com/2072-4292/13/2/277grasslandhabitat mappingNatura 2000Sentinel-2spectral indextime-series
spellingShingle Cristina Tarantino
Luigi Forte
Palma Blonda
Saverio Vicario
Valeria Tomaselli
Carl Beierkuhnlein
Maria Adamo
Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
Remote Sensing
grassland
habitat mapping
Natura 2000
Sentinel-2
spectral index
time-series
title Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
title_full Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
title_fullStr Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
title_full_unstemmed Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
title_short Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination
title_sort intra annual sentinel 2 time series supporting grassland habitat discrimination
topic grassland
habitat mapping
Natura 2000
Sentinel-2
spectral index
time-series
url https://www.mdpi.com/2072-4292/13/2/277
work_keys_str_mv AT cristinatarantino intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT luigiforte intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT palmablonda intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT saveriovicario intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT valeriatomaselli intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT carlbeierkuhnlein intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination
AT mariaadamo intraannualsentinel2timeseriessupportinggrasslandhabitatdiscrimination