Format du dépôt |
Fichier |
Type de dépôt |
Article dans une revue |
Titre |
en
Evaluation of Sentinel-1 and 2 Time Series for Land Cover Classification of Forest–Agriculture Mosaics in Temperate and Tropical Landscapes
|
Résumé |
en
Monitoring forest-agriculture mosaics is crucial for understanding landscape heterogeneity and managing biodiversity. Mapping these mosaics from remotely sensed imagery remains challenging, since ecological gradients from forested to agricultural areas make characterizing vegetation more difficult. The recent synthetic aperture radar (SAR) Sentinel-1 (S-1) and optical Sentinel-2 (S-2) time series provide a great opportunity to monitor forest-agriculture mosaics due to their high spatial and temporal resolutions. However, while a few studies have used the temporal resolution of S-2 time series alone to map land cover and land use in cropland and/or forested areas, S-1 time series have not yet been investigated alone for this purpose. The combined use of S-1 & S-2 time series has been assessed for only one or a few land cover classes. In this study, we assessed the potential of S-1 data alone, S-2 data alone, and their combined use for mapping forest-agriculture mosaics over two study areas: a temperate mountainous landscape in the Cantabrian Range (Spain) and a tropical forested landscape in Paragominas (Brazil). Satellite images were classified using an incremental procedure based on an importance rank of the input features. The classifications obtained with S-2 data alone (mean kappa index = 0.59-0.83) were more accurate than those obtained with S-1 data alone (mean kappa index = 0.28-0.72). Accuracy increased when combining S-1 and 2 data (mean kappa index = 0.55-0.85). The method enables defining the number and type of features that discriminate land cover classes in an optimal manner according to the type of landscape considered. The best configuration for the Spanish and Brazilian study areas included 5 and 10 features, respectively, for S-2 data alone and 10 and 20 features, respectively, for S-1 data alone. Short-wave infrared and VV and VH polarizations were key features of S-2 and S-1 data, respectively. In addition, the method enables defining key periods that discriminate land cover classes according to the type of images used. For example, in the Cantabrian Range, winter and summer were key for S-2 time series, while spring and winter were key for S-1 time series.
|
Auteur(s)
|
Audrey Mercier
1
, Julie Betbeder
2
, Florent Rumiano
3
, Jacques J. Baudry
4
, Valery Gond
5
, Lilian Blanc
5
, Clément Bourgoin
5
, Guillaume Cornu
5
, Carlos J. Ciudad
6
, Miguel Marchamalo
, René Poccard-Chapuis
7
, Laurence Hubert-Moy
2
1
Signalisation normale et pathologique de l'embryon aux thérapies innovantes des cancers
( 106192 )
- Orsay
- France
-
Institut Curie [Paris] ( 301888 )
;
-
Institut National de la Santé et de la Recherche Médicale U1021 ( 303623 )
;
-
Centre National de la Recherche Scientifique UMR3347 ( 441569 )
2
LETG - Rennes -
Littoral, Environnement, Télédétection, Géomatique
( 3177 )
- Maison de la Recherche Place du Recteur Henri Le Moal 35043 RENNES CEDEX
- France
-
Littoral, Environnement, Télédétection, Géomatique UMR 6554 ( 14266 )
;
-
Université de Caen Normandie ( 7127 )
;
-
Normandie Université ( 455934 )
;
-
Université d'Angers ( 74911 )
;
-
École Pratique des Hautes Études ( 110691 )
;
-
Université Paris Sciences et Lettres ( 564132 )
;
-
Université de Brest ( 300314 )
;
-
Université de Rennes 2 ( 406201 )
;
-
Centre National de la Recherche Scientifique UMR 6554 ( 441569 )
;
-
Institut de Géographie et d'Aménagement Régional de l'Université de Nantes ( 530572 )
;
-
Université de Nantes 93263 ( 93263 )
3
IUGA -
Université Grenoble Alpes - Institut d'urbanisme et de géographie alpine
( 543796 )
- 14 et 14 bis avenue Marie Reynoard - 38100 Grenoble
- France
-
Université Grenoble Alpes [2016-2019] ( 445543 )
4
SAD Paysage -
SAD Paysage
( 190320 )
- AGROCAMPUS OUEST, UPR0980 SAD Paysage, F-35042 Rennes, France
- France
-
Institut National de la Recherche Agronomique UR0980 ( 92114 )
;
-
AGROCAMPUS OUEST ( 108028 )
5
UPR Forêts et Sociétés -
Forêts et Sociétés
( 497978 )
- CIRAD, TA C-105 / D-Campus international de Baillarguet 34398 Montpellier Cedex 5 France
- France
-
Centre de Coopération Internationale en Recherche Agronomique pour le Développement 105 ( 11574 )
6
Biochemistry and Molecular Biology
( 174402 )
- Gran Via de les Corts Catalanes, 585, 08007 Barcelona
- Espagne
-
University of Barcelona ( 417362 )
;
-
Centro de Investigacion Biomédica en Red sobre Enfermedades Neurodegenerativas ( 454435 )
;
-
Instituto de Salud Carlos III [Madrid] ( 308343 )
7
UMR SELMET -
Systèmes d'élevage méditerranéens et tropicaux
( 412595 )
- TA C-112 / A - Campus international de Baillarguet ou Avenue Agropolis 34398 Montpellier Cedex 5, France
- France
-
Centre de Coopération Internationale en Recherche Agronomique pour le Développement UMR112 ( 11574 )
;
-
Institut National de la Recherche Agronomique UMR0868 ( 92114 )
;
-
Centre international d'études supérieures en sciences agronomiques ( 92699 )
;
-
Institut national d’études supérieures agronomiques de Montpellier ( 474617 )
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Audience |
Internationale
|
Public visé |
Scientifique
|
Numéro d'article |
|
Langue du document |
Anglais
|
Licence |
Paternité
|
Nom de la revue |
|
Date de publication |
2019-04
|
Volume |
11
|
Numéro |
8
|
Page/Identifiant |
979
|
Domaine(s) |
-
Sciences de l'Homme et Société/Géographie
-
Sciences de l'environnement
|
Mots-clés |
en
remote sensing, optical and SAR satellite images, feature selection, decision trees, random forests, brazilian amazon, cantabrian range
|
DOI |
10.3390/rs11080979 |
ProdINRA |
472582 |
UT key WOS |
000467646800089 |