Deep recurrent neural networks for winter vegetation quality mapping via multitemporal SAR sentinel-1

Ho Tong Minh Dinh, Ienco Dino, Gaetano Raffaele, Lalande Nathalie, Ndikumana Emile, Osman Faycal, Maurel Pierre. 2018. Deep recurrent neural networks for winter vegetation quality mapping via multitemporal SAR sentinel-1. IEEE Geoscience and Remote Sensing Letters, 15 (3) : 464-468.

https://doi.org/10.1109/LGRS.2018.2794581

Article de revue ; Article de recherche ; Article de revue à facteur d'impact

Version publiée - Anglais
Accès réservé aux personnels Cirad
Utilisation soumise à autorisation de l'auteur ou du Cirad.
Minh2018.pdf
Télécharger (1MB) | Demander une copie

Quartile : Q1, Sujet : GEOCHEMISTRY & GEOPHYSICS / Quartile : Q1, Sujet : IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY / Quartile : Q2, Sujet : ENGINEERING, ELECTRICAL & ELECTRONIC / Quartile : Q2, Sujet : REMOTE SENSING

Résumé : Mapping winter vegetation quality is a challenging problem in remote sensing. This is due to cloud coverage in winter periods, leading to a more intensive use of radar rather than optical images. The aim of this letter is to provide a better understanding of the capabilities of Sentinel-1 radar images for winter vegetation quality mapping through the use of deep learning techniques. Analysis is carried out on a multitemporal Sentinel-1 data over an area around Charentes-Maritimes, France. This data set was processed in order to produce an intensity radar data stack from October 2016 to February 2017. Two deep recurrent neural network (RNN)-based classifiers were employed. Our work revealed that the results of the proposed RNN models clearly outperformed classical machine learning approaches (support vector machine and random forest).

Mots-clés Agrovoc : télédétection, imagerie par satellite, indice de végétation, cartographie de l'occupation du sol, traitement des données, radar, réseau de neurones

Mots-clés géographiques Agrovoc : Aquitaine, France

Mots-clés complémentaires : deep learning

Classification Agris : U30 - Méthodes de recherche
F40 - Écologie végétale
U10 - Informatique, mathématiques et statistiques

Champ stratégique Cirad : Axe 6 (2014-2018) - Sociétés, natures et territoires

Auteurs et affiliations