Agritrop
Accueil

Crop identification using time series of Landsat-8 and radarsat-2 images: application in a groundwater irrigated region, south India

Sharma A.K., Hubert-Moy Laurence, Betbeder Julie, Ruiz Laurent, Sekhar M., Corgne Samuel. 2016. Crop identification using time series of Landsat-8 and radarsat-2 images: application in a groundwater irrigated region, south India. In : Proceedings of Living Planet Symposium 2016. Ouwehand L. (ed.). Noordwijk : ESA [European Space Agency], 4 p. (Living Planet Symposium, 740) ISBN 978-92-9221-305-3 European Space Agency Living Planet Symposium 2016, Prague, République tchèque, 9 Mai 2016/13 Mai 2016.

Communication avec actes
[img] Version publiée - Anglais
Accès réservé aux agents Cirad
Utilisation soumise à autorisation de l'auteur ou du Cirad.
Sharma_2016_LPS_Conf.pdf

Télécharger (285kB) | Demander une copie

Résumé : Monitoring land use and land cover and more particularly irrigated cropland dynamics is of great importance for water resources management and land use planning. The objective of this study was to evaluate the combined use of multi-temporal optical and radar data with a high spatial resolution in order to improve the precision of irrigated crop identification by taking into account information on crop phenological stages. SAR and optical parameters were derived from timeseries of seven quad-pol RADARSAT-2 and four Landsat-8 images which were acquired on the Berambadi catchment, South India, during the monsoon crop season at the growth stages of turmeric crop. To select the best parameter to discriminate turmeric crops, an analysis of covariance (ANCOVA) was applied on all the time-series parameters and the most discriminant ones were classified using the Support Vector Machine (SVM) technique. Results show that in absence of optical images, polarimetric parameters derived from SAR time-series can be used for the turmeric area estimates and that the combined use of SAR and optical parameters can improve the classification accuracy to identify turmeric.

Mots-clés libres : Irrigated cropland, SAR time-series, Optical time-series, Leaf area index (LAI), Polarimetric parameters

Auteurs et affiliations

  • Sharma A.K.
  • Hubert-Moy Laurence, Université de Rennes 2 (FRA)
  • Betbeder Julie, Université de Rennes 2 (FRA)
  • Ruiz Laurent, IFCWS (IND)
  • Sekhar M., IFCWS (IND)
  • Corgne Samuel, Université de Rennes 2 (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/595159/)

Voir la notice (accès réservé à la Dist) Voir la notice (accès réservé à la Dist)

[ Page générée et mise en cache le 2020-05-13 ]