Identification and characterization of agricultural winter land-use based on Alos-2 and Radarsat-2 polarimetric SAR time-series images

J. Denize (1) , Laurence Hubert-Moy (2) , Samuel Corgne (2) , J. Betbeder (3) , E. Pottier (1)

1 IETR - Institut d'Électronique et des Technologies du numéRique
2 LETG - Nantes - Littoral, Environnement, Télédétection, Géomatique
3 Cirad - Centre de Coopération Internationale en Recherche Agronomique pour le Développement

Land cover and land use monitoring, particularly during winter season, is still a major environmental challenge. Indeed, the presence of a vegetation cover, the dates of sowing, the length of the catch crops period, and land use types have an impact on pollutant transport to water bodies. The objective of this study was to evaluate the potential of C- and L-SAR times series to improve the identification and characterization of vegetation cover during winter season. Alos-2 and Radarsat-2 time-series were classified on a 130km2 site using SVM and RF algorithms. Land-use was classified with an OA of ~ 80 from Radarsat-2 polarimetric images acquired between August 2016 and May 2017 using RF classifier. © VDE VERLAG GMBH  Berlin  Offenbach.

Keywords: Land use; Polarimeters; Radar imaging; Time series; Vegetation; Water pollution; Environmental challenges; Land use type; Polarimetric image; Polarimetric SAR; Pollutant transport; Times series; Vegetation cover; Winter seasons; Synthetic aperture radar

Domains: Engineering Sciences [physics]

J. Denize, Laurence Hubert-Moy, Samuel Corgne, J. Betbeder, E. Pottier. Identification and characterization of agricultural winter land-use based on Alos-2 and Radarsat-2 polarimetric SAR time-series images. 12th European Conference on Synthetic Aperture Radar, EUSAR 2018, Jun 2018, Aachen, Germany. pp.549-553. ⟨hal-01874635⟩