Apport des images satellitaires de tres haute resolution spatiale pleiades a la caracterisation des cultures et des operations culturales en debut de saison

Abstract

This study is part of several projects aiming at spatially monitoring the effects of exogeno us organic matter apply on soil organic carbon sequestration, and necessitating for this purpose the gathering of spatial data about cropping systems. The aim of this study was to assess the contribution of very high spatial resolution (VHR) Pléiades images to both early season crop identification and mapping and changes in bare soil surface characteristics due to cultural operations. The study region covering 4000 ha including 2100 ha-croplands is located west of the peri-urban territory of the Versailles plain and the Alluets plateau (Yvelines, France). About 100 cropped fields were observed on the ground synchronously with two Pléiades images of 3 and 24 April 2013 and one SPOT4 image of 2 April 2013. The GIS structuring of these field data was used for delimitating both training and test zones for the support vector machine classifier with polynomial function kernel (pSVM). For the single date-images, the pSVM was computed on the 4 spectral bands while for the bitemporal Pléiades image, it relied on the 8 spectral bands and the two NDVI bands. For the single-date classifications of crops, the overall accuracy reached 87[%] for the SPOT4 image of 2 April (6 classes), 79[%] for the Pleiades image of 3 April (6 classes) and 82[%] for that of 24 April (7 classes). For the bi-temporal Pléiades image, the overall accuracy was about 80[%] (7 classes), winter crops, grasslands and fallows being very well detected while confusions occured between spring barley at initial stages (2-3 leaves) and bare soils prepared for other spring crops. At the earlier date (2-3 April), the Pléiades image very well discriminated cultural operations (>77[%], user's or producer's accuracies) as well as fallows and grasslands, and brought unique information about within-field spatial heterogeneity of crop development stages, while winter cereals and rapeseed were better discriminated by the SPOT4 image winter cereals (>70[%], user's or producer's accuracies). Pleiades images therefore bring information complementary to multispectral images with high spatial resolution.