Agritrop
Home

A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM)

Lebourgeois Valentine, Dupuy Stéphane, Vintrou Elodie, Ameline Maël, Butler Suzanne, Bégué Agnès. 2017. A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM). Remote Sensing, 9 (3):259, 20 p.

Journal article ; Article de recherche ; Article de revue à facteur d'impact Revue en libre accès total
[img]
Preview
Published version - Anglais
License CC0 1.0 Public Domain Dedication.
remotesensing-09-00259.pdf

Télécharger (6MB) | Preview

Quartile : Q2, Sujet : REMOTE SENSING

Abstract : Sentinel-2 images are expected to improve global crop monitoring even in challenging tropical small agricultural systems that are characterized by high intra- and inter-field spatial variability and where satellite observations are disturbed by the presence of clouds. To overcome these constraints, we analyzed and optimized the performance of a combined Random Forest (RF) classifier/object-based approach and applied it to multisource satellite data to produce land use maps of a smallholder agricultural zone in Madagascar at five different nomenclature levels. The RF classifier was first optimized by reducing the number of input variables. Experiments were then carried out to (i) test cropland masking prior to the classification of more detailed nomenclature levels, (ii) analyze the importance of each data source (a high spatial resolution (HSR) time series, a very high spatial resolution (VHSR) coverage and a digital elevation model (DEM)) and data type (spectral, textural or other), and (iii) quantify their contributions to classification accuracy levels. The results show that RF classifier optimization allowed for a reduction in the number of variables by 1.5- to 6-fold (depending on the classification level) and thus a reduction in the data processing time. Classification results were improved via the hierarchical approach at all classification levels, achieving an overall accuracy of 91.7% and 64.4% for the cropland and crop subclass levels, respectively. Spectral variables derived from an HSR time series were shown to be the most discriminating, with a better score for spectral indices over the reflectances. VHSR data were only found to be essential when implementing the segmentation of the area into objects and not for the spectral or textural features they can provide during classification. (Résumé d'auteur)

Mots-clés Agrovoc : Utilisation des terres, Télédétection, Terre agricole, Cartographie de l' utilisation des terres, Cartographie de l'occupation du sol, Image spot, Classification des terres, riz, sécurité alimentaire, Imagerie par satellite, Imagerie multispectrale

Mots-clés géographiques Agrovoc : Madagascar

Mots-clés libres : Remote sensing, Satellite, Food security, Land cover, Land use, Textures, Spectral indices, Rice, Madagascar

Classification Agris : E11 - Land economics and policies
E50 - Rural sociology
E80 - Home economics and crafts
E90 - Agrarian structure
U30 - Research methods

Champ stratégique Cirad : Axe 1 (2014-2018) - Agriculture écologiquement intensive

Agence(s) de financement européenne(s) : European Commission

Programme de financement européen : FP7

Projet(s) de financement européen(s) : Stimulating Innovation for Global Monitoring of Agriculture and its Impact on the Environment in support of GEOGLAM

Auteurs et affiliations

  • Lebourgeois Valentine, CIRAD-ES-UMR TETIS (FRA)
  • Dupuy Stéphane, CIRAD-ES-UMR TETIS (REU) ORCID: 0000-0002-9710-5364
  • Vintrou Elodie
  • Ameline Maël
  • Butler Suzanne
  • Bégué Agnès, CIRAD-ES-UMR TETIS (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/583973/)

View Item (staff only) View Item (staff only)

[ Page générée et mise en cache le 2021-02-27 ]