Multioutput support vector regression for remote sensing biophysical parameter estimation

Devis Tuia*, Jochem Verrelst, Luis Alonso, Fernando Perez-Cruz, Gustavo Camps-Valls

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

162 Citations (Scopus)

Abstract

This letter proposes a multioutput support vector regression (M-SVR) method for the simultaneous estimation of different biophysical parameters from remote sensing images. General retrieval problems require multioutput (and potentially nonlinear) regression methods. M-SVR extends the single-output SVR to multiple outputs maintaining the advantages of a sparse and compact solution by using an ε-insensitive cost function. The proposed M-SVR is evaluated in the estimation of chlorophyll content, leaf area index and fractional vegetation cover from a hyperspectral compact high-resolution imaging spectrometer images. The achieved improvement with respect to the single-output regression approach suggests that M-SVR can be considered a convenient alternative for nonparametric biophysical parameter estimation and model inversion.

Original languageEnglish
Article number5735189
Pages (from-to)804-808
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume8
Issue number4
DOIs
Publication statusPublished - 1 Jul 2011
Externally publishedYes

Keywords

  • Biophysical parameter estimation
  • model inversion
  • regression
  • support vector regression (SVR)

Fingerprint Dive into the research topics of 'Multioutput support vector regression for remote sensing biophysical parameter estimation'. Together they form a unique fingerprint.

Cite this