PRINCIPAL COMPONENT ANALYSIS BASED POLYNOMIAL CHAOS EXPANSION REGRESSION OF LEAF AREA INDEX FROM POLSAR IMAGERY

Mehmet Furkan Celik, Esra Erten

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

Predicting biophysical parameters with high accuracy and fast speed based on remote sensing-based modeling is an attractive topic. In this context, the revisit time, coverage, and illumination condition in-dependency make the Polarimetric Synthetic Aperture Radar (PolSAR) data is an attractive tool. In this paper, one of the most studied biophysical parameters, Leaf Area Index (LAI), is chosen to assess Polynomial Chaos Expansion (PCE) regression, commonly used metamodeling due to its precise and rapid approximation performance. Experimental analysis based on AgriSAR 2009 campaign, including oat and canola, is given to validate the PCE in the regression. According to the accuracy analysis, the Pearson correlation of 88% and 95% for oat and canola, respectively, were achieved.

Original languageEnglish
Pages6096-6099
Number of pages4
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium
Duration: 12 Jul 202116 Jul 2021

Conference

Conference2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/TerritoryBelgium
CityBrussels
Period12/07/2116/07/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

Radarsat-2 Data and Products MacDonald, Dettwiler and Associates Ltd. (MDA, 2009) All Rights Reserved. Radarsat is an official trademark of the Canadian Space Agency (CSA). All Radarsat-2 images have been provided by MDA and CSA in the framework of the ESA-funded AgriSAR2009 campaign. The ground data collection was conducted by the Indian Head Agriculture Research Facility (IHARF) and the University of Regina. The Polynomial Chaos Expansion computations are carried out in UQLab [10]. This study was funded by ITU Scientific Research Project with Protocol Number: MDK-42745.

FundersFunder number
Dettwiler and Associates Ltd.
ITU Scientific Research ProjectMDK-42745
Indian Head Agriculture Research Facility
Muscular Dystrophy Association
University of Regina
Canadian Space Agency

    Keywords

    • Global Sensitivity Analysis
    • Leaf Area Index
    • PolSAR
    • Polynomial Chaos Expansion
    • Regression

    Fingerprint

    Dive into the research topics of 'PRINCIPAL COMPONENT ANALYSIS BASED POLYNOMIAL CHAOS EXPANSION REGRESSION OF LEAF AREA INDEX FROM POLSAR IMAGERY'. Together they form a unique fingerprint.

    Cite this