elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Contact | Deutsch
Fontsize: [-] Text [+]

A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem

Bayer, Anita and Bachmann, Martin and Müller, Andreas and Kaufmann, Hermann (2012) A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem. Applied and Environmental Soil Science, 2012, pp. 1-20. Hindawi Publishing Corporation. DOI: 10.1155/2012/971252.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
5MB

Official URL: http://www.hindawi.com/journals/aess/2012/971252/

Abstract

The accurate assessment of selected soil constituents can provide valuable indicators to identify and monitor land changes coupled with degradation which are frequent phenomena in semiarid regions. Two approaches for the quantification of soil organic carbon, iron oxides, and clay content based on field and laboratory spectroscopy of natural surfaces are tested. (1) A physical approach which is based on spectral absorption feature analysis is applied. For every soil constituent, a set of diagnostic spectral features is selected and linked with chemical reference data by multiple linear regression (MLR) techniques. (2) Partial least squares regression (PLS) as an exclusively statistical multivariate method is applied for comparison. Regression models are developed based on extensive ground reference data of 163 sampled sites collected in the Thicket Biome, South Africa, where land changes are observed due to intensive overgrazing. The approaches are assessed upon their prediction performance and significance in regard to a future quantification of soil constituents over large areas using imaging spectroscopy.

Document Type:Article
Title:A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem
Authors:
AuthorsInstitution or Email of Authors
Bayer, Anitaanita.bayer@dlr.de
Bachmann, Martinmartin.bachmann@dlr.de
Müller, Andreasandreas.mueller@dlr.de
Kaufmann, Hermanncharly@gfz-potsdam.de
Date:2012
Journal or Publication Title:Applied and Environmental Soil Science
Refereed publication:Yes
In Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:No
Volume:2012
DOI:10.1155/2012/971252
Page Range:pp. 1-20
Publisher:Hindawi Publishing Corporation
Series Name:Quantitative Soil Spectroscopy
Status:Published
Keywords:Imaging Spectroscopy, Soil organic carbon, degradation, South Africa, Iron oxides, multiple linear regression analysis, partial least regression analysis
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben Fernerkundung der Landoberfläche
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Land Surface
Deposited By: Anita Daniela Bayer
Deposited On:28 Nov 2012 10:45
Last Modified:12 Dec 2013 21:50

Repository Staff Only: item control page

Browse
Search
Help & Contact
Informationen
electronic library is running on EPrints 3.3.12
Copyright © 2008-2012 German Aerospace Center (DLR). All rights reserved.