Digital mapping of soil texture using radarsat-2 polarimetric synthetic aperture radar data

Mohamed Niang, Michel C. Nolin, Guillaume Jégo, Isabelle Perron

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This study aimed to assess the contribution of RADARSAT-2 polarimetric synthetic aperture radar (SAR) data to digital mapping of soil surface texture of Rouville County, near Montreal, Canada. First, compositional data transformation using isometric log ratio (ilr) was applied to soil texture data to transpose the simplex into multidimensional real space, which is better suited to multivariate analysis. Thereafter, two assumptions on the relationships between RADARSAT-2 data and the ilr components were evaluated: (i) as linearly dependent by applying cokriging (CK) and regression kriging (RK); and (ii) as nonlinearly dependent by applying the ε-insensitive and nonlinear support vector regression (SVR). The results were compared with ordinary kriging (OK). The environmental variables used to define the covariates were monopolarization SAR channels, the parameters extracted from entropy/anisotropy/ mean α polarimetric, Freeman and Durden, and Touzi decompositions. Using 283 soil samples for training and 89 for validation, the results showed that the root mean square error (RMSE) of prediction obtained by OK was 8% for silt, 13% for clay, and 13% for sand. The SVR produced the best prediction accuracy compared with the geostatistical interpolation techniques. Compared with OK, the improvement of the digital mapping accuracies (in terms of RMSE reduction) with SVR was significant: RMSE was reduced by 18% for sand, 17% for silt, and 35% for clay. It was followed by RK, with RMSE reduction ranging from 6 to 13%, and then CK (3-5%). Using SAR polarimetric data extracted from a RADARSAT-2 image as covariates was found to be very useful for digital mapping of soil surface texture.

Original languageEnglish
Pages (from-to)673-684
Number of pages12
JournalSoil Science Society of America Journal
Volume78
Issue number2
DOIs
Publication statusPublished - 1 Jan 2014

Fingerprint

synthetic aperture radar
digital mapping
kriging
soil texture
RADARSAT
soil surveys
silt
soil surface
texture
clay
sand
prediction
entropy
multivariate analysis
interpolation
anisotropy
soil sampling
Canada
decomposition
environmental factors

ASJC Scopus subject areas

  • Soil Science

Cite this

Digital mapping of soil texture using radarsat-2 polarimetric synthetic aperture radar data. / Niang, Mohamed; Nolin, Michel C.; Jégo, Guillaume; Perron, Isabelle.

In: Soil Science Society of America Journal, Vol. 78, No. 2, 01.01.2014, p. 673-684.

Research output: Contribution to journalArticle

Niang, Mohamed ; Nolin, Michel C. ; Jégo, Guillaume ; Perron, Isabelle. / Digital mapping of soil texture using radarsat-2 polarimetric synthetic aperture radar data. In: Soil Science Society of America Journal. 2014 ; Vol. 78, No. 2. pp. 673-684.
@article{b3d7f560da8d459a8c2960e8636a9ab5,
title = "Digital mapping of soil texture using radarsat-2 polarimetric synthetic aperture radar data",
abstract = "This study aimed to assess the contribution of RADARSAT-2 polarimetric synthetic aperture radar (SAR) data to digital mapping of soil surface texture of Rouville County, near Montreal, Canada. First, compositional data transformation using isometric log ratio (ilr) was applied to soil texture data to transpose the simplex into multidimensional real space, which is better suited to multivariate analysis. Thereafter, two assumptions on the relationships between RADARSAT-2 data and the ilr components were evaluated: (i) as linearly dependent by applying cokriging (CK) and regression kriging (RK); and (ii) as nonlinearly dependent by applying the ε-insensitive and nonlinear support vector regression (SVR). The results were compared with ordinary kriging (OK). The environmental variables used to define the covariates were monopolarization SAR channels, the parameters extracted from entropy/anisotropy/ mean α polarimetric, Freeman and Durden, and Touzi decompositions. Using 283 soil samples for training and 89 for validation, the results showed that the root mean square error (RMSE) of prediction obtained by OK was 8{\%} for silt, 13{\%} for clay, and 13{\%} for sand. The SVR produced the best prediction accuracy compared with the geostatistical interpolation techniques. Compared with OK, the improvement of the digital mapping accuracies (in terms of RMSE reduction) with SVR was significant: RMSE was reduced by 18{\%} for sand, 17{\%} for silt, and 35{\%} for clay. It was followed by RK, with RMSE reduction ranging from 6 to 13{\%}, and then CK (3-5{\%}). Using SAR polarimetric data extracted from a RADARSAT-2 image as covariates was found to be very useful for digital mapping of soil surface texture.",
author = "Mohamed Niang and Nolin, {Michel C.} and Guillaume J{\'e}go and Isabelle Perron",
year = "2014",
month = "1",
day = "1",
doi = "10.2136/sssaj2013.07.0307",
language = "English",
volume = "78",
pages = "673--684",
journal = "Soil Science Society of America Journal",
issn = "0361-5995",
publisher = "Soil Science Society of America",
number = "2",

}

TY - JOUR

T1 - Digital mapping of soil texture using radarsat-2 polarimetric synthetic aperture radar data

AU - Niang, Mohamed

AU - Nolin, Michel C.

AU - Jégo, Guillaume

AU - Perron, Isabelle

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This study aimed to assess the contribution of RADARSAT-2 polarimetric synthetic aperture radar (SAR) data to digital mapping of soil surface texture of Rouville County, near Montreal, Canada. First, compositional data transformation using isometric log ratio (ilr) was applied to soil texture data to transpose the simplex into multidimensional real space, which is better suited to multivariate analysis. Thereafter, two assumptions on the relationships between RADARSAT-2 data and the ilr components were evaluated: (i) as linearly dependent by applying cokriging (CK) and regression kriging (RK); and (ii) as nonlinearly dependent by applying the ε-insensitive and nonlinear support vector regression (SVR). The results were compared with ordinary kriging (OK). The environmental variables used to define the covariates were monopolarization SAR channels, the parameters extracted from entropy/anisotropy/ mean α polarimetric, Freeman and Durden, and Touzi decompositions. Using 283 soil samples for training and 89 for validation, the results showed that the root mean square error (RMSE) of prediction obtained by OK was 8% for silt, 13% for clay, and 13% for sand. The SVR produced the best prediction accuracy compared with the geostatistical interpolation techniques. Compared with OK, the improvement of the digital mapping accuracies (in terms of RMSE reduction) with SVR was significant: RMSE was reduced by 18% for sand, 17% for silt, and 35% for clay. It was followed by RK, with RMSE reduction ranging from 6 to 13%, and then CK (3-5%). Using SAR polarimetric data extracted from a RADARSAT-2 image as covariates was found to be very useful for digital mapping of soil surface texture.

AB - This study aimed to assess the contribution of RADARSAT-2 polarimetric synthetic aperture radar (SAR) data to digital mapping of soil surface texture of Rouville County, near Montreal, Canada. First, compositional data transformation using isometric log ratio (ilr) was applied to soil texture data to transpose the simplex into multidimensional real space, which is better suited to multivariate analysis. Thereafter, two assumptions on the relationships between RADARSAT-2 data and the ilr components were evaluated: (i) as linearly dependent by applying cokriging (CK) and regression kriging (RK); and (ii) as nonlinearly dependent by applying the ε-insensitive and nonlinear support vector regression (SVR). The results were compared with ordinary kriging (OK). The environmental variables used to define the covariates were monopolarization SAR channels, the parameters extracted from entropy/anisotropy/ mean α polarimetric, Freeman and Durden, and Touzi decompositions. Using 283 soil samples for training and 89 for validation, the results showed that the root mean square error (RMSE) of prediction obtained by OK was 8% for silt, 13% for clay, and 13% for sand. The SVR produced the best prediction accuracy compared with the geostatistical interpolation techniques. Compared with OK, the improvement of the digital mapping accuracies (in terms of RMSE reduction) with SVR was significant: RMSE was reduced by 18% for sand, 17% for silt, and 35% for clay. It was followed by RK, with RMSE reduction ranging from 6 to 13%, and then CK (3-5%). Using SAR polarimetric data extracted from a RADARSAT-2 image as covariates was found to be very useful for digital mapping of soil surface texture.

UR - http://www.scopus.com/inward/record.url?scp=84901791338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901791338&partnerID=8YFLogxK

U2 - 10.2136/sssaj2013.07.0307

DO - 10.2136/sssaj2013.07.0307

M3 - Article

AN - SCOPUS:84901791338

VL - 78

SP - 673

EP - 684

JO - Soil Science Society of America Journal

JF - Soil Science Society of America Journal

SN - 0361-5995

IS - 2

ER -