Predicting soil engineering parameters from spectral data using PLSR

F. A. Yitagesu, F. D. Van Der Meer, H. Van Der Werff, I. W. Zigterman

Research output: Contribution to conferencePaperAcademicpeer-review

Abstract

Expansive soils give rise to major problems that need due attention in geo-technical investigations. Their characteristic to undergo large volume changes upon wetting and drying, has serious implications on the planning, design, construction, maintenance, and overall performance especially of lightweight civil engineering infrastructures. For this study, 80 soil samples were collected from the eastern part of Addis Ababa city. Specific expansive soil engineering parameters namely; Atterberg limits (liquid limits, plastic limits and plasticity indices), free swell and cation exchange capacity were measured in a soil mechanics laboratory. Reflectance spectra of each soil sample were acquired using the ASD fieldspec spectrometer. A multivariate calibration method, partial least squares regression (PLSR) analysis, through simple wavelength approach, was used to construct empirical prediction models that enable the estimation of engineering parameters of expansive soils from their reflectance spectra. Correlation coefficients obtained showed that a large portion of the variation in the engineering parameters (using full spectral band sets R=0.90, 0.87, 0.71, 0.81 and 0.71 for CEC, LL, PL, PI and FS respectively) could be accounted for by the spectral parameters. The results of the prediction models are high, indicating the potential of spectroscopy in deriving engineering parameters of expansive soils from their respective reflectance spectra, and hence its potential applicability in the geotechnical investigations of such soils.

Original languageEnglish
Pages589-593
Number of pages5
Publication statusPublished - 1 Dec 2007
Event32nd International Symposium on Remote Sensing of Environment 2007: Sustainable Development Through Global Earth Observations - San Jose, Costa Rica
Duration: 25 Jun 200729 Jun 2007
Conference number: 32

Conference

Conference32nd International Symposium on Remote Sensing of Environment 2007
Abbreviated titleISRSE 2007
CountryCosta Rica
CitySan Jose
Period25/06/0729/06/07

Fingerprint

Soils
Soil mechanics
Civil engineering
Regression analysis
Plasticity
Wetting
Spectrometers
Ion exchange
Drying
Positive ions
Spectroscopy
Calibration
Plastics
Planning
Wavelength
Liquids

Keywords

  • Engineering parameters
  • PLSR
  • Spectroscopy

Cite this

Yitagesu, F. A., Van Der Meer, F. D., Van Der Werff, H., & Zigterman, I. W. (2007). Predicting soil engineering parameters from spectral data using PLSR. 589-593. Paper presented at 32nd International Symposium on Remote Sensing of Environment 2007, San Jose, Costa Rica.
Yitagesu, F. A. ; Van Der Meer, F. D. ; Van Der Werff, H. ; Zigterman, I. W. / Predicting soil engineering parameters from spectral data using PLSR. Paper presented at 32nd International Symposium on Remote Sensing of Environment 2007, San Jose, Costa Rica.5 p.
@conference{fe4957de2ed544618d9e00b51fbb9769,
title = "Predicting soil engineering parameters from spectral data using PLSR",
abstract = "Expansive soils give rise to major problems that need due attention in geo-technical investigations. Their characteristic to undergo large volume changes upon wetting and drying, has serious implications on the planning, design, construction, maintenance, and overall performance especially of lightweight civil engineering infrastructures. For this study, 80 soil samples were collected from the eastern part of Addis Ababa city. Specific expansive soil engineering parameters namely; Atterberg limits (liquid limits, plastic limits and plasticity indices), free swell and cation exchange capacity were measured in a soil mechanics laboratory. Reflectance spectra of each soil sample were acquired using the ASD fieldspec spectrometer. A multivariate calibration method, partial least squares regression (PLSR) analysis, through simple wavelength approach, was used to construct empirical prediction models that enable the estimation of engineering parameters of expansive soils from their reflectance spectra. Correlation coefficients obtained showed that a large portion of the variation in the engineering parameters (using full spectral band sets R=0.90, 0.87, 0.71, 0.81 and 0.71 for CEC, LL, PL, PI and FS respectively) could be accounted for by the spectral parameters. The results of the prediction models are high, indicating the potential of spectroscopy in deriving engineering parameters of expansive soils from their respective reflectance spectra, and hence its potential applicability in the geotechnical investigations of such soils.",
keywords = "Engineering parameters, PLSR, Spectroscopy",
author = "Yitagesu, {F. A.} and {Van Der Meer}, {F. D.} and {Van Der Werff}, H. and Zigterman, {I. W.}",
year = "2007",
month = "12",
day = "1",
language = "English",
pages = "589--593",
note = "32nd International Symposium on Remote Sensing of Environment 2007 : Sustainable Development Through Global Earth Observations, ISRSE 2007 ; Conference date: 25-06-2007 Through 29-06-2007",

}

Yitagesu, FA, Van Der Meer, FD, Van Der Werff, H & Zigterman, IW 2007, 'Predicting soil engineering parameters from spectral data using PLSR' Paper presented at 32nd International Symposium on Remote Sensing of Environment 2007, San Jose, Costa Rica, 25/06/07 - 29/06/07, pp. 589-593.

Predicting soil engineering parameters from spectral data using PLSR. / Yitagesu, F. A.; Van Der Meer, F. D.; Van Der Werff, H.; Zigterman, I. W.

2007. 589-593 Paper presented at 32nd International Symposium on Remote Sensing of Environment 2007, San Jose, Costa Rica.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - Predicting soil engineering parameters from spectral data using PLSR

AU - Yitagesu, F. A.

AU - Van Der Meer, F. D.

AU - Van Der Werff, H.

AU - Zigterman, I. W.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Expansive soils give rise to major problems that need due attention in geo-technical investigations. Their characteristic to undergo large volume changes upon wetting and drying, has serious implications on the planning, design, construction, maintenance, and overall performance especially of lightweight civil engineering infrastructures. For this study, 80 soil samples were collected from the eastern part of Addis Ababa city. Specific expansive soil engineering parameters namely; Atterberg limits (liquid limits, plastic limits and plasticity indices), free swell and cation exchange capacity were measured in a soil mechanics laboratory. Reflectance spectra of each soil sample were acquired using the ASD fieldspec spectrometer. A multivariate calibration method, partial least squares regression (PLSR) analysis, through simple wavelength approach, was used to construct empirical prediction models that enable the estimation of engineering parameters of expansive soils from their reflectance spectra. Correlation coefficients obtained showed that a large portion of the variation in the engineering parameters (using full spectral band sets R=0.90, 0.87, 0.71, 0.81 and 0.71 for CEC, LL, PL, PI and FS respectively) could be accounted for by the spectral parameters. The results of the prediction models are high, indicating the potential of spectroscopy in deriving engineering parameters of expansive soils from their respective reflectance spectra, and hence its potential applicability in the geotechnical investigations of such soils.

AB - Expansive soils give rise to major problems that need due attention in geo-technical investigations. Their characteristic to undergo large volume changes upon wetting and drying, has serious implications on the planning, design, construction, maintenance, and overall performance especially of lightweight civil engineering infrastructures. For this study, 80 soil samples were collected from the eastern part of Addis Ababa city. Specific expansive soil engineering parameters namely; Atterberg limits (liquid limits, plastic limits and plasticity indices), free swell and cation exchange capacity were measured in a soil mechanics laboratory. Reflectance spectra of each soil sample were acquired using the ASD fieldspec spectrometer. A multivariate calibration method, partial least squares regression (PLSR) analysis, through simple wavelength approach, was used to construct empirical prediction models that enable the estimation of engineering parameters of expansive soils from their reflectance spectra. Correlation coefficients obtained showed that a large portion of the variation in the engineering parameters (using full spectral band sets R=0.90, 0.87, 0.71, 0.81 and 0.71 for CEC, LL, PL, PI and FS respectively) could be accounted for by the spectral parameters. The results of the prediction models are high, indicating the potential of spectroscopy in deriving engineering parameters of expansive soils from their respective reflectance spectra, and hence its potential applicability in the geotechnical investigations of such soils.

KW - Engineering parameters

KW - PLSR

KW - Spectroscopy

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2007/conf/vandermeer_pre.pdf

M3 - Paper

SP - 589

EP - 593

ER -

Yitagesu FA, Van Der Meer FD, Van Der Werff H, Zigterman IW. Predicting soil engineering parameters from spectral data using PLSR. 2007. Paper presented at 32nd International Symposium on Remote Sensing of Environment 2007, San Jose, Costa Rica.