Advanced

Predicting the dielectric constant-water content relationship using artificial neural networks

Persson, Magnus LU ; Sivakumar, B; Berndtsson, Ronny LU ; Jacobsen, OH and Schjonning, P (2002) In Soil Science Society of America Journal 66(5). p.1424-1429
Abstract
Accurate measurements of soil water content (theta) are important in various applications in hydrology and soil science. The time domain reflectometry (TDR) technique has been widely used for theta measurements during the last two decades. The TDR utilizes the apparent dielectric constant (K-s) for estimations of theta. The K-a-theta relationship has been described using both empirical and physical models. Universal calibration equations that fit a wide range of different soil types have been developed. However, to achieve high accuracy, a soil-specific calibration needs to be conducted. In the present study, we use an artificial neural network(ANN) to predict the K-a-theta relationship using soil physical parameters for ten different soil... (More)
Accurate measurements of soil water content (theta) are important in various applications in hydrology and soil science. The time domain reflectometry (TDR) technique has been widely used for theta measurements during the last two decades. The TDR utilizes the apparent dielectric constant (K-s) for estimations of theta. The K-a-theta relationship has been described using both empirical and physical models. Universal calibration equations that fit a wide range of different soil types have been developed. However, to achieve high accuracy, a soil-specific calibration needs to be conducted. In the present study, we use an artificial neural network(ANN) to predict the K-a-theta relationship using soil physical parameters for ten different soil types. The parameters that give the most significant reduction in the root mean square error (RMSE) are bulk density, clay content, and organic matter content. The K-a-theta relationship for each soil type is predicted using the other nine for calibration. It is shown that ANN predictions are as good as a soil specific calibration with comparable coefficient of determination and RMSE. Thus, by using ANN, highly accurate data can be obtained without need for elaborate soil specific calibration experiments. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Soil Science Society of America Journal
volume
66
issue
5
pages
1424 - 1429
publisher
Soil Science Society of Americ
external identifiers
  • wos:000177977100002
  • scopus:0013390676
ISSN
0361-5995
DOI
10.2136/sssaj2002.1424
language
English
LU publication?
yes
id
37737d57-b30d-4984-be02-3f109e8232e1 (old id 327824)
date added to LUP
2007-11-08 13:54:52
date last changed
2017-09-03 04:36:38
@article{37737d57-b30d-4984-be02-3f109e8232e1,
  abstract     = {Accurate measurements of soil water content (theta) are important in various applications in hydrology and soil science. The time domain reflectometry (TDR) technique has been widely used for theta measurements during the last two decades. The TDR utilizes the apparent dielectric constant (K-s) for estimations of theta. The K-a-theta relationship has been described using both empirical and physical models. Universal calibration equations that fit a wide range of different soil types have been developed. However, to achieve high accuracy, a soil-specific calibration needs to be conducted. In the present study, we use an artificial neural network(ANN) to predict the K-a-theta relationship using soil physical parameters for ten different soil types. The parameters that give the most significant reduction in the root mean square error (RMSE) are bulk density, clay content, and organic matter content. The K-a-theta relationship for each soil type is predicted using the other nine for calibration. It is shown that ANN predictions are as good as a soil specific calibration with comparable coefficient of determination and RMSE. Thus, by using ANN, highly accurate data can be obtained without need for elaborate soil specific calibration experiments.},
  author       = {Persson, Magnus and Sivakumar, B and Berndtsson, Ronny and Jacobsen, OH and Schjonning, P},
  issn         = {0361-5995},
  language     = {eng},
  number       = {5},
  pages        = {1424--1429},
  publisher    = {Soil Science Society of Americ},
  series       = {Soil Science Society of America Journal},
  title        = {Predicting the dielectric constant-water content relationship using artificial neural networks},
  url          = {http://dx.doi.org/10.2136/sssaj2002.1424},
  volume       = {66},
  year         = {2002},
}