Ghent University Academic Bibliography

Advanced

Extracting topsoil information from EM38DD sensor data using a neural network approach

Liesbet Cockx UGent, Marc Van Meirvenne UGent, UWA Vitharana, Lieven Verbeke UGent, David Simpson UGent, Timothy Saey UGent and Friedl Vancoillie UGent (2009) SOIL SCIENCE SOCIETY OF AMERICA JOURNAL. 73(6). p.2051-2058
abstract
Electromagnetic induction soil sensors are an increasingly important source of secondary information to predict soil texture. In a 10.5-ha polder field, an EM38DD survey was performed with a resolution of 2 by 2 m and 78 soil samples were analyzed for sub- and topsoil texture. Due to the presence of former water channels in the subsoil, the coefficient of variation of the subsoil clay content (45%) was much larger compared with the topsoil (13%). The horizontal (ECa-H) and vertical (ECa-V) electrical conductivity measurements displayed a similar pattern, indicating a dominant influence of the subsoil features on both signals. To extract topsoil textural information from the depth-weighted EM38DD signals we turned to artificial neural networks (ANNs). We evaluated the effect of different input layers on the ability to predict the topsoil clay content. To identify the response of the topsoil, both EM38DD orientations were used. To examine the influence of the local neighborhood, contextual ECa information by means of a window around each soil sample was added to the input. The best ANN model used both ECa-H and ECa-V data but no contextual information: a mean squared estimation error of 2.83%(2) was achieved, explaining 65.5% of the topsoil clay variability with a variance of 0.052%2. So, with the help of ANNs, the prediction of the topsoil clay content was optimized through an integrated use of the two EM38DD signals.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
FIELD, CLASSIFICATION, MANAGEMENT ZONES, PRECISION AGRICULTURE, ELECTROMAGNETIC INDUCTION, SOIL ELECTRICAL-CONDUCTIVITY, MAPPING CLAY CONTENT, WATER, FLANDERS, BELGIUM
journal title
SOIL SCIENCE SOCIETY OF AMERICA JOURNAL
Soil Sci. Soc. Am. J.
volume
73
issue
6
pages
2051 - 2058
Web of Science type
Article
Web of Science id
000271752700036
JCR category
SOIL SCIENCE
JCR impact factor
2.179 (2009)
JCR rank
7/31 (2009)
JCR quartile
1 (2009)
ISSN
0361-5995
DOI
10.2136/sssaj2008.0277
language
English
UGent publication?
yes
classification
A1
id
781001
handle
http://hdl.handle.net/1854/LU-781001
date created
2009-11-16 10:56:28
date last changed
2011-09-15 14:15:00
@article{781001,
  abstract     = {Electromagnetic induction soil sensors are an increasingly important source of secondary information to predict soil texture. In a 10.5-ha polder field, an EM38DD survey was performed with a resolution of 2 by 2 m and 78 soil samples were analyzed for sub- and topsoil texture. Due to the presence of former water channels in the subsoil, the coefficient of variation of the subsoil clay content (45\%) was much larger compared with the topsoil (13\%). The horizontal (ECa-H) and vertical (ECa-V) electrical conductivity measurements displayed a similar pattern, indicating a dominant influence of the subsoil features on both signals. To extract topsoil textural information from the depth-weighted EM38DD signals we turned to artificial neural networks (ANNs). We evaluated the effect of different input layers on the ability to predict the topsoil clay content. To identify the response of the topsoil, both EM38DD orientations were used. To examine the influence of the local neighborhood, contextual ECa information by means of a window around each soil sample was added to the input. The best ANN model used both ECa-H and ECa-V data but no contextual information: a mean squared estimation error of 2.83\%(2) was achieved, explaining 65.5\% of the topsoil clay variability with a variance of 0.052\%2. So, with the help of ANNs, the prediction of the topsoil clay content was optimized through an integrated use of the two EM38DD signals.},
  author       = {Cockx, Liesbet and Van Meirvenne, Marc and Vitharana, UWA and Verbeke, Lieven and Simpson, David and Saey, Timothy and Vancoillie, Friedl},
  issn         = {0361-5995},
  journal      = {SOIL SCIENCE SOCIETY OF AMERICA JOURNAL},
  keyword      = {FIELD,CLASSIFICATION,MANAGEMENT ZONES,PRECISION AGRICULTURE,ELECTROMAGNETIC INDUCTION,SOIL ELECTRICAL-CONDUCTIVITY,MAPPING CLAY CONTENT,WATER,FLANDERS,BELGIUM},
  language     = {eng},
  number       = {6},
  pages        = {2051--2058},
  title        = {Extracting topsoil information from EM38DD sensor data using a neural network approach},
  url          = {http://dx.doi.org/10.2136/sssaj2008.0277},
  volume       = {73},
  year         = {2009},
}

Chicago
Cockx, Liesbet, Marc Van Meirvenne, UWA Vitharana, Lieven Verbeke, David Simpson, Timothy Saey, and Friedl Vancoillie. 2009. “Extracting Topsoil Information from EM38DD Sensor Data Using a Neural Network Approach.” Soil Science Society of America Journal 73 (6): 2051–2058.
APA
Cockx, Liesbet, Van Meirvenne, M., Vitharana, U., Verbeke, L., Simpson, D., Saey, T., & Vancoillie, F. (2009). Extracting topsoil information from EM38DD sensor data using a neural network approach. SOIL SCIENCE SOCIETY OF AMERICA JOURNAL, 73(6), 2051–2058.
Vancouver
1.
Cockx L, Van Meirvenne M, Vitharana U, Verbeke L, Simpson D, Saey T, et al. Extracting topsoil information from EM38DD sensor data using a neural network approach. SOIL SCIENCE SOCIETY OF AMERICA JOURNAL. 2009;73(6):2051–8.
MLA
Cockx, Liesbet, Marc Van Meirvenne, UWA Vitharana, et al. “Extracting Topsoil Information from EM38DD Sensor Data Using a Neural Network Approach.” SOIL SCIENCE SOCIETY OF AMERICA JOURNAL 73.6 (2009): 2051–2058. Print.