searching Engineering Collection Change databases

Image of Publication

  • Peer Reviewed
  • Citation only


about this publication

Comparison of multiple linear regressions and artificial intelligence-based modeling techniques for prediction the soil cation exchange capacity of Aridisols and Entisols in a semi-arid region

Australian Journal of Agricultural Engineering
Volume 3 Issue 2 (Jun 2012)

Abstract: The cation exchange capacity (CEC) of the soil is a basic chemical property, as it has been approved that the spatial distribution of CEC is important for decisions concerning pollution prevention and crop management. Since laboratory procedures for estimating CEC are cumbersome and time-consuming, it is essential to develop an indirect approach such as pedo-transfer functions (PTFs) for prediction this parameter from more readily available soil data. The aim of this study was to compare multiple linear regressions (MLR), adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) including multi-layer perceptron (MLP) and radial basis function (RBF) models to develop PTFs for predicting CEC of Aridisols and Entisols in Khuzestan province, southwest Iran. Five soil parameters including bulk density, calcium carbonate, organic carbon, clay and silt were considered as input variables for proposed models. The prediction capability of the models was evaluated by means of comparison with observed data through various descriptive statistical indicators including mean square error (MSE) and determination coefficient (R2) values. Results revealed that the MLP model (R2=0.83, MSE=0.008) had the most reliable prediction when compared with the other models. Also results indicated that the ANFIS model (R2=0.50, MSE=0.009) had approximately similar accuracy with those of MLR (R2=0.51, MSE=1.21), while, their prediction performance was less than RBF (R2=0.74, MSE=0.034) model. However, regarding to obtained statistical indicators, ANNs especially MLP model provide new methodology with acceptable accuracy to estimate the CEC of Aridisols and Entisols that diminished the engineering effort, time and funds.

To cite this article: Kalkhajeh, Yusef Kianpoor; Arshad, Ruhollah Rezaie; Amerikhah, Hadi and Sami, Moslem. Comparison of multiple linear regressions and artificial intelligence-based modeling techniques for prediction the soil cation exchange capacity of Aridisols and Entisols in a semi-arid region [online]. Australian Journal of Agricultural Engineering, Vol. 3, No. 2, Jun 2012: 39-46. Availability: <http://search.informit.com.au/documentSummary;dn=722203574735923;res=IELENG> ISSN: 1836-9448. [cited 28 Jun 16].

Personal Author: Kalkhajeh, Yusef Kianpoor; Arshad, Ruhollah Rezaie; Amerikhah, Hadi; Sami, Moslem; Source: Australian Journal of Agricultural Engineering, Vol. 3, No. 2, Jun 2012: 39-46 Document Type: Journal Article ISSN: 1836-9448 Subject: Information services--Security measures; Fuzzy systems--Design; Regression analysis; Soils--Analysis; Peer Reviewed: Yes Affiliation: (1) Department of Soil Science, Faculty of Agriculture, Shahid Chamran University, Ahvaz, Iran
(2) Department of Soil Science, Faculty of Agriculture, Shahid Chamran University, Ahvaz, Iran
(3) Department of Soil Science, Faculty of Agriculture, Shahid Chamran University, Ahvaz, Iran
(4) Department of Agricultural Machinery, Faculty of Agriculture, Shahid Chamran University, Ahvaz, Iran

Database: Engineering Collection