Mathematical model of soil cation exchange capacity using GMDH-type neural network and genetic algorithm

Journal Title: Agricultural Advances - Year 2014, Vol 3, Issue 4

Abstract

Measuring the cation exchange capacity (CEC) for all horizons of every map unit component in a survey area is very time consuming and costly. This study was conducted (i) to evaluate the group method of data handling (GMDH) neural network (NN) and genetic algorithm model and (ii) to compare GMDH-type NN with other artificial neural networks such as the multilayer perceptron (MLP), radial basis function (RBF) and regression-based models for predicting CEC in soils of Lahijan, north of Iran. In this paper, the proposed model was trained before requested predictions. The data set was divided into two parts: 70% were used as data for training (110 soil samples), and 30% (40 soil samples) were used as a test set, which were randomly extracted from the database. In order to evaluate the models, coefficient of determination (R2), mean square error (MSE), root mean square error (RMSE) and mean absolute deviation (MAD) were used. Results showed that the GMDH-type and MLP NN models had larger R2 values than the multiple regression and RBF models. The results of GMDH model were very encouraging and congruent with the experimental results. In general, the GMDH-type-NNs models provided more reliable predictions than the ANNs and regression-based models.

Authors and Affiliations

A. Bazrafshan*| Department of Soil Science, Faculty of Agriculture, University of Guilan, Rasht, Iran., M. Shabanpour| Department of Soil Science, Faculty of Agriculture, University of Guilan, Rasht, Iran., M. Norouzi| Department of Soil Science, Faculty of Agriculture, University of Guilan, Rasht, Iran., S. Fallahi| Department of Mathematics, Faculty of Sciences, University of Guilan, Rasht, Iran.

Keywords

Related Articles

Recent developments in diagnosis and management of nutrients constraints in acid lime

Acidlime is considered highly nutrient responsive crop. Occurrence of multiple nutrient deficienciesmakes the redressal of such nutrient deficiencies all the more complexexercise. Site specific nutrient management stu...

Genetic diversity of barley verities by RAPD markers

The fourteen barleyverities were studied by RAPD markersto assessment of their genetic diversity. From 40 used primers, 17 primersestablished suitable banding patterns. Totally, 435 bands were produced between564- 41...

Determination of larval development stages in beluga (Huso huso Linnaeus, 1758)

The study of egg andlarvae stages tn fishes is one of new fields in Ichthyology. There are manychanges in larvae stage and the study of fish bio-history can provide someinformation about the changes of this stage to us...

Symptomatology, survey and surveillance of citrus gummosis disease caused by Phytophthora spp.

An extensive roving survey was conducted in different districts of Marathwada region of Maharashtra state to isolate the pathogen associated with the gummosis of sweet orange. In all 103 sweet orange orchards surveyed...

Modern technologies and Nigerian’s small scale farmers: constraints and prospects of its adoption

In spite of abundant modern technologies and guide lines available for use in increasing Agricultural productivity, most of the Nigeria small scale farmers who constitute the majority in agricultural sector cannot adop...

Download PDF file
  • EP ID EP547
  • DOI 10.14196/aa.v3i4.1267
  • Views 430
  • Downloads 20

How To Cite

A. Bazrafshan*, M. Shabanpour, M. Norouzi, S. Fallahi (2014). Mathematical model of soil cation exchange capacity using GMDH-type neural network and genetic algorithm. Agricultural Advances, 3(4), 111-123. https://europub.co.uk/articles/-A-547