Research on Model of Predicting Irrigation Water Requirement Based on Kernel Method

DOI

10.2991/emeit.2012.296How to use a DOI?

Keywords

Irrigation water requirement, Prediction model, Nonlinear character extraction, Kernel canonical correlation analysis, Support vector machine

Abstract

Scientific irrigation is very important for saving water in agriculture, increasing output and benefit in our country. In this paper a method of nonlinear character extraction based on kernel canonical correlation analysis(KCCA) is presented in which information of soil and environment are input vectors of model. Nonlinear character are extracted by KCCA, then main character variables are determined which reflects the complex relationship between original input and output data and the array dimension of input data is simplified. At last the model based on least squares support vector machine (SVM) were completed. By comparing simulation results, precision and rapidity of the prediction model based on KCCA-SVM are higher than those of CCA-SVM and LS-SCM model. The experimental results show that the method is very effective.

Copyright

© 2012, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bingxiang ZHONG
PY  - 2012/09
DA  - 2012/09
TI  - Research on Model of Predicting Irrigation Water Requirement Based on Kernel Method
BT  - Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)
PB  - Atlantis Press
SP  - 1338
EP  - 1341
SN  - 1951-6851
UR  - https://doi.org/10.2991/emeit.2012.296
DO  - 10.2991/emeit.2012.296
ID  - ZHONG2012/09
ER  -