Use of genetic-algorithm-optimized back propagation neural network and ordinary kriging for predicting the spatial distribution of groundwater quality parameter
Lists
Only you see this
Abstract
This study focuses on applying the model of Genetic Algorithm optimized Back Propagation Neural Networks (GABPNN) to formulate the forecast methodology of groundwater quality parameter with spatial data as parameters. Back Propagation neural network (BPNN) is the basic arithmetic of this method. Genetic Algorithm (GA) was used to optimize the weights and biases of BPNN. The GABPNN was firstly introduced into spatial prediction of groundwater quality parameter in Langfang city (China) and it was compared with ordinary Kriging(OK). The groundwater quality parameter such as chloride was selected for the study, the performance of the models was found to be very good. The results of the GABPNN model application were that the regional prediction map of the optimal GABPNN model could describe the spatial distribution situation of groundwater quality parameter and that the predictive validity of the GABPNN model was better than that of ordinary Kriging. The result shows that the GABPNN model is a reasonable and feasible method for spatial distribution of groundwater quality parameter in Langfang city (China).
BibTeX
@inproceedings{li2013use,
author = {Jian Li and Zheng Zhang and Feng Yu and Xiumei Zhang},
title = {{Use of genetic-algorithm-optimized back propagation neural network and ordinary kriging for predicting the spatial distribution of groundwater quality parameter}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2013},
doi = {10.1117/12.2011857},
}Loading related content...