Analysis of Hydrological Data Based on BP Neural Network Approximation and Polynomial Fitting

Shou Jun Li; Xiao Ping Ma; Hong Yu

doi:10.4028/www.scientific.net/AMR.518-523.4115

Paper Titles

The Multi-Objective Differential Evolutionary Algorithms and its Application in Optimal Allocation of Water Resources
p.4093

To Classify the Groundwater Hydrographs by Factor Analysis Method
p.4097

Advancement in Research of Hydrological Processes Simulation for Karst Region and Future Challenges
p.4104

Analysis and Comparison on Typical Methods for Predicting Composite Roughness of River
p.4111

Analysis of Hydrological Data Based on BP Neural Network Approximation and Polynomial Fitting
p.4115

Analysis of Interactions between Surface Water and Groundwater by Using Water Chemistry and δD, δ¹⁸O — Case Study of Bulang River Basin
p.4119

Analysis of Legal System and Public Policy on Rural Water Source in China
p.4126

Analysis on Reinjecting Modes in Geothermal Well of Porous Aquifer
p.4130

Application of Fuzzy Matter-Element Model Based on Cooperative Game Weight in Evaluation of Groundwater Carrying Capacity
p.4135

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 518-523Analysis of Hydrological Data Based on BP Neural...

Analysis of Hydrological Data Based on BP Neural Network Approximation and Polynomial Fitting

Abstract:

It is an important means of hydrological data analysis for drawing hydrological data curve. The paper conducts a study on drawing method of stage-discharge curve in two aspects including BP neural network approximation and curve fitting, according to data extracted from a hydrologic station located in Suqian section of Beijing-Hangzhou Canal. Normalization of the input sample is processed in order to caculate conveniently and prevent partial neurons to supersaturate. Then, neuronal number is determined by method of heuristics. And the transfer function and training function are finalized on the premise of target error 0.0001.Error analysis is performed after simulation of BP network approximation. 2- and 3-order curve fitting is done based on principle of least squares of polynomial fitting, then followed by error analysis. Comparison of both methods comes to the conclusion that approximation of BP network for a given data is more accurate than that of curve fitting.

You might also be interested in these eBooks

Advances in Environmental Science and Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 518-523)

Pages:

4115-4118

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.518-523.4115

Citation:

Cite this paper

Online since:

May 2012

Authors:

Shou Jun Li, Xiao Ping Ma, Hong Yu

Keywords:

Approximation of BP Network, Curve Fitting, Error Analysis, Hydrological Data, MATLAB

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Caili Wu, Bin Huang: China Rural Water and Hydropower, 2008(5),pp.71-74, in Chinese.

Google Scholar

[2] Xiaoyun Lei, Lixia ZHANG, Xinping Liang: Journal of China Hydrology, 2008(2),pp.43-46.

Google Scholar

[3] Xufan Cao, Zhou Ye, Jun Wan: Neural Network, 2008(5),pp.34-38, in Chinese.

Google Scholar

[4] Yunbin: Safety in Coal Mines, Xidian University of Science& Technology Press,2008.

Google Scholar

[5] Zhexu Hou,Zhiqiang Sun: Neural Network Theory and its Realization Based on MATLAB R2007, Publishing House of Electronics Industry,2007,in Chinese

Google Scholar

[6] Jiusheng Li,R. E. Yoder,L. O. Odhiambo,J. Zhang: Irrigation Science, 2004(1), pp.23-26

Google Scholar

[7] Odhiambo L O, Yoder R E, Mines J W: Transactions of the ASAE, 2001, 44 (6),pp.1625-1633

Google Scholar

[8] Jiusheng Li,R E Yoder,L O Odhiambo,J Zhang: Irrigation Science, 2004(23) ,pp.29-37

Google Scholar

[9] Choueiki M H, Mount-Campbell C A: IEEE Trans Neural Networks, 1999(10) ,pp.55-63

Google Scholar