A modular neural network approach for locating cloud-to-ground lightning strokes

Author

Emamghoreishi, S.A. ; Moini, R. ; Sadeghi, S.H.H.

Author_Institution

Electromagn. Res. Lab., Amirkabir Univ. of Technol., Tehran, Iran

Volume

2

fYear

2001

fDate

2001

Firstpage

1042

Abstract

A modular neuro-based approach is proposed for locating cloud-to-ground lightning strokes. The locating process is done in two stages. In the first stage, a multi-layer perceptron feed forward network with one hidden layer is used to estimate the location range of the return stroke channel (RSC). The estimated value of the RSC location range at the output of the first stage determines the appropriate ANN trained for three near (1-10 km), intermediate (10-20 km), and far (20-80 km) zones. The simulation results demonstrate that the RSC locations can be predicted with an absolute error not greater than 1 km and a relative error less than 5%

Keywords

atmospheric techniques; electromagnetic fields; feedforward neural nets; geophysics computing; lightning; multilayer perceptrons; 1 to 80 km; cloud-to-ground lightning strokes location; hidden layer; lightning electromagnetic field simulator; modular neural network approach; multi-layer perceptron feed forward network; return stroke channel locations prediction; Artificial neural networks; Computational modeling; Electromagnetic fields; Electromagnetic measurements; Feeds; Laboratories; Lightning; Multilayer perceptrons; Neural networks; Predictive models;

fLanguage

English

Publisher

ieee

Conference_Titel

Electromagnetic Compatibility, 2001. EMC. 2001 IEEE International Symposium on

Conference_Location

Montreal, Que.

Print_ISBN

0-7803-6569-0

Type

conf

DOI

10.1109/ISEMC.2001.950547

Filename

950547