Presentation 1994/7/25
Local Weather Prediction System by Neural Networks
Satoru Koumura, Yasushi Matsuda, Yoshihiko Sekine, Yasunari Shidama, Hiroo Yamaura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Numerical prediction modelling is now a main numerical analysis of weather prediction system in Japan,but it is not fit for local weather prediction,for the distance between two grid points is at least 30 kilometers.We tried to build up a local weather prediction system by a 4-layered neural network. As a result we obtained suitable wind speed and direction in Haneda with pressure in 4 station points(Akita,Hachijo-shima, Choshi and Omaezaki)as a main element.This method is effective as a new weather prediction system in the limited period.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Weather Prediction
Paper # NC94-27
Date of Issue

Conference Information
Committee NC
Conference Date 1994/7/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Local Weather Prediction System by Neural Networks
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Weather Prediction
1st Author's Name Satoru Koumura
1st Author's Affiliation Graduate School of Science and Technology,Shinshu University()
2nd Author's Name Yasushi Matsuda
2nd Author's Affiliation Graduate School of Bioresources,Mie University
3rd Author's Name Yoshihiko Sekine
3rd Author's Affiliation Faculty of Bioresources,Mie University
4th Author's Name Yasunari Shidama
4th Author's Affiliation Faculty of Engineering,Shinshu University
5th Author's Name Hiroo Yamaura
5th Author's Affiliation Faculty of Engineering,Shinshu University
Date 1994/7/25
Paper # NC94-27
Volume (vol) vol.94
Number (no) 182
Page pp.pp.-
#Pages 8
Date of Issue