著者

水野 勝教 林 伸久 後藤 泰之 雪田 和人 一柳 勝宏 横水 康伸 松村 年郎

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌. B (ISSN:03854213)

巻号頁・発行日

vol.120, no.5, pp.665-671, 2000

被引用文献数

3

---

This paper describes an application of a neural network for estimating the ground rainfall from radar echo data. A neural network system for this purpose is developed through a case study on a dam for hydro-power plant located the upper district of the Ooi River in Central Japan. We use the neural network comprised of three layers; an input layer, a hidden layer and output layer. The input data to the neural network are any numebr of radar echo amount observed in each radar mesh and x-y-z coordinates showing its location.<br> The four types of neural networks with different number of input units are proposed and discussed the relative importance of the number of input data. It is found that the estimating system using the most simple neural network yields good results for rainfall distribution.