Neural network prediction of solar activity

Publisher Website
Google Scholar
Abstract
The neural network technique is used to analyze the time series of solar activity, as measured through the relative Wolf number. Firstly, the embedding dimension of the time-series c haracteristic attractor is obtained. Secondly, after describing the de sign and training of the net, the performance o f t he p resent approach in forecasting yearly mean sunspot numbers is favorably c ompared to that of conventional statistical methods. Finally, predictions for the remaining part of the 22th and the whole 23th cycle are presented.

This publication has 0 references indexed in Scilit: