Automatically assigned DDC number:

Manually assigned DDC number: 00632

Title: Modeling and Predicting Sunspot Activity - State Space Reconstruction + Artificial Neural Network Methods

Author:

Author:

Subject: D. R. Kulkarni,J. C. Parikh Modeling and Predicting Sunspot Activity - State Space Reconstruction + Artificial Neural Network Methods

Description: . Ideas of state space reconstruction of dynamics are combined with nonparametric artificial neural network approach to model sunspot activity. The structural aspects of the model are for the most part determined from the sunspot data. The model gives a very good fit to the data. Further it predicts weaker solar activity in the current (23-rd) cycle, with a maximum of 144Sigma36. 1. Introduction The dynamics of solar activity as reflected in the variation of sunspot number is a complex phenomenon. Inspite of the great interest in this phenomenon there is as yet no dynamical theory which can make accurate predictions of sunspot number. As a consequence, historical data of the yearly average of the sunspot number has been used to make predictions employing various methods of time series analysis [Box and Jenkins, 1976; Weigend and Gershenfeld, 1994]. In this note, we also use the historical data to make predictions. As the data upto 1850 is not very reliable we use the yearly averag...

Contributor: The Pennsylvania State University CiteSeer Archives

Publisher: unknown

Date: 1998-02-02

Format: ps

Identifier: http://citeseer.ist.psu.edu/140330.html

Source: http://www.geophys.washington.edu/Space/GRL/articles/25/4/kulkarni/text.ps

Language: en

Rights: unrestricted

Graph

<?xml   version="1.0"   encoding="UTF-8"?>

<references_metadata>

      <rec   ID="SELF"   Type="SELF"   CiteSeer_Book="SELF"   CiteSeer_Volume="SELF"   Title="Modeling   and   Predicting   Sunspot   Activity   -   State   Space   Reconstruction   +   Artificial   Neural   Network   Methods"   />

</references_metadata>

www.000webhost.com