A Machine Learning Approach for Predicting the Sunspot of Solar Cycle

Abstract

Sunspots are the fascinating things on the periphery which is the reason it would be all the more captivating if sunspots become predictable. Sunspot number (SSN) is used in this regard to predicting the Solar Cycle (SC) 25 using the data set containing data from the year of 1818. This is work mainly a representation of Artificial Neural Network (ANN) for predicting the Solar Cycle (SC). For time series related data set as well as continuous data set the main issue is gap length of the data set. Long Short Term Memory (LSTM) network can handle this type of continuous dataset also capable of learning long term dependencies as well. This work mainly detaches various sunspot numbers (SSN) for measuring the Solar Cycle (SC) 25. Like other sunspot numbers (SSN) prediction method this work is not splitting the data set into many parts for analyzing. This result is propulsion for disclosing various differences as well as influence. This model is one of the most effective time series model for measuring the Solar Cycle (SC) 25 compared with other predicted models of time series.