Sunspot number time series prediction using neural networks with quantum gate nodes

Abstract

Sunspot is one of the most basic and obvious activity occurred in the solar photosphere, the number of sunspot have great influence on the production and life as well as climate change. Therefore, studying and predicting of sunspots have important meaning. Aiming at the problem of highly nonlinear in sunspot number and the conventional methods are difficult to convergence, a new prediction method based on neural network with quantum gate is proposed to improve the accuracy of the forecast for Sunspot number time series. The input data is expressed by the qubit, which rotated by the rotation gate, as the control qubits control the hidden layer qubits reverse. In the same way, the hidden layer qubits control the output layer. At last, the probability amplitude of state |1> is regarded as the network output. This proposed method has such advantages as high precision and strong generalization ability, and it is a new promising approach for solving time series prediction problem of sunspot number.