Forecasting the 10.7-cm Solar Radio Flux Using Deep CNN-LSTM Neural Networks

Abstract

Predicting the time series of 10.7-cm solar radio flux is a challenging task because of its daily variability. This paper proposed a non-linear method, a convolutional and recurrent neural network combined model to achieve end-to-end F10.7 forecasts. The network consists of a one-dimensional convolutional neural network and a long short-term memory network. The CNN network extracted features from F10.7 original data, then trained the feature signals in the long short-term memory network, and outputted the predicted values. The F10.7 daily data during 2003–2014 are used for the testing set. The mean absolute percentage error values of approximately 2.04%, 2.78%, and 4.66% for 1-day, 3-day, and 7-day forecasts, respectively. The statistical results of evaluating the root mean square error, spearman correlation coefficient shows a superior effect as a whole for the 1–27 days forecast, compared with the ordinary single neural network and combination models.

Probabilistic Solar Proxy Forecasting With Neural Network Ensembles

“…The N-BEATS ensemble also achieved improved or similar performance when compared to the CNES (French Space Agency) CLS model, which is a shallow neural network based on 4 different radio flux wavelengths. Luo et al (2022) acknowledge the previous methods for forecasting F 10 rely heavily on linear methods and propose the usage of Convolutional Neural Networks (CNNs) and LSTMs. The usage of linear methods for forecasting F 10 results in relatively stable mid to long term predictions but fall short when high quality predictions on a smaller horizon are required.…”

“…These varied methods have produced a variety of conclusions, some models claim that linear methods outperform neural networks seen in Huang et al (2009), Warren et al (2017). Other authors have claimed that they can use machine learning methods to outperform linear methods like Luo et al (2022), Stevenson et al (2022). Methods, such as these, must be carefully compared in order to reduce contradictory conclusions.…”

“…Other authors have claimed that they can use machine learning methods to outperform linear methods like Luo et al. (2022), Stevenson et al. (2022).…”

“…Luo et al. (2022) acknowledge the previous methods for forecasting F 10 rely heavily on linear methods and propose the usage of Convolutional Neural Networks (CNNs) and LSTMs. The usage of linear methods for forecasting F 10 results in relatively stable mid to long term predictions but fall short when high quality predictions on a smaller horizon are required.…”

F10.7 Daily Forecast Using LSTM Combined With VMD Method

“…Xiao et al (2017) employed a Back Propagation Neural Network to predict the F 10.7 index, which exhibited better short-term prediction accuracy compared to other models. Luo et al (2022) combined Convolutional Neural Networks with Long Short-Term Memory (LSTM) to predict the value of F 10.7 for the next 27 days, spanning from 2003 to 2014. Gao et al (2022) combined the sunspots number into LSTM to make a short-term prediction method for F 10.7 in the next 7 days based on a 54-day solar radiation flux index, with a root mean square error (RMSE) 11% lower than that of the Space Weather Prediction Center (SWPC) in America.…”