Application of Deep Learning to Solar and Space Weather Data: 4. Generation Denoised Solar Magnetograms

In this study, we apply a deep learning model to denoising solar magnetograms. For this, we design a model based on conditional generative adversarial network (cGAN), which is one of the deep learning algorithms, for the image-to-image translation from a single magnetogram to a denoised magnetogram. For the single magnetogram, we use SDO/HMI line-of-sight magnetograms at the center of solar disk, and for the denoised magnetogram, we make 21-frame-stacked magnetograms at the center of solar disk. We train a model using 6702 pairs of the single and denoised magnetograms from 2013 January to 2013 October and evaluate the model using 1370 pairs from 2013 November to 2013 December. Our results from this study are as follows. First, our model successfully denoise SDO/HMI magnetograms. Second, the average pixel-to-pixel correlation coefficient between denoised magnetograms and stacked magnetograms is larger than 0.92, and the correlation coefficient of total unsigned magnetic flux between two magnetograms is larger than 0.99. Third, the noise level of denoised magnetograms from our model is greatly reduced from 10 G to 4 G, and it is consistent with that of stacked magnetograms 4 G. Our results can be applied to many scientific fields in which the integration of many frames is used to improve the signal-to-noise ratio.