Enhancing SDO/HMI images using deep learning
share
The Helioseismic and Magnetic Imager (HMI) provides continuum images and magnetograms with a cadence better than one every minute. It has been continuously observing the Sun 24 hours a day for the past 7 years. The obvious trade-off between cadence and spatial resolution makes that HMI is not enough to analyze the smallest-scale events in the solar atmosphere. Our aim is developing a new method to enhance HMI data, simultaneously deconvolving and superresolving images and magnetograms. The resulting images will mimick observations with a diffraction-limited telescope twice the diameter of HMI. The method, that we term Enhance, is based on two deep fully convolutional neural networks that input patches of HMI observations and output deconvolved and superresolved data. The neural networks are trained on synthetic data obtained from simulations of the emergence of solar active regions. We have obtained deconvolved and supperresolved HMI images. To solve this ill-defined problem with infinite solutions we have used a neural network approach to add prior information from the simulations. We test Enhance against Hinode data that has been degraded to a 28 cm diameter telescope showing very good consistency. The code is open sourced for the community.
READ FULL TEXT
