Homogenising SoHO/EIT and SDO/AIA 171Å$~$ Images: A Deep Learning Approach
This addresses the need for homogeneous solar image data for space weather prediction, but it is incremental as it builds on prior deep learning methods by adding uncertainty estimation.
The study tackled the problem of combining different solar EUV image surveys by training an ensemble of deep learning models to create a homogeneous dataset for 2 solar cycles, finding that ensemble uncertainty decreases with larger training sets and higher uncertainty in underrepresented test data.
Extreme Ultraviolet images of the Sun are becoming an integral part of space weather prediction tasks. However, having different surveys requires the development of instrument-specific prediction algorithms. As an alternative, it is possible to combine multiple surveys to create a homogeneous dataset. In this study, we utilize the temporal overlap of SoHO/EIT and SDO/AIA 171~Å~surveys to train an ensemble of deep learning models for creating a single homogeneous survey of EUV images for 2 solar cycles. Prior applications of deep learning have focused on validating the homogeneity of the output while overlooking the systematic estimation of uncertainty. We use an approach called `Approximate Bayesian Ensembling' to generate an ensemble of models whose uncertainty mimics that of a fully Bayesian neural network at a fraction of the cost. We find that ensemble uncertainty goes down as the training set size increases. Additionally, we show that the model ensemble adds immense value to the prediction by showing higher uncertainty in test data that are not well represented in the training data.