A Comparative Study on Generative Models for High Resolution Solar Observation Imaging

by   Mehdi Cherti, et al.

Solar activity is one of the main drivers of variability in our solar system and the key source of space weather phenomena that affect Earth and near Earth space. The extensive record of high resolution extreme ultraviolet (EUV) observations from the Solar Dynamics Observatory (SDO) offers an unprecedented, very large dataset of solar images. In this work, we make use of this comprehensive dataset to investigate capabilities of current state-of-the-art generative models to accurately capture the data distribution behind the observed solar activity states. Starting from StyleGAN-based methods, we uncover severe deficits of this model family in handling fine-scale details of solar images when training on high resolution samples, contrary to training on natural face images. When switching to the diffusion based generative model family, we observe strong improvements of fine-scale detail generation. For the GAN family, we are able to achieve similar improvements in fine-scale generation when turning to ProjectedGANs, which uses multi-scale discriminators with a pre-trained frozen feature extractor. We conduct ablation studies to clarify mechanisms responsible for proper fine-scale handling. Using distributed training on supercomputers, we are able to train generative models for up to 1024x1024 resolution that produce high quality samples indistinguishable to human experts, as suggested by the evaluation we conduct. We make all code, models and workflows used in this study publicly available at <https://github.com/SLAMPAI/generative-models-for-highres-solar-images>.


page 6

page 7

page 9

page 17

page 20

page 22

page 25


SCSS-Net: Solar Corona Structures Segmentation by Deep Learning

Structures in the solar corona are the main drivers of space weather pro...

Analyzing Solar Irradiance Variation From GPS and Cameras

The total amount of solar irradiance falling on the earth's surface is a...

Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning

Owing to the remarkable photometric precision of space observatories lik...

High Resolution Solar Image Generation using Generative Adversarial Networks

We applied Deep Learning algorithm known as Generative Adversarial Netwo...

SOLAR: A Highly Optimized Data Loading Framework for Distributed Training of CNN-based Scientific Surrogates

CNN-based surrogates have become prevalent in scientific applications to...

Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder

High energy particles originating from solar activity travel along the t...

Perception Evaluation -- A new solar image quality metric based on the multi-fractal property of texture features

Next-generation ground-based solar observations require good image quali...

Please sign up or login with your details

Forgot password? Click here to reset