Comparison Between Gramian Angular Fields (GAF) and Markov Transition Field (MTF) Images Data by Using them as Input to the Deep Learning Neural Network Solar Flare Production Platform

Abstract

The prediction of solar storms from real-time satellites data is an essential to protect various aviation, power, and communication infrastructures. For this reason, current research interest is focusing on creating systems that can predict solar fare accurately. This paper combers Gramian Angular Fields (GAF) images and Markov Transition Field (MTF) images that have been generated by converting pre-flare Geostationary Operational Environmental Satellite (GOES) data from 2010 to 2016. After that, the deep learning neural network for the solar flare production platform accepts both MTF and GAF images as input to generate the predictions. Furthermore, this paper; investigated using MTF and GAF images spritely as input to the solar flare production platform. After that, the results of MTF and GAF images were compared using various prediction verification measures.