Implementation paradigm for supervised flare forecasting studies: a deep learning application with video data

Abstract

Solar flare forecasting can be realized by means of the analysis of magnetic data through artificial intelligence techniques. The aim is to predict whether a magnetic active region (AR) will originate solar flares above a certain class within a certain amount of time. A crucial issue is concerned with the way the adopted machine learning method is implemented, since forecasting results strongly depend on the criterion with which training, validation, and test sets are populated. In this paper we propose a general paradigm to generate these sets in such a way that they are independent from each other and internally well-balanced in terms of AR flaring effectiveness. This set generation process provides a ground for comparison for the performance assessment of machine learning algorithms. Finally, we use this implementation paradigm in the case of a deep neural network, which takes as input videos of magnetograms recorded by the Helioseismic and Magnetic Imager on-board the Solar Dynamics Observatory (SDO/HMI). To our knowledge, this is the first time that the solar flare forecasting problem is addressed by means of a deep neural network for video classification, which does not require any a priori extraction of features from the HMI magnetograms.

References in corpus (25)

• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• Toward Reliable Benchmarking of Solar Flare Forecasting Methods
• Imaging coronal magnetic-field reconnection in a solar flare
• 25 Years of Self-Organized Criticality: Solar and Astrophysics
• A Comparison of Flare Forecasting Methods, I: Results from the "All-Clear" Workshop
• Global Properties of Solar Flares
• Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning
• Deep Flare Net (DeFN) model for solar flare prediction
• Predicting Solar Flares Using a Long Short-Term Memory Network
• Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Product and Random Forest Algorithm
• A Comparison of Flare Forecasting Methods. II. Benchmarks, Metrics and Performance Results for Operational Solar Flare Forecasting Systems
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Flare Prediction Using Photospheric and Coronal Image Data
• How to Train Your Flare Prediction Model: Revisiting Robust Sampling of Rare Events
• Flare forecasting at the Met Office Space Weather Operations Centre
• Predicting solar flares with machine learning: investigating solar cycle dependence
• Turbulence, Complexity, and Solar Flares
• Feature ranking of active region source properties in solar flare forecasting and the uncompromised stochasticity of flare occurrence
• A Comparison of Flare Forecasting Methods. III. Systematic Behaviors of Operational Solar Flare Forecasting Systems
• A Comparison of Flare Forecasting Methods. IV. Evaluating Consecutive-Day Forecasting Patterns
• Operational solar flare prediction model using Deep Flare Net
• Reliable Probability Forecast of Solar Flares: Deep Flare Net-Reliable (DeFN-R)
• Predictive Capabilities of Avalanche Models for Solar Flares
• Supervised convolutional neural networks for classification of flaring and nonflaring active regions using line-of-sight magnetograms
• Score-oriented loss (SOL) functions

Cited by in corpus (1)

• Bypassing the static input size of neural networks in flare forecasting by using spatial pyramid pooling