Deep Flare Net (DeFN) model for solar flare prediction

Abstract

We developed a solar flare prediction model using a deep neural network (DNN), named Deep Flare Net (DeFN). The model can calculate the probability of flares occurring in the following 24 h in each active region, which is used to determine the most likely maximum classes of flares via a binary classification (e.g., >=M class versus <M class or >=C class versus <C class). From 3x10^5 observation images taken during 2010-2015 by Solar Dynamic Observatory, we automatically detected sunspots and calculated 79 features for each region, to which flare occurrence labels of X-, M-, and C-class were attached. We adopted the features used in Nishizuka et al. (2017) and added some features for operational prediction: coronal hot brightening at 131 A (T>=10^7 K) and the X-ray and 131 A intensity data 1 and 2 h before an image. For operational evaluation, we divided the database into two for training and testing: the dataset in 2010-2014 for training and the one in 2015 for testing. The DeFN model consists of deep multilayer neural networks, formed by adapting skip connections and batch normalizations. To statistically predict flares, the DeFN model was trained to optimize the skill score, i.e., the true skill statistic (TSS). As a result, we succeeded in predicting flares with TSS=0.80 for >=M-class flares and TSS=0.63 for >=C-class flares. Note that in usual DNN models, the prediction process is a black box. However, in the DeFN model, the features are manually selected, and it is possible to analyze which features are effective for prediction after evaluation.

arXiv comment24 pages, 7 figures, 3 tables, Accepted for publication in ApJ

References in corpus (32)

• Adam: A Method for Stochastic Optimization
• An Observational Overview of Solar Flares
• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• Toward Reliable Benchmarking of Solar Flare Forecasting Methods
• A Comparison of Flare Forecasting Methods, I: Results from the "All-Clear" Workshop
• Magnetic Field Structures Triggering Solar Flares and Coronal Mass Ejections
• Solar Flare Prediction Model with Three Machine-Learning Algorithms Using Ultraviolet Brightening and Vector Magnetogram
• Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Product and Random Forest Algorithm
• High-resolution observations of flare precursors in the low solar atmosphere
• Catastrophe versus instability for the eruption of a toroidal solar magnetic flux rope
• A Bayesian Approach to Solar Flare Prediction
• Flare Prediction Using Photospheric and Coronal Image Data
• Magnetohydrodynamic Simulation of the X2.2 Solar Flare on 2011 February 15: I. Comparison with the Observations
• Solar Magnetic Feature Detection and Tracking for Space Weather Monitoring
• A hybrid supervised/unsupervised machine learning approach to solar flare prediction
• Study on Triggering Process of Solar Flares Based on Hinode/SOT Observations
• Flare forecasting at the Met Office Space Weather Operations Centre
• Numerical Simulations of Flare-productive Active Regions: delta-sunspots, Sheared Polarity Inversion Lines, Energy Storage, and Predictions
• Prediction of Solar Flares Using Unique Signatures of Magnetic Field Images
• Magnetic Systems Triggering the M6.6-class Solar Flare in NOAA Active Region 11158
• Ensemble Forecasting of Major Solar Flares -- First Results
• UFCORIN: A Fully Automated Predictor of Solar Flares in GOES X-Ray Flux
• Numerical Study on Emergence of Kinked Flux Tube for Understanding of Possible Origin of Delta-spot Regions
• The Power-Law Distribution of Flare Kernels and Fractal Current Sheets in a Solar Flare
• Flaring Rates and the Evolution of Sunspot Group McIntosh Classifications
• Prediction of Solar Flare Size and Time-to-Flare Using Support Vector Machine Regression
• An automated classification approach to ranking photospheric proxies of magnetic energy build-up
• Relationships Between Characteristics of the Line-of-Sight Magnetic Field and Solar Flare Forecasts
• Verification of operational solar flare forecast: Case of Regional Warning Center Japan
• Using the Maximum X-ray Flux Ratio and X-ray Background to Predict Solar Flare Class
• Plasma heating in the very early phase of solar flares
• A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast

Cited by in corpus (32)

• The Challenge of Machine Learning in Space Weather Nowcasting and Forecasting
• Flare-productive active regions
• Predicting Solar Flares Using a Long Short-Term Memory Network
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data
• Predicting solar flares with machine learning: investigating solar cycle dependence
• Feature ranking of active region source properties in solar flare forecasting and the uncompromised stochasticity of flare occurrence
• Operational solar flare prediction model using Deep Flare Net
• Solar image denoising with convolutional neural networks
• Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks
• Implementation paradigm for supervised flare forecasting studies: a deep learning application with video data
• Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecasting
• Fine-grained Solar Flare Forecasting Based on the Hybrid Convolutional Neural Networks
• Reliable Probability Forecast of Solar Flares: Deep Flare Net-Reliable (DeFN-R)
• Supervised convolutional neural networks for classification of flaring and nonflaring active regions using line-of-sight magnetograms
• Measuring the magnetic origins of solar flares, CMEs and Space Weather
• A Framework for Designing and Evaluating Solar Flare Forecasting Systems
• Non-LTE inversions of a confined X2.2 flare: I. Vector magnetic field in the photosphere and chromosphere
• Leveraging the Mathematics of Shape for Solar Magnetic Eruption Prediction
• Solar Flares Forecasting Using Time Series and Extreme Gradient Boosting Ensembles
• Machine Learning Approaches to Solar-Flare Forecasting: Is Complex Better?
• Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods
• Solar Active Region Magnetogram Image Dataset for Studies of Space Weather
• Predicting Solar Energetic Particles Using SDO/HMI Vector Magnetic Data Products and a Bidirectional LSTM Network
• Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecasting
• Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): I. Overview, Magnetohydrodynamic Modeling, and Stokes Profile Synthesis
• A New Space Weather Tool for Identifying Eruptive Active Regions
• Automatic Detection of Occulted Hard X-ray Flares Using Deep-Learning Methods
• Predicting the Evolution of Photospheric Magnetic Field in Solar Active Regions Using Deep Learning
• A Comparative Analysis of Machine-learning Models for Solar Flare Forecasting: Identifying High-performing Active Region Flare Indicators
• The Flare Likelihood and Region Eruption Forecasting (FLARECAST) Project: Flare forecasting in the big data & machine learning era
• Testing and Validating Two Morphological Flare Predictors by Logistic Regression Machine Learning