Solar Flare Prediction Using Long Short-term Memory (LSTM) and Decomposition-LSTM with Sliding Window Pattern Recognition

Abstract

We investigate the use of Long Short-Term Memory (LSTM) and Decomposition-LSTM (DLSTM) networks, combined with an ensemble algorithm, to predict solar flare occurrences using time-series data from the GOES catalog. The dataset spans from 2003 to 2023 and includes 151,071 flare events. Among approximately possible patterns, 7,552 yearly pattern windows are identified, highlighting the challenge of long-term forecasting due to the Sun's complex, self-organized criticality-driven behavior. A sliding window technique is employed to detect temporal quasi-patterns in both irregular and regularized flare time series. Regularization reduces complexity, enhances large flare activity, and captures active days more effectively. To address class imbalance, resampling methods are applied. LSTM and DLSTM models are trained on sequences of peak fluxes and waiting times from irregular time series, while LSTM and DLSTM, integrated with an ensemble approach, are applied to sliding windows of regularized time series with a 3-hour interval. Performance metrics, particularly TSS (0.74), recall (0.95) and the area under the curve (AUC=0.87) in the receiver operating characteristic (ROC), indicate that DLSTM with an ensemble approach on regularized time series outperforms other models, offering more accurate large-flare forecasts with fewer false errors compared to models trained on irregular time series. The superior performance of DLSTM is attributed to its ability to decompose time series into trend and seasonal components, effectively isolating random noise. This study underscores the potential of advanced machine learning techniques for solar flare prediction and highlights the importance of incorporating various solar cycle phases and resampling strategies to enhance forecasting reliability.

Published in the Astrophysical Journal Supplement Series, volume 279, 2025, DOI: 10.3847/1538-4365/addc73

References in corpus (29)

• 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
• Solar Flare Prediction Model with Three Machine-Learning Algorithms Using Ultraviolet Brightening and Vector Magnetogram
• Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning
• Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Product and Random Forest Algorithm
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Flare Prediction Using Photospheric and Coronal Image Data
• A Statistical Solar Flare Forecast Method
• Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data
• Prediction of Solar Flares Using Unique Signatures of Magnetic Field Images
• Prediction of Solar Flare Size and Time-to-Flare Using Support Vector Machine Regression
• Operational solar flare prediction model using Deep Flare Net
• Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization
• Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecasting
• Reliable Probability Forecast of Solar Flares: Deep Flare Net-Reliable (DeFN-R)
• Solar Flares Complex Networks
• Predictive Capabilities of Avalanche Models for Solar Flares
• A new catalogue of solar flare events from soft x-ray GOES signal in the period 1986-2020
• DeepSun: Machine-Learning-as-a-Service for Solar Flare Prediction
• Properties of Flare-Imminent versus Flare-Quiet Active Regions from the Chromosphere through the Corona II: NonParametric Discriminant Analysis Results from the NWRA Classification Infrastructure (NCI)
• Low Dimensional Convolutional Neural Network For Solar Flares GOES Time Series Classification
• Machine Learning Approaches to Solar-Flare Forecasting: Is Complex Better?
• The characteristics of flare- and CME-productive solar active regions
• Principle of Minimum Energy in Magnetic Reconnection in a Self-Organized Critical Model for Solar Flares
• Energy Balance in Avalanche Models for Solar Flares
• Solar Active Region Magnetogram Image Dataset for Studies of Space Weather
• Properties of Flare-Imminent versus Flare-Quiet Active Regions from the Chromosphere through the Corona I: Introduction of the AIA Active Region Patches (AARPs)
• Do Cellular Automaton Avalanche Models Simulate the Quasi-Periodic Pulsations of Solar Flares?