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

arXiv: https://arxiv.org/abs/2507.05313 · HTML: https://mlsanity.com/paper/2507.05313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 99 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization](https://mlsanity.com/paper/2212.04985/) (2022)
- [Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecasting](https://mlsanity.com/paper/2209.07406/) (2022)
- [Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data](https://mlsanity.com/paper/2204.03710/) (2022)
- [Flare Prediction Using Photospheric and Coronal Image Data](https://mlsanity.com/paper/1708.01323/) (2017)
- [Machine learning in solar physics](https://mlsanity.com/paper/2306.15308/) (2023)
- [DeepSun: Machine-Learning-as-a-Service for Solar Flare Prediction](https://mlsanity.com/paper/2009.04238/) (2020)
- [Low Dimensional Convolutional Neural Network For Solar Flares GOES Time Series Classification](https://mlsanity.com/paper/2101.12550/) (2021)
- [Solar Active Region Magnetogram Image Dataset for Studies of Space Weather](https://mlsanity.com/paper/2305.09492/) (2023)
- [Locally Self-Adjustive Smoothing for Measurement Noise Reduction with Application to Automated Peak Detection](https://mlsanity.com/paper/2310.17663/) (2023)

## Abstract (arXiv)

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.