mlsanityData to 7 Oct 2026

How to Train Your Flare Prediction Model: Revisiting Robust Sampling of Rare Events

arXiv 2103.07542 ↗First posted 12 Mar 2021astro-ph.SR cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

We present a case study of solar flare forecasting by means of metadata feature time series, by treating it as a prominent class-imbalance and temporally coherent problem. Taking full advantage of pre-flare time series in solar active regions is made possible via the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark dataset; a partitioned collection of multivariate time series of active region properties comprising 4075 regions and spanning over 9 years of the Solar Dynamics Observatory (SDO) period of operations. We showcase the general concept of temporal coherence triggered by the demand of continuity in time series forecasting and show that lack of proper understanding of this effect may spuriously enhance models' performance. We further address another well-known challenge in rare event prediction, namely, the class-imbalance issue. The SWAN-SF is an appropriate dataset for this, with a 60:1 imbalance ratio for GOES M- and X-class flares and a 800:1 for X-class flares against flare-quiet instances. We revisit the main remedies for these challenges and present several experiments to illustrate the exact impact that each of these remedies may have on performance. Moreover, we acknowledge that some basic data manipulation tasks such as data normalization and cross validation may also impact the performance -- we discuss these problems as well. In this framework we also review the primary advantages and disadvantages of using true skill statistic and Heidke skill score, as two widely used performance verification metrics for the flare forecasting task. In conclusion, we show and advocate for the benefits of time series vs. point-in-time forecasting, provided that the above challenges are measurably and quantitatively addressed.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 2 of its 60 references that are in the map. First posted on arXiv 12 Mar 2021.

Builds on

2 of 60 references.

References · 2

  1. 2017A hybrid supervised/unsupervised machine learning approach to solar flare predictioncited by 11
  2. 2020A Framework for Designing and Evaluating Solar Flare Forecasting Systemscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 4; 2024: 7; 2025: 7; 2026: 1.

26 papers.

Sort:

  1. 2022Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecastingcited by 17
  2. 2022Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Datacited by 15
  3. 2023Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methodscited by 12
  4. 2023Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecastingcited by 7
  5. 2023Towards Interpretable Solar Flare Prediction with Attention-based Deep Neural Networkscited by 7
  6. 2024Embedding Ordinality to Binary Loss Function for Improving Solar Flare Forecastingcited by 4
  7. 2024Contrastive Representation Learning for Predicting Solar Flares from Extremely Imbalanced Multivariate Time Series Datacited by 4
  8. 2022Improving Solar Flare Prediction by Time Series Outlier Detectioncited by 3
  9. 2024Enhancing Multivariate Time Series-based Solar Flare Prediction with Multifaceted Preprocessing and Contrastive Learningcited by 3
  10. 2025Surya: Foundation Model for Heliophysicscited by 3
  11. 2021Towards Synthetic Multivariate Time Series Generation for Flare Forecastingcited by 2
  12. 2021Feature Selection on a Flare Forecasting Testbed: A Comparative Study of 24 Methodscited by 2
14 more
  1. 2024ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generationcited by 2
  2. 2024EXCON: Extreme Instance-based Contrastive Representation Learning of Severely Imbalanced Multivariate Time Series for Solar Flare Predictioncited by 2
  3. 2024VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classificationcited by 2
  4. 2022Using Multiple Instance Learning for Explainable Solar Flare Predictioncited by 1
  5. 2025Global Cross-Time Attention Fusion for Enhanced Solar Flare Prediction from Multivariate Time Seriescited by 1
  6. 2021Construction Cost Index Forecasting: A Multi-feature Fusion Approachcited by 0
  7. 2023Probabilistic solar flare forecasting using historical magnetogram datacited by 0
  8. 2024Class-Based Time Series Data Augmentation to Mitigate Extreme Class Imbalance for Solar Flare Predictioncited by 0
  9. 2025Ordinal Encoding as a Regularizer in Binary Loss for Solar Flare Predictioncited by 0
  10. 2025Beyond Point Matching: Evaluating Multiscale Dubuc Distance for Time Series Similaritycited by 0
  11. 2025Effectiveness of High-Dimensional Distance Metrics on Solar Flare Time Seriescited by 0
  12. 2025Enhancing Explainability in Solar Energetic Particle Event Prediction: A Global Feature Mapping Approachcited by 0
  13. 2025Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Recordscited by 0
  14. 2026SolarGPT-QA: A Domain-Adaptive Large Language Model for Educational Question Answering in Space Weather and Heliophysicscited by 0