FCN4Flare: Fully Convolution Neural Networks for Flare Detection

Stellar flares originate from the sudden reconnection of magnetic flux lines within the star's atmosphere, particularly in the chromosphere. Automated flare detection enables exploiting vast photometric datasets from missions like Kepler. Prior methods rely on outlier detection, facing challenges of complexity, detection accuracy, and scalability. This paper presents FCN4Flare, a deep learning approach using fully convolutional networks for precise point-to-point flare prediction regardless of light curve length. Key innovations include the NaN Mask to handle missing data, dilated convolutions to preserve local information, and the MaskDice loss to mitigate severe class imbalance. Experiments demonstrate significantly improved detection performance over previous models, with a 0.64 Dice coefficient on Kepler data. Applying FCN4Flare to Kepler and LAMOST, we compile a catalog of 30,285 high-confidence flares across 1426 stars. Flare energies are estimated and stellar/exoplanet properties analyzed, identifying pronounced activity for an M-dwarf hosting a habitable zone planet. This work overcomes limitations of prior flare detection methods via deep learning, enabling new scientific discoveries through analysis of photometric time-series data.