Decreasing false-alarm rates in CNN-based solar flare prediction using SDO/HMI data
Published in The Astrophysical Journal Supplement Series, 2022
Recommended citation: Deshmukh, V. and Flyer, N. and van der Sande K. and Berger, T. (2022). “Decreasing false-alarm rates in CNN-based solar flare prediction using SDO/HMI data.” The Astrophysical Journal Supplement Series. 260(9). https://iopscience.iop.org/article/10.3847/1538-4365/ac5b0c/pdf
A hybrid two-stage machine-learning architecture that addresses the problem of excessive false positives (false alarms) in solar flare prediction systems is investigated. The first stage is a convolutional neural network (CNN) model based on the VGG-16 architecture that extracts features from a temporal stack of consecutive Solar Dynamics Observatory Helioseismic and Magnetic Imager magnetogram images to produce a flaring probability. The probability of flaring is added to a feature vector derived from the magnetograms to train an extremely randomized trees (ERT) model in the second stage to produce a binary deterministic prediction (flare/no-flare) in a 12 hr forecast window.
Recommended citation: Deshmukh, V. and Flyer, N. and van der Sande K. and Berger, T. (2022). “Decreasing false-alarm rates in CNN-based solar flare prediction using SDO/HMI data.” The Astrophysical Journal Supplement Series. 260(9).