UFCORIN: A fully automated predictor of solar flares in GOES X-ray flux

We have developed UFCORIN, a platform for studying and automating space weather prediction. Using our system we have tested 6160 different combinations of Solar Dynamic Observatory/Helioseismic and Magnetic Imager data as input data, and simulated the prediction of GOES X‐ray flux for 2 years (2011–2012) with 1 h cadence. We have found that direct comparison of the true skill statistic (TSS) from small cross‐validation sets is ill posed and used the standard scores (z) of the TSS to compare the performance of the various prediction strategies. The z of a strategy is a stochastic variable of the stochastically chosen cross‐validation data set, and the z for the three strategies best at predicting X‐, ≥M‐, and ≥C‐class flares are better than the average z of the 6160 strategies by 2.3σ, 2.1σ, and 3.8σ confidence levels, respectively. The best three TSS values were 0.75 ± 0.07, 0.48 ± 0.02, and 0.56 ± 0.04, respectively. Key Points We have developed UFCORIN, a general purpose time series predictor for solar flare prediction We establish the comparison method of different prediction strategies using z scores We discovered the range of wavelet wavelength that maximizes the prediction skill of large flares