Deep Flare Net (NICT)

◆ Sample images (when solar activity is high)
Image01 Image02 Image03 Image04 Image05 Image06 Image07

◆ Deep Flare Net-Reliable (DeFN-R)

・Our prediction model using deep neural networks, named Deep Flare Net (DeFN),
obtains solar observation data in real time and predicts solar flares in the next 24 hr.

・Deep Flare Net-Reliable (DeFN-R) is an extension of the original forecast model
DeFN for probabilistic forecasting, with improved reliability over DeFN.

・The scale of the flare is called X, M, and C class from the largest to the smallest.
DeFN-R forecasts the probability of X-class, M-class or higher, and C-class or
higher flares.

・The bar graph shows the forecasted probability of a flare. We achieved a hight level
of confidence with a small difference between the forecast probability and the
frequency of occurrence by DeFN-R.

・If you want to predict whether a flare will occur or not, you need to set a probability
threshold. When the probability threshold is set to the median of the flare occurrence
distribution, it reproduces the same performance as DeFN.

・The probability of occurrence P for the full solar disk of M-class or higher is displayed
in the upper right corner. When the probability of occurrence in each region is
p₁, p₂, p₃..., it is calculated by P=1-(1-p₁)(1-p₂)(1-p₃)....

・See DeFN-R performance more in detail in the following paper.
- Nishizuka et al. 2020, The Astrophysical J., 899, 150

・The database and code of DeFN model are released free.
- Released DeFN Database (WDC@NICT)
- Released Code of DeFN (GitHub)

◆ Acknowledgement
The data used here are courtesy of SDO/NASA, GOES/NOAA and
SDO-JSOC team (Stanford University, LMSAL and NASA).

Today's Solar Activity

Space Weather Forecast (NICT)