Deep Flare Net (NICT)

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

◆ Deep Flare Net-Quadro (DeFN-Q)

・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-Quadro (DeFN-Q) is an extention of the original forecast model
DeFN for deterministic forecasts of 4-class flares.

・Solar flares are classified into X, M, and C-class flares. DeFN-Q model is designed for
deterministic forecast of X, M, C, and less than C-class flares.

・The training data consists of the line-of-sight and vector magnetograms (HMI/SDO),
131A and 1600A images (AIA/SDO) and the soft X-ray data (GOES).

・Solar flares occur in active regions, where magnetic field is strong around sunspots.
DeFN automatically detects active regions with strong magnetic field (>40 Gauss).

・Few flares occur in quiet regions where magnetic field is weak, but they are not
predicted by DeFN, as well as limb flares. DeFN skips when the lack of full data.

・Detected regions are numbered for each prediction. The area No. corresponds to No.
in the right graph. DeFN-Q can predict 4 categories of X, M, C, and no flares.

・DeFN-Q predict flares with the size which probability is larget in the pie graph.
It is unique that there are few missed flares.

・The probability of occurrence P for the full solar disk of M-class or higher is displayed
in the upper 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 performances more in detail in the following papers.
- Nishizuka et al. submitted.

・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)