SolARED: Solar Active Region Emergence Dataset

1-D ML-Ready Dataset for Early Detection of the Active Regions Emergence

The Solar Active Region Emergence Dataset (SolARED) is developed to enhance ML capabilities to explore dynamics at the photosphere associated with the emergence and evolution of active regions, as well as the surrounding quiet Sun. The web tool allows the user to select an area within an active region (AR) to visualize the tracked subregion (tile) and corresponding timelines, choose the emergence criterion, and download the data in ".fits" format. SolARED dataset is obtained from the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO) observables of Doppler velocity, magnetic field, and continuum intensity. The dataset includes 1D tile-averaged timelines of acoustic maps for four frequency ranges (Pa), unsigned magnetic flux (ΦM), and continuum intensity (IC) for 50 large ARs that have emerged on the observable solar disc between 2010 and 2023. For more detailed data product description and example of its utilization for ML-driven prediction of the emergence of solar active regions see Kasapis et al. (2024 , 2025).

Map Time:

Tile #:

Emergence/Activity Criteria

hours
hours

Tile # Emergence Information

ΦB Emergence:
Ic Emergence:

Download Timeline Data

Select Physical Quantities

Magnetic Flux
Continuum Intensity
Acoustic Power

Select Desired Area

Current Selected Tile
All 81 Tiles

Start Time:

End Time:

Latitude:

Carrington Longitude:

Longitude at Start:

Longitude at End:

Area at Start: msh

Area at End: msh

Max Area: msh

Time of Max Area:

Zurich Class:

Hale Class:

Unsigned magnetic flux
Continuum intensity
Mean acoustic power

Website Information

Acknowledgements:
This work is supported by the NASA AI/ML HECC Expansion Program, NASA Heliophysics Supporting Research Program, and the NASA grants 80NSSC19K0630, 80NSSC19K0268, 80NSSC20K1870, and 80NSSC22M0162, 23-HGIO23_2-0077, along with the Grace Hopper AI Research Institute (GHAIRI) grant funded by the New Jersey Institute of Technology (NJIT).



References:
[1] Kasapis S., Kitiashvili I.N., Kosovichev A.G., Stefan J.T., Apte B. 2023. Predicting the Emergence of Solar Active Regions Using Machine Learning. Proc. IAU, 19(S365), pp.311-319. (1, 2)
[2] Kasapis S., Kitiashvili I. N., Kosovichev A. G., Stefan, J. T. Prediction of intensity variations associated with emerging active regions using helioseismic power maps and machine learning. ApJS. 10.3847/1538-4365/adfbe2 (2025) (1)
[3] Hoeksema J. T., Liu Y., Hayashi K., Sun X., Schou J., Couvidat S., Norton A., Bobra M., Centeno R., Leka K. D., Barnes G., Turmon M. 2014. The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: Overview and Performance. Solar Physics, 289, pp.3483-3530. (1) [4] Kasapis, S., Dogan, E., Kitiashvili, I.N., Kosovichev, A.G., Stefan, J.T., Butler, J.D., Tirona, J., Patil, S. and Xu, M., 2026. SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions. arXiv preprint arXiv:2601.13145. (1) [5] Tirona, J., Patil, S., Kasapis, S., Dogan, E., Stefan, J., Kitiashvili, I.N., Kosovichev, A.G. and Xu, M., 2026. Forecasting Continuum Intensity for Solar Active Region Emergence Prediction using Transformers. arXiv preprint arXiv:2601.13144. (1)

Contact:
The website was designed and is maintained by Spiridon Kasapis (skasapis@princeton.edu) and Irina Kitiashvili (irina.n.kitiashvili@nasa.gov) and it was further developed by Jake D. Butler and Eren Dogan.