The Automated Solar Activity Prediction (a.k.a ASAP) is a computer system
that is designed to predict significant flares (the figure below shows the currently
completed part) and CMEs in near real-time. ASAP currently works for flare
prediction and further work on CMEs continues.
SOHO/MDI Continuum and Magnetogram images are used to detect sunspots and
find their McIntosh classifications. These classifications are fed to the
learning models to provide real-time predictions for the possible occurrence
of flares. The flare prediction system can be described in three stages:
1. Sunspot grouping.
a. Detection of sunspot candidates from MDI continuum images using
morphological image processing algorithms.
b. Detection of active region candidates from MDI magnetogram images using
morphological image processing algorithms. The MDI magnetogram images show
the magnetic fields of the solar photosphere, with black and white areas
indicating opposite magnetic polarities. These areas are detected separately
and combined afterwards to determine the active region candidates.
c. Applying a “region growing” algorithm to combine sunspot
and active region candidates.
d. Using neural networks to combine regions of opposite magnetic
polarities to determine the exact boundaries of sunspot groups.
2. McIntosh-based classification.
a. Extracting local features from every sunspot in every group using image
processing and neural networks.
i. Extracting the length, tallness, and area of the sunspot.
ii. Using neural networks to decide the type of penumbra (i.e., Mature or
Rudimentary) and whether the sunspot is Symmetric or Asymmetric.
b. Extracting features from each sunspot group using image processing. The
extracted features are length, largest spot, polarity and distribution.
c. Applying all the extracted features to a decision tree to determine
their McIntosh classification.
3. Flare prediction using Neural Networks.
a. The publicly available NGDC sunspots and flares catalogues were
investigated to associate flares with the sunspots that caused them. The
association is determined based on the location (i.e., same NOAA number) and
b. A Neural Networks is optimised, trained using this association
information. The input for NNs are composed of sunspot group classification
(McIntosh) and sunspot areas.
c. The neural networks are combined to produce a hybrid system to give
flaring probability of each sunspot group and their flare intensity