The variation of solar irradiance is one of the natural forcing mechanisms of
the terrestrial climate. Hence, the time-dependent solar irradiance is an
important input parameter for climate modelling. The solar surface magnetic
field is a powerful proxy for solar irradiance reconstruction. The analyses of
data obtained with the Michelson Doppler Imager (MDI) on board the SOHO mission
are therefore useful for the identification of solar surface magnetic features
to be used in solar irradiance reconstruction models. However, there is still a
need for automated technologies that would enable the identification of solar
activity features from large databases. To achieve this we present a series of
enhanced segmentation algorithms developed to detect and calculate the area
coverages of specific magnetic features from MDI intensitygrams and
magnetograms. These algorithms are part of the Automated Solar Activity
Prediction (ASAP) tool. The segmentation algorithms allow us to identify the
areas on the solar disk covered by magnetic elements inside and outside
boundaries of active regions. Depending on their contrast properties, magnetic
features within an active region boundary are classified as sunspot umbra and
penumbra, or faculae. Outside an active region boundary magnetic elements are
identified as network. We present the detailed steps involved in the
segmentation process and provide the area coverages of the segmented MDI
intensitygrams and magnetograms. The feature segmentation has been carried out
on daily intensitygrams and magnetograms from April 21, 1996 to April 11, 2011.
This offers an exciting opportunity to undertake further investigations that
benefit from solar features segmentations, such as solar irradiance
reconstruction, which we plan to investigate in the future.

利用 Michelson Doppler Imager （MDI）数据，开发了一系列增强型分割算法来探测和计算 MDI 图像中的特定磁学特征的覆盖面积，并根据其在主动区边界内 / 外的对比性质将其分类为太阳黑子至边缘、亮斑、网络等，以期进行更进一步的研究，如太阳辐射的重建。