Investigating the solar magnetic field is crucial to understand the physical
processes in the solar interior as well as their effects on the interplanetary
environment. We introduce a novel method to predict the evolution of the solar
line-of-sight (LoS) magnetogram using image-to-image translation with Denoising
Diffusion Probabilistic Models (DDPMs). Our approach combines "computer science
metrics" for image quality and "physics metrics" for physical accuracy to
evaluate model performance. The results indicate that DDPMs are effective in
maintaining the structural integrity, the dynamic range of solar magnetic
fields, the magnetic flux and other physical features such as the size of the
active regions, surpassing traditional persistence models, also in flaring
situation. We aim to use deep learning not only for visualisation but as an
integrative and interactive tool for telescopes, enhancing our understanding of
unexpected physical events like solar flares. Future studies will aim to
integrate more diverse solar data to refine the accuracy and applicability of
our generative model.

通过图像到图像的转换和去噪扩散概率模型，我们引入了一种新的方法来预测太阳光学磁图的演变，该方法综合了图像质量的计算机科学指标和物理准确度的物理指标来评估模型性能，结果显示，扩散概率模型不仅在维持太阳磁场的结构完整性、动态范围、磁通量等物理特征方面表现出色，而且在活动区的大小等其他物理特征以及耐火情况下的传统持久性模型中超越传统持久性模型，我们的目标是使用深度学习作为观测望远镜的集成和交互工具，提高我们对太阳耀斑等意外物理事件的理解，未来的研究将致力于整合更多多样化的太阳数据，以提高我们的生成模型的准确性和适用性。

磁图到磁图：太阳演化的生成预测

Magnetogram-to-Magnetogram: Generative Forecasting of Solar Evolution

A new data product from the Helioseismic and Magnetic Imager (HMI) onboard
the Solar Dynamics Observatory (SDO) called Space-weather HMI Active Region
Patches (SHARPs) is now available. SDO/HMI is the first space-based instrument
to map the full-disk photospheric vector magnetic field with high cadence and
continuity. The SHARP data series provide maps in patches that encompass
automatically tracked magnetic concentrations for their entire lifetime; map
quantities include the photospheric vector magnetic field and its uncertainty,
along with Doppler velocity, continuum intensity, and line-of-sight magnetic
field. Furthermore, keywords in the SHARP data series provide several
parameters that concisely characterize the magnetic-field distribution and its
deviation from a potential-field configuration. These indices may be useful for
active-region event forecasting and for identifying regions of interest. The
indices are calculated per patch and are available on a twelve-minute cadence.
Quick-look data are available within approximately three hours of observation;
definitive science products are produced approximately five weeks later. SHARP
data are available at this http URL and maps are available in either
of two different coordinate systems. This article describes the SHARP data
products and presents examples of SHARP data and parameters.

通过 SDO/HMI 新数据产品 SHARP data series，该文介绍了高精度空间磁场观测，并提出多种参数以区分磁场配置和便于活动区域预测。