Generation of Modern Satellite Data from Galileo Sunspot Drawings in 1612 by Deep Learning
Generation of Modern Satellite Data from Galileo Sunspot Drawings in 1612 by Deep Learning
复制标题
通过深度学习从 1612 年伽利略太阳黑子绘图生成现代卫星数据
作者：
Harim Lee;E. Park;Y. Moon
历史上的太阳黑子图是了解过去太阳活动的重要资源。我们使用基于条件生成对抗网络的深度学习模型，从伽利略太阳黑子图中生成太阳磁图和EUV图像。我们使用来自威尔逊山天文台的太阳黑子图对及其相应的磁图（或UV/EUV图像）训练模型，从2011年到2015年，除了每年6月和12月的太阳动力学观测卫星。我们通过比较6月和12月的实际磁图（或UV/EUV图像）和相应的AI生成的磁图来评估模型。结果表明，人工智能磁图的双极结构与原始磁图一致，无符号磁通量（或强度）与原始磁图一致。将此模型应用于1612年伽利略的太阳黑子图，我们生成了太阳黑子的日震和磁成像仪般的磁图和大气成像组件般的EUV图像。我们希望EUV强度可以用于估计太阳EUV辐照度在长期的历史时间。
Historical sunspot drawings are very important resources for understanding past solar activity. We generate solar magnetograms and EUV images from Galileo sunspot drawings using a deep learning model based on conditional generative adversarial networks. We train the model using pairs of sunspot drawings from the Mount Wilson Observatory and their corresponding magnetograms (or UV/EUV images) from 2011 to 2015 except for every June and December by the Solar Dynamic Observatory satellite. We evaluate the model by comparing pairs of actual magnetograms (or UV/EUV images) and the corresponding AI-generated ones in June and December. Our results show that bipolar structures of the AI-generated magnetograms are consistent with those of the original ones and their unsigned magnetic fluxes (or intensities) are consistent with those of the original ones. Applying this model to the Galileo sunspot drawings in 1612, we generate Helioseismic and Magnetic Imager-like magnetograms and Atmospheric Imaging Assembly-like EUV images of the sunspots. We hope that the EUV intensities can be used for estimating solar EUV irradiance at long-term historical times.