感谢
@◆HCl◆ @小谦.WX @大水台6 @CTCS-5 @Oliver小章鱼 和风羽酱-sdk等风迷对本项目的技术支持和启发

顺便贴一下6月那会搜到的论文,不知道这三个月还有没有新的,链接就不贴了,直接搜标题吧:
Nighttime Reflectance Generation in the Visible Bandof Satellites 应该是最早的模型之一,单波段AI-VIS
Deep Learning-Generated Nighttime Reflectance andDaytime Radiance of the Midwave Infrared Band of aGeostationary Satellite 用来模拟MWIR的模型
Impact of Satellite Sounding Data on Virtual VisibleImagery Generation Using Conditional GenerativeAdversarial Network 用了IR和WV俩波段增加模型准确度
Hypothetical Visible Bands of Advanced Meteorological Imager onboard the Geostationary Korea Multi-Purpose Satellite -2A Using Data-To-Data Translation 用了很多波段组合模拟真彩色,和上面kma网站这版比较相似
Creating synthetic night-time visible-light meteorological satellite images using theGAN method 用FY4A数据训练的,甚至加了ERA5数据进去
NightVision: Generating Nighttime Satellite Imageryfrom Infra-Red Observations 一场hackathon的结果