报告题目：Learning a Digital Twin of the Earth Climate System via Neural Turing Test

报  告 人： 潘宝祥 研究员

邀  请 人： 刘德地 教授

时      间： 2022年7月11日（星期一）上午10:00

地      点： 水电科技大楼A区202会议室

会议链接： https://meeting.tencent.com/dm/SiKx5HO4az3W

腾讯视频会议（ID: 448 688 164）   B站直播 （ID: 23115892)

报告人简介：

潘宝祥，美国劳伦斯利弗摩尔国家实验室研究员，主要研究兴趣包括概率信息理论、结合机器学 习与动力模式的天气-气候尺度预报、动力系统可预报性。2012年本科毕业于武汉大学，2015年 在清华大学获得工学硕士学位，2019年于加州大学欧文分校(University of California, Irvine) 获得工学博士学位，师从Dr. Soroosh Sorooshian, Dr. Kuolin Hsu, Dr. Amir AghaKouchak。

报告简介：

The earth climate system is featured by the chaotic geophysical fluid dynamics and the complicated interaction among various subsystems. This chaoticity and complexity raise the need to disentangle internal climate variability noise, external forcing, and model formulation deficiencies to answer climate-relevant questions, such as weather variability and climate adaptation. This talk discusses a self-supervised adversarial learning method for merging climate models and climate observations to disentangle different sources of uncertainties in climate prediction, therefore diagnosing, correcting, and improving our modeling of the earth system. We discuss the limitations of supervised (deep) learning in climate applications, and highlight the necessity of shifting toward novel learning paradigms to realize the power of modern machine learning techniques. We believe by replacing human model diagnosis experts with tireless machine "nitpickers" and "cleaners", we may soon reach a true "digital twin" of the earth climate system.

欢迎相关专业教师和研究生的光临！