北京大学工学院
航空航天工程系学术报告
|
Thermodynamically consistent deep model reductions via OnsagerNet for deterministic and stochastic systems |
报告人 于海军 研究员
中国科学院数学与系统科学研究院
主持人：宋保方 研究员
时间：6月14日（周五）下午16:00-17:30
地点：力学楼434会议室
报告人简介：
于海军，中国科学院数学与系统科学研究院研究员, 博士生导师，中国科学院大学岗位教授。于2002年获得北京大学学士学位, 2007年获得北京大学博士学位。2007-2010年曾先后在美国普林斯顿大学和普渡大学从事博士后研究。主要研究方向为高精度数值方法. 研究内容涉及高维偏微分方程稀疏网格方法，相变路径计算数值方法，相场建模和计算，以及与微分方程相关的机器学习等. 作为课题负责人先后承担过自然科学基金委青年、面上、重大研究计划、国际合作等科研项目.
报告内容摘要：
Discovering hidden low-dimensional dynamical models from provided trajectory data or establishing reduced surrogate models for given high-dimensional PDE systems using deep learning methods is one of the promising topics in computational science and machine learning fields. Broadly speaking, there are two fundamental approaches: unstructured and structured. In the first approach, deep neural networks are directly used to fit the dynamical data, which in the second one, deep networks with special physical structure are used to fit physical data. In this talk, I will briefly introduce our recent attempts that belongs to the second approach to find low-dimensional models by combining deep learning methods and a generalized Onsager principle. The obtained reduced models are mathematically well-posed and physically interpretable. The method is applied to both deterministic and stochastic dynamical systems. Detailed numerical results of different applications will be presented.
欢迎广大老师和研究生参加！
