报告题目：Case study for scientific machine learning
报告人：明平兵（中国科学院数学与系统科学研究院）
报告时间：2026年9月29日10：30
报告地点：数学科学学院205
报告摘要：We shall present two examples to show the strength of the scientific machine learning (SciML). In the first example, we propose a deep learning based method for simulating the large bending deformation of bilayer plates. The method exhibits the capability to converge to an absolute minimizer, overcoming the limitation of gradient flow methods getting trapped in the local minimizer basins. We showcase better performance with fewer numbers of degrees of freedom for the relative energy errors of the minimizer through numerical experiments. In the second example, a machine learning method is proposed to deal with the spectrum of the fractional Schrodinger operators. Numerical experiments demonstrate that the method outperforms many traditional numerical methods for this problem in several scenarios. This is a joint work with Yixiao Guo , Hao Yu Xiang Li (AMSS) and Yulei Liao (HKU).
报告人简介：明平兵，中国科学院数学与系统科学研究院计算数学与科学工程计算研究所研究员、博士生导师，科学与工程计算国家重点实验室副主任。国家杰出青年科学基金获得者、国家“万人计划”中青年科技创新领军人才、冯康科学计算奖得主。主要从事多尺度计算数学、固体多尺度建模与数值模拟、Cauchy-Born法则数学理论、拟连续体方法稳定性分析及计算数学与机器学习交叉研究，在材料多尺度计算理论与算法方向取得多项原创性成果，研究成果发表于JAMS、CPAM、ARMA等国际顶尖期刊，学术影响力深厚。

编辑：王苗   审核：舒乾宇   终审：屈加文