报告题目:高阶怪波的ASPINN方法及其在(2+1)维CHKP方程中的应用

报告人：安红利 教授 （南京农业大学）

报告时间：2024年5月25日 周六 16:00-17:00

报告地点：屏峰校区 广A214

摘要：In this talk, we propose an adaptive sampling physics-informed neural network method (ASPINN),which renders the points in local sharp regions to be selected sufficiently by a new adaptive search algorithm to lead to a prefect prediction performance. To valid the performance of our method, the (2 + 1)-dimensional CHKP equation is taken as an illustrative example. Experimental results reveal that the original PINNs can hardly be able to predict dynamical behaviors of the high-order rogue waves for the CHKP equation, but the ASPINN method can not only predict dynamical behaviors of these high-order rogue waves, but also greatly improve the prediction efficiency and accuracy to four orders of magnitude. In addition, we discuss the data-driven parameters discovery and some main factors affecting the neural network performance of the CHKP equation.

报告人简介：安红利，南京农业大学教授，博导，南京农业大学钟山学者—学术新秀，江苏省“青蓝工程”优秀骨干青年教师。主要研究方向是数学物理方程、可积系统理论及其应用。曾主持了国家自然科学基金面上项目3项、江苏省自然科学基金面上和青年项目2项、留学人员科技活动择优资助项目优秀类等共9项课题。目前已在国际期刊《Phys. Review E》,《Stud. Appl. Math.》,《J. Phys. A》和《J. Math. Phys.》等发表学术论文50余篇。

邀请人：郝夏芝