Call for Papers: Machine Learning and Partial Differential Equations
글쓴이 : KSIAM
작성일 : 2019-12-26

Call for Papers: Machine Learning and Partial Differential Equations 

Guest Editors: Minseok Choi (POSTEC), Jae-Hun Jung (Ajou University/SUNY Buffalo)

Main review article by George Em Karniadakis (Brown University)

Submission deadline: July 31, 2020

Rationale: In last decades machine learning has been proven to provide highly efficient and accurate methods in various applications of science and engineering. Machine learning also has shed light upon partial differential equations for solutions. Machine learning such as deep learning not only provides a new way of solving partial differential equations but also finds a way, inspired by partial differential equation analysis, of explaining why the deep learning method outperforms over traditional approaches. 

 In this special issue, we aim to introduce recent progresses on machine learning and partial differential equations  and provide a place for researchers working in this area to share their experiences. Thus we invite a wide range of journal papers such as review articles, original research papers, and short notes. 

Topics covered include, but are not limited to: 

• Machine learning for solving partial differential equations

• Data-driven modeling and simulation

• Data-driven algorithms for computational fluid dynamics

• Partial differential equation driven deep neural network architecture 

• Machine learning for uncertainty quantification

The Journal of Korean Society for Industrial and Applied Mathematics is a peer-reviewed journal which has a fast publication cycle. Submission goes through the following submission page: