In recent years, the scalar auxiliary variable (SAV) approach has become very popular and hot in the design of linear, high-order and unconditional energy stable schemes of gradient flow models. However, the nature of SAV-based numerical schemes preserving modified energy dissipation limits its wider application. A relaxation technique to correct the modified energy for the baseline SAV method (RSAV) was proposed by Zhao et al. and Shen et al.. The RSAV approach is unconditionally energy stable with respect to a modified energy that is closer to the original free energy, and provides a much improved accuracy when compared with the SAV approach. In this paper, inspired by the RSAV approach, we propose a novel technique to correct the modified energy of the SAV approach, which can be proved to be an optimal energy approximation. We construct new high-order implicit-explicit schemes based on the proposed energy-optimal SAV (EOP-SAV) approach. The constructed EOP-SAV schemes not only provide an improved accuracy but also simplify calculation, and can be viewed as the optimal relaxation. We also prove that the numerical schemes based on the EOP-SAV approach are unconditionally energy stable. Compared with the RSAV approach, the proposed EOP-SAV approach does not need introduce any relaxed factors and can share the similar procedure for error estimates. Several interesting numerical examples have been presented to demonstrate the accuracy and effectiveness of the proposed methods.


翻译:暂无翻译

0
下载
关闭预览

相关内容

机器学习系统设计系统评估标准
[综述]深度学习下的场景文本检测与识别
专知会员服务
78+阅读 · 2019年10月10日
Hierarchically Structured Meta-learning
CreateAMind
27+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
29+阅读 · 2019年5月18日
Unsupervised Learning via Meta-Learning
CreateAMind
44+阅读 · 2019年1月3日
国家自然科学基金
0+阅读 · 2015年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2009年12月31日
Arxiv
0+阅读 · 2023年6月8日
Arxiv
0+阅读 · 2023年6月7日
VIP会员
相关资讯
Hierarchically Structured Meta-learning
CreateAMind
27+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
29+阅读 · 2019年5月18日
Unsupervised Learning via Meta-Learning
CreateAMind
44+阅读 · 2019年1月3日
相关基金
国家自然科学基金
0+阅读 · 2015年12月31日
国家自然科学基金
0+阅读 · 2012年12月31日
国家自然科学基金
0+阅读 · 2009年12月31日
Top
微信扫码咨询专知VIP会员