Physics-informed attention-based neural network for solving non-linear partial differential equations

作者
Ruben Rodriguez-Torrado,Ruiz, Pablo,Luis Cueto‐Felgueroso,Michael Cerny Green,Tyler Friesen,Sébastien F. Matringe,Julian Togelius
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:13
标识
DOI:10.48550/arxiv.2105.07898
摘要

Physics-Informed Neural Networks (PINNs) have enabled significant improvements in modelling physical processes described by partial differential equations (PDEs). PINNs are based on simple architectures, and learn the behavior of complex physical systems by optimizing the network parameters to minimize the residual of the underlying PDE. Current network architectures share some of the limitations of classical numerical discretization schemes when applied to non-linear differential equations in continuum mechanics. A paradigmatic example is the solution of hyperbolic conservation laws that develop highly localized nonlinear shock waves. Learning solutions of PDEs with dominant hyperbolic character is a challenge for current PINN approaches, which rely, like most grid-based numerical schemes, on adding artificial dissipation. Here, we address the fundamental question of which network architectures are best suited to learn the complex behavior of non-linear PDEs. We focus on network architecture rather than on residual regularization. Our new methodology, called Physics-Informed Attention-based Neural Networks, (PIANNs), is a combination of recurrent neural networks and attention mechanisms. The attention mechanism adapts the behavior of the deep neural network to the non-linear features of the solution, and break the current limitations of PINNs. We find that PIANNs effectively capture the shock front in a hyperbolic model problem, and are capable of providing high-quality solutions inside and beyond the training set.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
WuYixiao1012完成签到,获得积分10
刚刚
冬草完成签到,获得积分10
刚刚
小巧的白竹完成签到,获得积分10
刚刚
ziy完成签到,获得积分10
刚刚
Aurora.H完成签到,获得积分10
1秒前
宗佳茹完成签到,获得积分10
1秒前
LZKUN完成签到,获得积分10
1秒前
科目三的应助被huhuiya采纳,获得10
1秒前
2秒前
YS0701完成签到,获得积分10
2秒前
ponysmile发布了新的文献求助30
2秒前
2秒前
2秒前
lala完成签到,获得积分10
3秒前
时途完成签到,获得积分10
3秒前
中和皇极的应助被古月水兽采纳,获得10
3秒前
makenemore完成签到,获得积分10
3秒前
开心没烦恼完成签到,获得积分10
3秒前
WRWRWR完成签到,获得积分10
3秒前
911完成签到 ,获得积分10
4秒前
天天向上完成签到 ,获得积分10
4秒前
希望天下0贩的0的应助被远方采纳,获得10
5秒前
fogsea完成签到,获得积分10
5秒前
5秒前
6秒前
邓宸峰完成签到,获得积分10
6秒前
6秒前
夜未央完成签到 ,获得积分10
6秒前
7秒前
研友_VZG7GZ的应助被啊琴黎采纳,获得10
7秒前
隐形小兔子完成签到,获得积分10
7秒前
jiajia完成签到,获得积分10
7秒前
7秒前
huhuiya完成签到,获得积分10
8秒前
坚定的连虎完成签到,获得积分10
8秒前
9秒前
9秒前
清风完成签到,获得积分10
9秒前
fj完成签到,获得积分10
9秒前
fogsea发布了新的文献求助10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180135
求助须知:如何正确求助?哪些是违规求助? 9570290
关于积分的说明 21809391
捐赠科研通 7776237
什么是DOI,文献DOI怎么找? 3433266
关于科研通互助平台的介绍 2557465
邀请新用户注册赠送积分活动 2479039