We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries. To this end, we introduce General-Geometry Neural Whitney Forms (Geo-NeW): a data-driven finite element method. We jointly learn a differential operator and compatible reduced finite element spaces defined on the underlying geometry. The resulting model is solved to generate predictions, while exactly preserving physical conservation laws through Finite Element Exterior Calculus. Geometry enters the model as a discretized mesh both through a transformer-based encoding and as the basis for the learned finite element spaces. This explicitly connects the underlying geometry and imposed boundary conditions to the solution, providing a powerful inductive bias for learning neural PDEs, which we demonstrate improves generalization to unseen domains. We provide a novel parameterization of the constitutive model ensuring the existence and uniqueness of the solution. Our approach demonstrates state-of-the-art performance on several steady-state PDE benchmarks, and provides a significant improvement over conventional baselines on out-of-distribution geometries.
Elucidating the Conformal Structure of the Brinkman Penalisation Method for Geometry-Adapted, Structure-Preserving Operator Learning of Hamiltonian PDEs
University of Bath(巴斯大学);RIKEN(理化学研究所);Kyushu University(九州大学)
Convergence of the generalization error for deep gradient flow methods for PDEs
Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands.;Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands \& Institute of Applied;Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands
A Structure-Preserving Framework for Solving Parabolic Partial Differential Equations with Neural Networks
Department of Applied Mathematics, The Hong Kong Polytechnic University(应用数学系,香港Polytechnic大学);Department of Mathematics, University of South Carolina(数学系,南卡罗来纳大学)
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
The State Key Lab of Brain-Machine Intelligence, Zhejiang University, Hangzhou, China(脑机智能国家重点实验室,浙江大学,杭州,中国);College of Computer Science and Technology, Zhejiang University, Hangzhou, China(计算机科学与技术学院,浙江大学,杭州,中国)
Convolutional-neural-operator-based transfer learning for solving PDEs
School of Mathematics(数学系);Key Laboratory of Maritime Intelligent Cyberspace Technology (Hohai University), Ministry of Education(航海智能信息空间技术重点实验室(河海大学))
Learning embeddings of non-linear PDEs: the Burgers' equation
Departament de Física Quántica i Astrofí sica, Universitat de Barcelona(巴塞罗那大学量子物理与天体物理系);Institut de Ciencies del Cosmos (ICC), Universitat de Barcelona(巴塞罗那大学天体物理研究所);Institucio Catalana de Recerca i Estudis Avancats (ICREA)(加泰罗尼亚高级研究与高级教育研究所)
UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs
Stony Brook University (SUNY)(纽约州立大学石溪分校);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学)
PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
National University of Defense Technology(国防科技大学);National SuperComputer Center in Tianjin(天津国家超算中心);National University of Singapore(新加坡国立大学);Tiangong University(天工大学);Peking University(北京大学)
Diffeomorphism Neural Operator for various domains and parameters of partial differential equations
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics(南京航空航天大学机电学院);School of Mechanical and Power Engineering, Nanjing Tech University(南京工业大学机械与动力工程学院)
School of Mathematics, Jilin University, 2699 Qianjin Street, Changchun, 130012, Jilin, China. Chair for Dynamics, Control, Machine Learning;Numerics (Alexander von Humboldt Professorship), Department of Mathematics, Friedrich–Alexander-Universit\"at Erlangen–N\"urnberg, 91058 Erlangen, Germany.;Institut de Mathematiques de Bourgogne, Université Bourgogne Europe, CNRS, 21000 Dijon, France.;Division of Mathematical Sciences, School of Physical;Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, 637371, Singapore.;School of Mathematical Sciences, Nankai University, Tianjin 300071, China.;Numerics (Alexander von Humboldt Professorship), Department of Mathematics, Friedrich–Alexander-Universit\"at Erlangen–N\"urnberg, 91058 Erlangen, Germany. Departamento de Matem\'aticas, Universidad Aut\'onoma de Madrid, 28049 Madrid, Spain. Chair of Computational Mathematics, Fundaci\'on Deusto. Av. de las Universidades, 24, 48007 Bilbao, Basque Country, Spain.