5 papers
Learning Physics from an Imperfect Ancestor
S. Mohammad Mousavi, Teeratorn Kadeethum, Nikolaos Bouklas +1
Neural operators evaluate parametric partial differential equations cheaply but degrade sharply outside their training distribution. Physics-informed neural networks avoid dependen…
Modular Variables and the Limits of Phase Detectability in Open Quantum Systems
S. V. Mousavi
Modular variables serve as a striking example of quantum nonlocality, particularly in superpositions of wave packets that are spatially well separated, where the relative phase bet…
Imposing Boundary Conditions on Neural Operators via Learned Function Extensions
Sepehr Mousavi, Siddhartha Mishra, Laura De Lorenzis
Neural operators have emerged as powerful surrogates for the solution of partial differential equations (PDEs), yet their ability to handle general, highly variable boundary condit…
Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domains
Shizheng Wen, Arsh Kumbhat, Levi Lingsch +4
The very challenging task of learning solution operators of PDEs on arbitrary domains accurately and efficiently is of vital importance to engineering and industrial simulations. D…
RIGNO: A Graph-based framework for robust and accurate operator learning for PDEs on arbitrary domains
Sepehr Mousavi, Shizheng Wen, Levi Lingsch +3
Learning the solution operators of PDEs on arbitrary domains is challenging due to the diversity of possible domain shapes, in addition to the often intricate underlying physics. W…