![](https://static.wixstatic.com/media/2a3ff9_c6f97cd05abd40a5acae59058fecfd25.png/v1/fill/w_96,h_96,al_c,q_85,usm_0.66_1.00_0.01,blur_2,enc_auto/2a3ff9_c6f97cd05abd40a5acae59058fecfd25.png)
Post Processing Sparse And Instantaneous 2D Velocity Fields Using Physics-Informed Neural Networks
D. Di Carlo (1), D. Heitz (2), T. Corpetti (1)
(1) Univ. de Rennes 2, LETG, CNRS, Rennes, France
(2) INRAE, OPAALE, Rennes, France
DOI:
This work tackles the problem of resolving high-resolution velocity fields from a set of sparse off-grid observations. We follow the framework of Physics-Informed Neural Networks where simple Multi-layer Perceptor (MLP) are trained to solve partial differential equations (PDEs). In contrast with other state-of-the-art methods based of Convolutional Neural Networks, these models can be applied to super-resolve sparse Lagrangian velocity measurements. Moreover, such a framework can be easily extended to output divergence-free quantities and offer simple implementation of prior physical as regularization terms. In particular, we employ a sub-grid model based on structure-functions to improve the accuracy of the super-resolved velocity fields of turbulent flows. Numerical experimentation on synthetic data shows that the proposed approach can accurately reconstruct dense Eulerian velocity fields from sparse Lagrangian velocity measurements.
![20th Edition](https://static.wixstatic.com/media/2a3ff9_3d2f6b2c316c4388bffb37600c2e7ded~mv2.png/v1/fill/w_572,h_322,al_c,q_85,usm_0.66_1.00_0.01,enc_auto/Image-empty-state.png)