Deep Ray
Research Subjects
Deep Ray has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Assad A. Oberai
Department of Aerospace and Mechanical Engineering, University of Southern California, Los Angeles, CA 90089, USA
16 shared publications - Orazio Pinti
University of Southern California
8 shared publications - Jan S. Hesthaven
Karlsruhe Institute of Technology
5 shared publications - Dhruv V. Patel
Department of Mechanical Engineering Stanford University
4 shared publications - Siddhartha Mishra
ETH Zurich
4 shared publications - Praveen Chandrashekar
Centre for Applicable Mathematics, Tata Institute of Fundamental Research, Bangalore, India
3 shared publications
Latest Publications
- Open Access
- 8 May 2026
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 458
An optimal Petrov–Galerkin framework for operator networks
- 8 May 2026
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 458
Open AccessAn optimal Petrov–Galerkin framework for operator networks
- 5 November 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (6) , C1196-C1222
Learning WENO for Entropy Stable Schemes to Solve Conservation Laws
Entropy conditions play a crucial role in the extraction of a physically relevant solution for systems of conservation laws, thus motivating the construction of entropy stable schemes that satisfy a discrete analogue of such conditions. TeCNO schemes [U. S. Fjordholm, S. Mishra, and E. Tadmor, SIAM J. Numer. Anal., 50 (2012), pp. 544–573] form a class of arbitrary high-order entropy stable finite difference solvers, which require specialized reconstruction algorithms satisfying the sign property at each cell interface. Third-order weighted essentially non-oscillatory (WENO) schemes called SP-WENO [U. S. Fjordholm and D. Ray, J. Sci. Comput., 68 (2016), pp. 42–63] and SP-WENOc [D. Ray, A third-order entropy stable scheme for the compressible Euler equations, in Theory, Numerics and Applications of Hyperbolic Problems II, Springer, 2018, pp. 503–515] have been designed to satisfy the sign property. However, these WENO algorithms can perform poorly near shocks, with the numerical solutions exhibiting large spurious oscillations. In the present work, we propose a variant of the SP-WENO, termed as Deep Sign-Preserving WENO (DSP-WENO), where a neural network is trained to learn the WENO weighting strategy. The sign property and third-order accuracy are strongly imposed in the algorithm, which constrains the WENO weight selection region to a convex polygon. Thereafter, a neural network is trained to select the WENO weights from this convex region with the goal of improving the shock-capturing capabilities without sacrificing the rate of convergence in smooth regions. The proposed synergistic approach retains the mathematical framework of the TeCNO scheme while integrating deep learning to remedy the computational issues of the WENO-based reconstruction. We present several numerical experiments to demonstrate the significant improvement with DSP-WENO over the existing variants of WENO satisfying the sign property.
- 5 November 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (6) , C1196-C1222
Learning WENO for Entropy Stable Schemes to Solve Conservation Laws
Entropy conditions play a crucial role in the extraction of a physically relevant solution for systems of conservation laws, thus motivating the construction of entropy stable schemes that satisfy a discrete analogue of such conditions. TeCNO schemes [U. S. Fjordholm, S. Mishra, and E. Tadmor, SIAM J. Numer. Anal., 50 (2012), pp. 544–573] form a class of arbitrary high-order entropy stable finite difference solvers, which require specialized reconstruction algorithms satisfying the sign property at each cell interface. Third-order weighted essentially non-oscillatory (WENO) schemes called SP-WENO [U. S. Fjordholm and D. Ray, J. Sci. Comput., 68 (2016), pp. 42–63] and SP-WENOc [D. Ray, A third-order entropy stable scheme for the compressible Euler equations, in Theory, Numerics and Applications of Hyperbolic Problems II, Springer, 2018, pp. 503–515] have been designed to satisfy the sign property. However, these WENO algorithms can perform poorly near shocks, with the numerical solutions exhibiting large spurious oscillations. In the present work, we propose a variant of the SP-WENO, termed as Deep Sign-Preserving WENO (DSP-WENO), where a neural network is trained to learn the WENO weighting strategy. The sign property and third-order accuracy are strongly imposed in the algorithm, which constrains the WENO weight selection region to a convex polygon. Thereafter, a neural network is trained to select the WENO weights from this convex region with the goal of improving the shock-capturing capabilities without sacrificing the rate of convergence in smooth regions. The proposed synergistic approach retains the mathematical framework of the TeCNO scheme while integrating deep learning to remedy the computational issues of the WENO-based reconstruction. We present several numerical experiments to demonstrate the significant improvement with DSP-WENO over the existing variants of WENO satisfying the sign property.
- Open Access
- 9 May 2025
- Published by Springer Nature
- p. C1
Correction to: Deep Learning and Computational Physics
- 9 May 2025
- Published by Springer Nature
- p. C1
Open AccessCorrection to: Deep Learning and Computational Physics
- Open Access
An optimal Petrov-Galerkin framework for operator networks
The optimal Petrov-Galerkin formulation to solve partial differential equations (PDEs) recovers the best approximation in a specified finite-dimensional (trial) space with respect to a suitable norm. However, the recovery of this optimal solution is contingent on being able to construct the optimal weighting functions associated with the trial basis. While explicit constructions are available for simple one- and two-dimensional problems, such constructions for a general multidimensional problem remain elusive. In the present work, we revisit the optimal Petrov-Galerkin formulation through the lens of deep learning. We propose an operator network framework called Petrov-Galerkin Variationally Mimetic Operator Network (PG-VarMiON), which emulates the optimal Petrov-Galerkin weak form of the underlying PDE. The PG-VarMiON is trained in a supervised manner using a labeled dataset comprising the PDE data and the corresponding PDE solution, with the training loss depending on the choice of the optimal norm. The special architecture of the PG-VarMiON allows it to implicitly learn the optimal weighting functions, thus endowing the proposed operator network with the ability to generalize well beyond the training set. We derive approximation error estimates for PG-VarMiON, highlighting the contributions of various error sources, particularly the error in learning the true weighting functions. Several numerical results are presented for the advection-diffusion equation to demonstrate the efficacy of the proposed method. By embedding the Petrov-Galerkin structure into the network architecture, PG-VarMiON exhibits greater robustness and improved generalization compared to other popular deep operator frameworks, particularly when the training data is limited.
Open AccessAn optimal Petrov-Galerkin framework for operator networks
The optimal Petrov-Galerkin formulation to solve partial differential equations (PDEs) recovers the best approximation in a specified finite-dimensional (trial) space with respect to a suitable norm. However, the recovery of this optimal solution is contingent on being able to construct the optimal weighting functions associated with the trial basis. While explicit constructions are available for simple one- and two-dimensional problems, such constructions for a general multidimensional problem remain elusive. In the present work, we revisit the optimal Petrov-Galerkin formulation through the lens of deep learning. We propose an operator network framework called Petrov-Galerkin Variationally Mimetic Operator Network (PG-VarMiON), which emulates the optimal Petrov-Galerkin weak form of the underlying PDE. The PG-VarMiON is trained in a supervised manner using a labeled dataset comprising the PDE data and the corresponding PDE solution, with the training loss depending on the choice of the optimal norm. The special architecture of the PG-VarMiON allows it to implicitly learn the optimal weighting functions, thus endowing the proposed operator network with the ability to generalize well beyond the training set. We derive approximation error estimates for PG-VarMiON, highlighting the contributions of various error sources, particularly the error in learning the true weighting functions. Several numerical results are presented for the advection-diffusion equation to demonstrate the efficacy of the proposed method. By embedding the Petrov-Galerkin structure into the network architecture, PG-VarMiON exhibits greater robustness and improved generalization compared to other popular deep operator frameworks, particularly when the training data is limited.
- 7 June 2024
- Published by Springer Nature
- p. 9-39
Introduction to Deep Neural Networks
- 7 June 2024
- Published by Springer Nature
- p. 71-86
Solving PDEs with Neural Networks
- 7 June 2024
- Published by Springer Nature
- p. 87-119
Operator Networks
- 7 June 2024
- Published by Springer Nature
- p. 121-146
Generative Deep Learning
- 7 June 2024
- Published by Springer Nature
- p. 1-7
Introduction
- 7 June 2024
- Published by Springer Nature
- p. 41-48
Residual Neural Networks