Yanlai Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yanlai Chen has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Akil Narayan
Department of Mathematics, University of Utah, Salt Lake City, USA
7 shared publications - Zhenli Xu
Shanghai Jiao Tong University
7 shared publications - Fengyan Li
Department of Mathematical Sciences, Rensselaer Polytechnic Institute, Troy, USA
5 shared publications - Sigal Gottlieb
Department of Mathematics, University of Massachusetts, Dartmouth, USA
5 shared publications - Bernardo Cockburn
School of Mathematics, University of Minnesota, Minneapolis, USA
4 shared publications - Bo Dong
Department of Mathematics, University of Massachusetts Dartmouth, North Dartmouth, USA
4 shared publications
Latest Publications
- 22 September 2026
- Published by Elsevier in Computers & Mathematics with Applications
- Vol. 222, 223-243
EGPT-PINN: Entropy-regularized generative pre-trained physics informed neural networks for parameterized nonlinear conservation laws
- 22 September 2026
- Published by Elsevier in Computers & Mathematics with Applications
- Vol. 222, 223-243
EGPT-PINN: Entropy-regularized generative pre-trained physics informed neural networks for parameterized nonlinear conservation laws
- Open Access
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
High-order Conservative Discontinuous Galerkin Methods via Implicit Penalization for the Generalized Korteweg--de Vries Equation and the Hirota--Satsuma KdV System
We develop new conservative discontinuous Galerkin (DG) methods for nonlinear wave problems, focusing on the generalized Korteweg--de Vries (gKdV) equation and the coupled Hirota--Satsuma KdV (HS-KdV) system. The proposed methods preserve mass through the single-valued structure of numerical traces, while energy and Hamiltonian conservation are enforced by implicitly determining penalty parameters in the numerical traces through auxiliary conservation constraints. In our previous work [11], we developed a conservative DG method for the gKdV equation; however, that formulation involves the time derivative of the jump of the approximate solution, which complicates extensions beyond second-order temporal accuracy. Our new formulation overcomes this limitation by introducing a redesigned trace configuration that eliminates the derivative-of-jump term. {This novel enhancement seamlessly paves the way for higher-order} time discretizations and requires solving fewer nonlinear systems per time step than the previous approach. For the coupled HS-KdV system, we present the first conservative DG method that preserves all three invariants of the exact solution. Numerical results demonstrate the accuracy and expected convergence behavior of the proposed methods, as well as long-time stability and strong conservation properties for both the gKdV equation and HS-KdV system.
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHigh-order Conservative Discontinuous Galerkin Methods via Implicit Penalization for the Generalized Korteweg--de Vries Equation and the Hirota--Satsuma KdV System
We develop new conservative discontinuous Galerkin (DG) methods for nonlinear wave problems, focusing on the generalized Korteweg--de Vries (gKdV) equation and the coupled Hirota--Satsuma KdV (HS-KdV) system. The proposed methods preserve mass through the single-valued structure of numerical traces, while energy and Hamiltonian conservation are enforced by implicitly determining penalty parameters in the numerical traces through auxiliary conservation constraints. In our previous work [11], we developed a conservative DG method for the gKdV equation; however, that formulation involves the time derivative of the jump of the approximate solution, which complicates extensions beyond second-order temporal accuracy. Our new formulation overcomes this limitation by introducing a redesigned trace configuration that eliminates the derivative-of-jump term. {This novel enhancement seamlessly paves the way for higher-order} time discretizations and requires solving fewer nonlinear systems per time step than the previous approach. For the coupled HS-KdV system, we present the first conservative DG method that preserves all three invariants of the exact solution. Numerical results demonstrate the accuracy and expected convergence behavior of the proposed methods, as well as long-time stability and strong conservation properties for both the gKdV equation and HS-KdV system.
- 25 June 2026
- Published by Global Science Press in Communications in Computational Physics
- Vol. 40 (4) , 1293-1316
$S^2$GPT-PINN: Reduced Basis and Hyper Reduction-Driven Double Reduction for Physics-Informed Neural Networks
We propose $S^2$GPT-PINN, Sparse and Small Generative Pre-Trained Physics-Informed Neural Network, for solving parametric partial differential equations (PDEs). $S^2$GPT-PINN is tailored to domain-specific (families of) PDEs and characterized by its compact architecture and minimal computational need. Leveraging a small amount of extremely high quality data via a mathematically rigorous greedy algorithm following the traditional Reduced Basis Method, $S^2$GPT-PINN relies on orders of magnitude less parameters than PINNs to achieve extremely high efficiency via two levels of customizations and reductions. The first is knowledge distillation via task-specific activation functions that are transferred from Pre-Trained PINNs selected by the greedy algorithm. The second is a judicious hyper reduction when calculating the physics-informed loss of the network compressing the number of collocation points by orders of magnitude to the size of the small network.
- 25 June 2026
- Published by Global Science Press in Communications in Computational Physics
- Vol. 40 (4) , 1293-1316
$S^2$GPT-PINN: Reduced Basis and Hyper Reduction-Driven Double Reduction for Physics-Informed Neural Networks
We propose $S^2$GPT-PINN, Sparse and Small Generative Pre-Trained Physics-Informed Neural Network, for solving parametric partial differential equations (PDEs). $S^2$GPT-PINN is tailored to domain-specific (families of) PDEs and characterized by its compact architecture and minimal computational need. Leveraging a small amount of extremely high quality data via a mathematically rigorous greedy algorithm following the traditional Reduced Basis Method, $S^2$GPT-PINN relies on orders of magnitude less parameters than PINNs to achieve extremely high efficiency via two levels of customizations and reductions. The first is knowledge distillation via task-specific activation functions that are transferred from Pre-Trained PINNs selected by the greedy algorithm. The second is a judicious hyper reduction when calculating the physics-informed loss of the network compressing the number of collocation points by orders of magnitude to the size of the small network.
- Open Access
- 3 April 2026
- Published by Elsevier in SSRN Electronic Journal
Nonlinear Model Order Reduction on Quadratic Manifolds via Greedy Algorithms with Dimension-Dependent Regularization
Traditional projection-based reduced-order modeling approximates the full-order model by projecting it onto a linear subspace. With a fast-decaying Kolmogorov n-width of the solution manifold, the resulting reduced-order model (ROM) can be an efficient and accurate emulator. However, for parametric partial differential equations with slowly decaying Kolmogorov n-width, the dimension of the linear subspace required for a reasonable accuracy becomes very large, which undermines computational efficiency. To address this limitation, quadratic manifold methods have recently been proposed. These data-driven methods first identify a quadratic mapping by minimizing the linear projection error over a large set of snapshots, often with the aid of regularization techniques to solve the associated minimization problem, and then use this mapping to construct ROMs.In this paper, we propose and test a novel enhancement to this quadratic manifold approach by introducing a first-of-its-kind double-greedy algorithm on the regularization parameters coupled with a standard greedy algorithm on the physical parameter. Our approach balances the trade-off between the accuracy of the quadratic mapping and the stability of the resulting nonlinear ROM, leading to a highly efficient and data-sparse algorithm. Numerical experiments conducted on equations such as linear transport, acoustic wave, advection-diffusion, and Burgers' demonstrate the accuracy, efficiency, and stability of the proposed algorithm.
- 3 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessNonlinear Model Order Reduction on Quadratic Manifolds via Greedy Algorithms with Dimension-Dependent Regularization
Traditional projection-based reduced-order modeling approximates the full-order model by projecting it onto a linear subspace. With a fast-decaying Kolmogorov n-width of the solution manifold, the resulting reduced-order model (ROM) can be an efficient and accurate emulator. However, for parametric partial differential equations with slowly decaying Kolmogorov n-width, the dimension of the linear subspace required for a reasonable accuracy becomes very large, which undermines computational efficiency. To address this limitation, quadratic manifold methods have recently been proposed. These data-driven methods first identify a quadratic mapping by minimizing the linear projection error over a large set of snapshots, often with the aid of regularization techniques to solve the associated minimization problem, and then use this mapping to construct ROMs.In this paper, we propose and test a novel enhancement to this quadratic manifold approach by introducing a first-of-its-kind double-greedy algorithm on the regularization parameters coupled with a standard greedy algorithm on the physical parameter. Our approach balances the trade-off between the accuracy of the quadratic mapping and the stability of the resulting nonlinear ROM, leading to a highly efficient and data-sparse algorithm. Numerical experiments conducted on equations such as linear transport, acoustic wave, advection-diffusion, and Burgers' demonstrate the accuracy, efficiency, and stability of the proposed algorithm.
- 18 December 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 548
Reduced basis methods for parametric steady-state radiative transfer equation
- 18 December 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 548
Reduced basis methods for parametric steady-state radiative transfer equation
- Open Access
Reduced Basis Methods for Parametric Steady-State Radiative Transfer Equation
The radiative transfer equation (RTE) is a fundamental mathematical model to describe physical phenomena involving the propagation of radiation and its interactions with the host medium. Deterministic methods can produce accurate solutions without any statistical noise, yet often at a price of expensive computational costs originating from the intrinsic high dimensionality of the model. With this work, we present the first systematic investigation of projection-based reduced order models (ROMs) following the reduced basis method (RBM) framework to simulate the parametric steady-state RTE with isotropic scattering and one energy group. Four ROMs are designed, with each defining a nested family of reduced surrogate solvers of different resolution/fidelity. They are based on either a Galerkin or least-squares Petrov-Galerkin projection and utilize either an $L_1$ or residual-based importance/error indicator. Two of the proposed ROMs are certified in the setting when the absorption cross section is positively bounded below uniformly. One technical focus and contribution lie in the proposed implementation strategies under the affine assumption of the parameter dependence of the model. These well-crafted broadly applicable strategies not only ensure the efficiency and accuracy of the offline training stage and the online prediction of reduced surrogate solvers, they also take into account the conditioning of the reduced systems as well as the stagnation-free residual evaluation for numerical robustness. Computational complexities are derived for both the offline training and online prediction stages of the proposed model order reduction strategies, and they are demonstrated numerically along with the accuracy and robustness of the reduced surrogate solvers. Numerically we observe four to six orders of magnitude speedup of our ROMs compared to full order models for some 2D2v examples.Open AccessReduced Basis Methods for Parametric Steady-State Radiative Transfer Equation
The radiative transfer equation (RTE) is a fundamental mathematical model to describe physical phenomena involving the propagation of radiation and its interactions with the host medium. Deterministic methods can produce accurate solutions without any statistical noise, yet often at a price of expensive computational costs originating from the intrinsic high dimensionality of the model. With this work, we present the first systematic investigation of projection-based reduced order models (ROMs) following the reduced basis method (RBM) framework to simulate the parametric steady-state RTE with isotropic scattering and one energy group. Four ROMs are designed, with each defining a nested family of reduced surrogate solvers of different resolution/fidelity. They are based on either a Galerkin or least-squares Petrov-Galerkin projection and utilize either an $L_1$ or residual-based importance/error indicator. Two of the proposed ROMs are certified in the setting when the absorption cross section is positively bounded below uniformly. One technical focus and contribution lie in the proposed implementation strategies under the affine assumption of the parameter dependence of the model. These well-crafted broadly applicable strategies not only ensure the efficiency and accuracy of the offline training stage and the online prediction of reduced surrogate solvers, they also take into account the conditioning of the reduced systems as well as the stagnation-free residual evaluation for numerical robustness. Computational complexities are derived for both the offline training and online prediction stages of the proposed model order reduction strategies, and they are demonstrated numerically along with the accuracy and robustness of the reduced surrogate solvers. Numerically we observe four to six orders of magnitude speedup of our ROMs compared to full order models for some 2D2v examples. - Open Access
Derivative-informed Graph Convolutional Autoencoder with Phase Classification for the Lifshitz-Petrich Model
The Lifshitz-Petrich (LP) model is a classical model for describing complex spatial patterns such as quasicrystals and multiphase structures. Solving and classifying the solutions of the LP model is challenging due to the presence of high-order gradient terms and the long-range orientational order characteristic of the quasicrystals. To address these challenges, we propose a Derivative-informed Graph Convolutional Autoencoder (DiGCA) to classify the multi-component multi-state solutions of the LP model. The classifier consists of two stages. In the offline stage, the DiGCA phase classifier innovatively incorporates both solutions and their derivatives for training a graph convolutional autoencoder which effectively captures intricate spatial dependencies while significantly reducing the dimensionality of the solution space. In the online phase, the framework employs a neural network classifier to efficiently categorize encoded solutions into distinct phase diagrams. The numerical results demonstrate that the DiGCA phase classifier accurately solves the LP model, classifies its solutions, and rapidly generates detailed phase diagrams in a robust manner, offering significant improvements in both efficiency and accuracy over traditional methods.
Open AccessDerivative-informed Graph Convolutional Autoencoder with Phase Classification for the Lifshitz-Petrich Model
The Lifshitz-Petrich (LP) model is a classical model for describing complex spatial patterns such as quasicrystals and multiphase structures. Solving and classifying the solutions of the LP model is challenging due to the presence of high-order gradient terms and the long-range orientational order characteristic of the quasicrystals. To address these challenges, we propose a Derivative-informed Graph Convolutional Autoencoder (DiGCA) to classify the multi-component multi-state solutions of the LP model. The classifier consists of two stages. In the offline stage, the DiGCA phase classifier innovatively incorporates both solutions and their derivatives for training a graph convolutional autoencoder which effectively captures intricate spatial dependencies while significantly reducing the dimensionality of the solution space. In the online phase, the framework employs a neural network classifier to efficiently categorize encoded solutions into distinct phase diagrams. The numerical results demonstrate that the DiGCA phase classifier accurately solves the LP model, classifies its solutions, and rapidly generates detailed phase diagrams in a robust manner, offering significant improvements in both efficiency and accuracy over traditional methods.
- Open Access
ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
We propose a novel data-lean operator learning algorithm, the Reduced Basis Neural Operator (ReBaNO), to solve a group of PDEs with multiple distinct inputs. Inspired by the Reduced Basis Method and the recently introduced Generative Pre-Trained Physics-Informed Neural Networks, ReBaNO relies on a mathematically rigorous greedy algorithm to build its network structure offline adaptively from the ground up. Knowledge distillation via task-specific activation function allows ReBaNO to have a compact architecture requiring minimal computational cost online while embedding physics. In comparison to state-of-the-art operator learning algorithms such as PCA-Net, DeepONet, FNO, and CNO, numerical results demonstrate that ReBaNO significantly outperforms them in terms of eliminating/shrinking the generalization gap for both in- and out-of-distribution tests and being the only operator learning algorithm achieving strict discretization invariance.
Open AccessReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
We propose a novel data-lean operator learning algorithm, the Reduced Basis Neural Operator (ReBaNO), to solve a group of PDEs with multiple distinct inputs. Inspired by the Reduced Basis Method and the recently introduced Generative Pre-Trained Physics-Informed Neural Networks, ReBaNO relies on a mathematically rigorous greedy algorithm to build its network structure offline adaptively from the ground up. Knowledge distillation via task-specific activation function allows ReBaNO to have a compact architecture requiring minimal computational cost online while embedding physics. In comparison to state-of-the-art operator learning algorithms such as PCA-Net, DeepONet, FNO, and CNO, numerical results demonstrate that ReBaNO significantly outperforms them in terms of eliminating/shrinking the generalization gap for both in- and out-of-distribution tests and being the only operator learning algorithm achieving strict discretization invariance.
- Open Access
AAROC: Reduced Over-Collocation Method with Adaptive Time Partitioning and Adaptive Enrichment for Parametric Time-Dependent Equations
Nonlinear and nonaffine terms in parametric partial differential equations can potentially lead to a computational cost of a reduced order model (ROM) that is comparable to the cost of the original full order model (FOM). To address this, the Reduced Residual Reduced Over-Collocation method (R2-ROC) is developed as a hyper-reduction method within the framework of the reduced basis method in the collocation setting. R2-ROC greedily selects two sets of reduced collocation points based on the (generalized) empirical interpolation method for both solution snapshots and residuals, thereby avoiding the computational inefficiency. The vanilla R2-ROC method can face instability when applied to parametric fluid dynamic problems. To address this, an adaptive enrichment strategy has been proposed to stabilize the ROC method. However, this strategy can involve in an excessive number of reduced collocation points, thereby negatively impacting online efficiency. To ensure both efficiency and accuracy, we propose an adaptive time partitioning and adaptive enrichment strategy-based ROC method (AAROC). The adaptive time partitioning dynamically captures the low-rank structure, necessitating fewer reduced collocation points being sampled in each time segment. Numerical experiments on the parametric viscous Burgers' equation and lid-driven cavity problems demonstrate the efficiency, enhanced stability, and accuracy of the proposed AAROC method.
Open AccessAAROC: Reduced Over-Collocation Method with Adaptive Time Partitioning and Adaptive Enrichment for Parametric Time-Dependent Equations
Nonlinear and nonaffine terms in parametric partial differential equations can potentially lead to a computational cost of a reduced order model (ROM) that is comparable to the cost of the original full order model (FOM). To address this, the Reduced Residual Reduced Over-Collocation method (R2-ROC) is developed as a hyper-reduction method within the framework of the reduced basis method in the collocation setting. R2-ROC greedily selects two sets of reduced collocation points based on the (generalized) empirical interpolation method for both solution snapshots and residuals, thereby avoiding the computational inefficiency. The vanilla R2-ROC method can face instability when applied to parametric fluid dynamic problems. To address this, an adaptive enrichment strategy has been proposed to stabilize the ROC method. However, this strategy can involve in an excessive number of reduced collocation points, thereby negatively impacting online efficiency. To ensure both efficiency and accuracy, we propose an adaptive time partitioning and adaptive enrichment strategy-based ROC method (AAROC). The adaptive time partitioning dynamically captures the low-rank structure, necessitating fewer reduced collocation points being sampled in each time segment. Numerical experiments on the parametric viscous Burgers' equation and lid-driven cavity problems demonstrate the efficiency, enhanced stability, and accuracy of the proposed AAROC method.
- 8 July 2024
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 430
TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs
- 8 July 2024
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 430
TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs