Physics-informed neural networks for solving derivative-constrained partial differential equations
Open Access
- 4 May 2026
- journal article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 113 (5) , 055301
Abstract
Physics-informed neural networks (PINNs) recast partial differential equations (PDEs) solving as an optimization problem in function space by minimizing a residual-based objective, yet many applications require additional derivative-based relations that are just as fundamental as the governing equations. In this paper, we present derivative-constrained PINNs (DC-PINNs), a general framework that treats constrained PDE solving as an optimization guided by a minimum objective function criterion where the physics resides in the minimum principle. DC-PINNs embed general nonlinear constraints on states and derivatives, e.g., bounds, monotonicity, convexity, incompressibility, computed efficiently via automatic differentiation, and they employ self-adaptive loss balancing to tune the influence of each objective, reducing reliance on manual hyperparameters and problem-specific architectures. DC-PINNs consistently reduce constraint violations and improve physical fidelity versus baseline PINN variants, representative hard-constraint formulations on benchmarks, including heat diffusion with bounds, financial volatilities with arbitrage-free, and fluid flow with vortices shed. Explicitly encoding derivative constraints stabilizes training and steers optimization toward physically admissible minima even when the PDE residual alone is small, providing reliable solutions of constrained PDEs grounded in energy minimum principles.Keywords
All Related Versions
Funding Information
- Department of Science and Technology Studies, University College London
This publication has 32 references indexed in Scilit:
- Respecting causality for training physics-informed neural networksComputer Methods in Applied Mechanics and Engineering, 2024
- Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equationsAdvances in Computational Mathematics, 2023
- Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s NextJournal of Scientific Computing, 2022
- Exact imposition of boundary conditions with distance functions in physics-informed deep neural networksComputer Methods in Applied Mechanics and Engineering, 2022
- hp-VPINNs: Variational physics-informed neural networks with domain decompositionComputer Methods in Applied Mechanics and Engineering, 2021
- Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problemsComputer Methods in Applied Mechanics and Engineering, 2020
- Nektar++: Enhancing the capability and application of high-fidelity spectral/hp element methodsComputer Physics Communications, 2020
- The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational ProblemsCommunications in Mathematics and Statistics, 2018
- A note on sufficient conditions for no arbitrageFinance Research Letters, 2005
- Volatility estimation from observed option pricesDecisions in Economics and Finance, 2000