Physics-Informed Neural Networks for Joint Source and Parameter Estimation in Advection-Diffusion Equations
Organizations: School of Agriculture and Science, University of KwaZulu-Natal, Pietermaritzburg, SA 3201 · AIMS RIC, Kigali, Rwanda · Department of Applied Mathematics, University of Washington, Seattle, WA, USA
Abstract
Source inversion problems under sparse measurements for parabolic partial differential equations (PDEs) are particularly challenging to solve using physics-informed neural networks (PINNs), due to their severe ill-posedness and the multiple unknowns involved including the source function and the PDE parameters. Although the neural tangent kernel (NTK) of PINNs has been widely used in forward problems involving a single neural network, its extension to inverse problems involving multiple neural networks remains less explored. In this work, we propose a weighted adaptive approach based on the NTK of PINNs including multiple networks representing the solution, the unknown source, and the PDE parameters. The key idea behind our methodology is to simultaneously solve the joint recovery of these unknowns thereby using the underlying PDE as a constraint that couples multiple unknowns functional parameters, leading to more efficient use of the limited information in the measurements. Furthermore, we provide a theoretical analysis of the approximation error of PINNs in a source inverse problem governed by the advection-diffusion equation (ADE) with known velocity and diffusion coefficients. In particular, we derive an error bound for the estimated source function in terms of the PINN's training error, the noise level and the discretization error. This analysis provides theoretical insight into the factors influencing the approximation accuracy. We present numerical experiments on 2D and 3D ADE using different types of measurements data reflecting practical engineering systems. Our results demonstrate the successful performance of PINNs in solving our source inversion problem and its robustness to noise in the measurements.
Figures & tables
| Obs | Vx | Vy | D | |||
| Noise | Predicted | Relative error | Predicted | Relative error | Predicted | Relative error |
| 0.20074 | 0.37% | -0.2014 | 0.7% | 0.00944 | 5.6% | |
| 0.20151 | 0.75% | -0.20174 | 0.87% | 0.00933 | 6.7% | |
| 0.2038 | 1.9% | -0.2058 | 2.9 | 0.00917 | 8.3% | |
| 15 Obs | Vx | Vy | D | |||
| Noise | Predicted | Relative error | Predicted | Relative error | Predicted | Relative error |
| 4 Obs | Vx | Vy | D | |||
| Noise | Predicted | Relative error | Predicted | Relative error | Predicted | Relative error |
| 0.19912 | 0.44% | -0.20525 | 2.62% | 0.008643 | 13.57% | |
| 0.19469 | 2.65% | -0.15938 | 20.31% | 0.00538 | 46.2% | |
| 0.18404 | 7.98% | -0.23356 | 16.78% | 0.0021 | 79% | |
| 15 Obs | Vx | Vy | D | |||
| Noise | Predicted | Relative error | Predicted | Relative error | Predicted | Relative error |
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
PDE Inverse Problems
Partial differential equation (PDE) inverse problems recover hidden fields, parameters, or sources from observations governed by physical laws.
See all 114 papers