Stabilized Adaptive Loss and Residual-Based Collocation for Physics-Informed Neural Networks
This addresses accuracy and training issues in PINNs for computational physics problems, representing an incremental improvement.
The paper tackles limitations of Physics-Informed Neural Networks (PINNs) in handling high-stiffness or shock-dominated problems by developing an adaptive loss balancing scheme and a residual-based collocation scheme, reducing relative L2 errors by about 44% for Burgers' equation and 70% for Allen-Cahn equation compared to traditional PINNs.
Physics-Informed Neural Networks (PINNs) have been recognized as a mesh-free alternative to solve partial differential equations where physics information is incorporated. However, in dealing with problems characterized by high stiffness or shock-dominated dynamics, traditional PINNs have been found to have limitations, including unbalanced training and inaccuracy in solution, even with small physics residuals. In this research, we seek to address these limitations using the viscous Burgers' equation with low viscosity and the Allen-Cahn equation as test problems. In addressing unbalanced training, we have developed a new adaptive loss balancing scheme using smoothed gradient norms to ensure satisfaction of initial and boundary conditions. Further, to address inaccuracy in the solution, we have developed an adaptive residual-based collocation scheme to improve the accuracy of solutions in the regions with high physics residuals. The proposed new approach significantly improves solution accuracy with consistent satisfaction of physics residuals. For instance, in the case of Burgers' equation, the relative L2 error is reduced by about 44 percent compared to traditional PINNs, while for the Allen-Cahn equation, the relative L2 error is reduced by approximately 70 percent. Additionally, we show the trustworthy solution comparison of the proposed method using a robust finite difference solver.