4. Conclusions

This work compares the solutions of a one-dimensional viscous Burgers’ equation of a test problem using a Physics Informed Neural Network (PINN) and a numerical Gaussian Quadrature Method (GQM) method. The Burgers' equation is a partial differential equation (PDE) with derivatives in both space and time, which is commonly solved by a numerical method, as the GQM. A comparison of the accuracy and required processing time of both solutions executed in the LNCC Santos Dumont supercomputer is also presented for different number of OpenMP threads using CPU cores. The GQM presented much lower processing times, and better speedups and parallel efficiencies. As future work, it is intended to exploit other PINN architectures and numerical methods, as well as taking advantage of GPU use, mainly for the PINN.