Solving second-order nonlinear evolution partial differential equations using deep learning*
|
Solving second-order nonlinear evolution partial differential equations using deep learning* |
| Jun Li(李军),Yong Chen(陈勇) |
| Figure 10. Hyperbolic secant initial condition. Top: a solution to the Burgers' equation is compared to the solution to the learned PDE. The system correctly captures the dynamics behavior and reproduces the solution with a relative ${{\mathbb{L}}}_{2}$ error of 3.99 × 10−02. Bottom: comparison between the predicted dynamics and the exact solution at the three temporal snapshots. The model training took approximately 7 min. |
|
|