Table 6 Results of Algorithm 1 with gaussian noise added to sparse data for Schrödinger equation.
From: Parameter identification for PDEs using sparse interior data and a recurrent neural network
GaussiaNoise | ||||
|---|---|---|---|---|
Results | \(\sigma = 0.01\) | \(\sigma = 0.03\) | \(\sigma = 0.05\) | \(\sigma = 0.1\) |
Relative \(L_{2}\) errors | 5.55e\(-\)3 | 6.46e\(-\)3 | 1.01e\(-\)2 | 2.32e\(-\)2 |
Estimated diffusion rate errors | 4.12e\(-\)3 | 6.32e\(-\)3 | 7.67e\(-\)3 | 1.02e\(-\)2 |
