From: Deep learning method for super-resolution reconstruction of the spatio-temporal flow field
Dataset | Model | MAEÂ (\(\times 10^{-4}\text {s}^{-1}\)) | \(L_2\) error norms |
---|---|---|---|
\(Dataset_{s}\) | MST-UNet | 2.44 | 0.046 |
 | \(\text {SLR-UNet}\) | 4.00 | 0.065 |
 | \(\text {MTLR1-UNet}\) | 2.99 | 0.055 |
 | \(\text {MTLR2-UNet}\) | 3.52 | 0.062 |
\(Dataset_{l}\) | MST-UNet | 1.24 | 0.031 |
 | \(\text {SLR-UNet}\) | 1.94 | 0.039 |
 | \(\text {MTLR1-UNet}\) | 1.76 | 0.038 |
 | \(\text {MTLR2-UNet}\) | 1.81 | 0.038 |