Table 2 Effect of dropout size on the S-BiLSTM model.
From: Application of stacked bidirectional LSTM neural networks in reservoir porosity prediction
Dropout size | MAE | RMSE | Predictive accuracy (%) |
|---|---|---|---|
0.1 | 0.0289 | 0.0399 | 21.41 |
0.2 | 0.0264 | 0.0381 | 27.81 |
0.3 | 0.0181 | 0.0315 | 50.72 |
0.4 | 0.0064 | 0.0189 | 82.44 |
0.5 | 0.0026 | 0.012 | 92.75 |
0.6 | 0.0035 | 0.0141 | 90.51 |
0.7 | 0.0053 | 0.0172 | 85.39 |
0.8 | 0.0097 | 0.0232 | 73.67 |
