Table 3 Hyperparameter optimization results of well H22.
From: Steering drilling wellbore trajectory prediction based on the NOA-LSTM-FCNN method
Method | Number of hidden layers | Number of convolution layers | Maximum training times | Minimum training batch | learning rate |
|---|---|---|---|---|---|
BP | 75 | \ | 938 | 33 | 0.152 |
CNN | 62 | 114 | 920 | 14 | 0.0137 |
LSTM | 45 | \ | 1250 | 18 | 0.0429 |
GRU | 89 | \ | 637 | 36 | 0.0842 |
LSTM-FCNN | 52 | 198 | 526 | 29 | 0.03871 |
