Research Article
Developing a Robust Surrogate Model of Chemical Flooding Based on the Artificial Neural Network for Enhanced Oil Recovery Implications
Table 1
Statistical analysis of the implemented chemical flooding data samples [
9].
| Parameter | Unit | Type | Min. | Max. | Average | Standard deviation |
| Surfactant slug size | PV | Input | 0.097 | 0.259 | 0.177 | 0.072 | Surfactant concentration | Vol. fraction | Input | 0.005 | 0.03 | 0.017 | 0.011 | Polymer concentration in surfactant slug | wt.% | Input | 0.1 | 0.25 | 0.177 | 0.067 | Polymer drive size | PV | Input | 0.324 | 0.648 | 0.482 | 0.144 | Polymer concentration in polymer drive | wt.% | Input | 0.1 | 0.2 | 0.148 | 0.044 |
ratio | ā | Input | 0.01 | 0.25 | 0.129 | 0.107 | Salinity of polymer drive | Meq/mL | Input | 0.3 | 0.4 | 0.349 | 0.045 | Recovery factor (RF) | % | Output | 14.82 | 56.99 | 39.67 | 9.24 | Net present value (NPV) | $ MM | Output | 1.781 | 7.229 | 4.45 | 1.53 |
|
|