Table 5 Prediction and evaluation of the timing for SWF in ASP flooding fields.

From: Research on the timing for subsequent water flooding in Alkali-Surfactant-Polymer flooding in Daqing Oilfield based on automated machine learning

ID

Block Name

Predicted Water Cut of Original Plan (%)

Optimized Predicted Water Cut (%)

Adjustment of Injection Plan

Predicted by Calculation Method in Sect. 1

Predicted by Machine Learning Model

Relative Errors

Adjustment Method

Actual Water Cut (%)

1

X34D2

97.23

95.85

95.62

0.240

Early Transition to SWF

95.65

2

X7D1

96.55

97.09

97.32

0.237

Extended Polymer Slug

97.27

3

B2DZ

94.63

96.09

95.83

0.271

Extended Polymer Slug

95.85

4

B2XD

92.27

95.58

95.2

0.398

Extended Polymer Slug

95.18

5

B2DX

94.52

96.49

96.74

0.259

Extended Polymer Slug

96.72

6

N6D

96.38

96.88

97.25

0.382

Extended Polymer Slug

97.22