1. Creating Trends for Reservoir Modelling Using ANN
Markus Lund Vevle*, Jon Magne Aagaard

2. Creating Trends for Reservoir Modelling Using ANN
Trends help describe large scale reservoir characteristics
There can be both a lateral and depth trend
Trend analysis can be time consuming
Linear regression is one way of extracting trends
ANN can do regression modelling, how does it compare?
Emerson Confidential

3. Outline
Data used
Algorithm
Results
Summary
Emerson Confidential

4. Data used Gullfaks, offshore Norway:
151 wells in total
5 zones, with per zone with data
Average cell thickness ~2 m
Amplitude seismic
Maui, Taranaki basin, New Zealand:
5 wells with data (synthetic)
Acoustic impedance
Average cell thickness ~ 6.5 m
Emerson Confidential

5. Algorithm ANN, structure and backpropagation algorithm in C++
SoftSign for activation function
Root Mean Squared Error
RMSProp for Mini Batch training
Custom adaptive algorithm for epoch training.
Network architecture restricted to equal sized hidden layers
Training and verification data grouped according to K-fold cross validation methodology
3D output of one epoch, optimum epochs and from linear regression
Emerson Confidential

6. Gullfaks - settings Input settings: Runtime graph showing
Softsign activation function for hidden layers
Linear activation function for output layer
3 hidden layers
3 neurons in each layer
10 cross validation groups
Mini-Batch size 128
Blocked well data, porosity, and depth information
Runtime graph showing
Linear regression prediction error (green)
NN prediction error (red)
NN optimum prediction error (purple/violet)
NN training error (black)
Emerson Confidential

7. Gullfaks Tarbert – Well data vs trend output Results
Both wells used for training
Subtle difference between NN (blue) and Linear reg (black)

8. Gullfaks Tarbert – Well data vs trend output Results
Both log tracks are the same well
Left figure when well was used for training
Right figure when well was left out

9. Gullfaks Tarbert – Well data vs trend output Results
More variability in well data → potential for overfitting
NN (blue) captures better the decreasing trend in the bottom (left figure)

10. Gullfaks Tarbert – Well data Results
Apparent trend first increasing porosity, then decreasing
Emerson Confidential

11. Gullfaks Tarbert – Well data and Linear regression Results
Lower part of the trend is captured
Emerson Confidential

12. Gullfaks Tarbert – Well data and ANN (one epoch) Results
Both upper and lower part of the trend is captured
Emerson Confidential

13. Gullfaks Tarbert – Well data and ANN (one epoch + optimum) Results
Both upper and lower part of the trend is captured
Emerson Confidential

14. Gullfaks Tarbert – Output in 3D Results
Blue dots – Wells
Input data centered around the middle
Least knowledge about the east flank

15. Gullfaks Tarbert – Output in 3D
Results

16. Gullfaks Tarbert – Cross section west-east Results
Subtle differences where there is well control

17. Gullfaks – other zones Results Is it always necessary?
Often seen prediction error from linear regression vs NN is very small ~ 1%

18. Gullfaks – other zones
Results
Sometimes you get strange effects

19. Gullfaks – other zones
Results

20. Gullfaks – other zones
Results

21. Maui
Results
5 wells with synthetic data
AI parameter

22. Maui
Results AI
ANN output trend

23. Maui
Results

24. Maui
Results

25. Maui
Results
Overall trend captured

26. Maui
Results
More details are captured. Does not try to fit the biggest outliers.

27. Summary and discussion
ANN can be used for extracting trends
With only well data
Smooth output
A combination of well data and spatially distributed data, for better lateral understanding
More details emerge
Overfitting was not observed (?)
Runtime is from 10’s of seconds to a couple of minutes
More data means slower
Defining the network takes time
Is the settings we used valid across many fields?
Data is needed