System and method for analyzing reservoir changes during production
There is disclosed a system and method for analyzing geological features of a reservoir, such as a subterranean hydrocarbon reservoir undergoing changes during different stages of its production, by utilizing an artificial neural network to learn from hydrocarbon reservoir production project. In an aspect, there is provide a system and method for utilizing data collected from 4D seismic studies in order to train an artificial neural network to recognize how physical properties of a hydrocarbon reservoir change over time, as the hydrocarbon reservoir is produced. In an embodiment, the system and method are adapted to generate and obtain a plurality of image slices or image planes derived from a 3D seismic baseline and at least one monitor acquired over the course production of the hydrocarbon reservoir. Corresponding 2D image slices derived from the 3D seismic baseline and a subsequent monitor are correlated and matched and are then used to train an artificial neural network to create a predictive model of how the reservoir may change over time.
1. A method of analyzing reservoir changes during production to increase reservoir production efficiency, comprising:
obtaining a seismic baseline of a reservoir prior to the production;
acquiring at least one seismic monitor of the reservoir after the production has started;
aligning the at least one seismic monitor with the seismic baseline to correlate one or more geological features of the reservoir;
generating a 3D seismic volume of differences by subtracting the seismic baseline from the aligned at least one seismic monitor;
utilizing a sliding window to generate a plurality of 2D image slices from the 3D seismic volume of differences and a mask;
training an artificial neural network utilizing the plurality of 2D image slices to generate a prediction model that predicts the reservoir changes during the production of the reservoir based on the seismic baseline and observed differences;
using the prediction model generated by the artificial neural network to generate actionable data to increase the reservoir production efficiency; and
using the actionable data to alter production methods in order to increase the reservoir production efficiency.
2. The method of claim 1 , wherein:
the seismic baseline is obtained by initiating and recording acoustic waves reflected by the one or more geological features of the reservoir prior to the production.
3. The method of claim 1 , wherein:
the at least one seismic monitor is obtained by periodically initiating and recording acoustic waves reflected by the one or more geological features of the reservoir as the one or more geological features change during the production.
4. The method of claim 3 , wherein:
the plurality of 2D image slices represent image planes derived from the 3D seismic volume of differences generated for the aligned at least one seismic monitor.
5. The method of claim 1 , wherein:
the mask is generated by applying a threshold to identify the one or more geological features of the reservoir.
6. The method of claim 5 , wherein:
the one or more geological features of the reservoir are a steam chamber or a heated zone.
7. The method of claim 1 , wherein:
the at least one seismic monitor is acquired over a duration of a 4D seismic study.
8. The method of claim 7 , wherein: the prediction model generated by the artificial neural network is configured to predict a location of a steam chamber or a heated zone during the production.
9. The method of claim 8 , wherein: the prediction model generated by the artificial neural network is further trained from data obtained from the 4D seismic study in order to improve the prediction model for subsequent predictions.
10. The method of claim 9 , further comprising:
training the artificial neural network utilizing a plurality of 4D seismic studies from a plurality of reservoirs.
11. The method of claim 1 , wherein: the prediction model generated by the artificial neural network is used to generate the actionable data that is used to alter the production methods in order to increase the reservoir production efficiency for the reservoir corresponding to the seismic baseline and the least one seismic monitor.
12. The method of claim 1 , wherein: the prediction model generated by the artificial neural network is used to generate the actionable data that is used to alter the production methods in order to increase the reservoir production efficiency for a new reservoir different than the reservoir corresponding to the seismic baseline and the least one seismic monitor.
13. The method of claim 12 , wherein:
the prediction model generated by the artificial neural network is further trained from data obtained from a 4D seismic study of the new reservoir.
14. A system for analyzing reservoir changes during production to increase reservoir production efficiency, the system adapted to:
obtain a seismic baseline of a reservoir prior to the production;
acquire at least one seismic monitor of the reservoir after the production has started;
align the at least one seismic monitor with the seismic baseline to correlate one or more geological features of the reservoir;
generate a 3D seismic volume of differences by subtracting the seismic baseline from the aligned at least one seismic monitor;
utilize a sliding window to generate a plurality of 2D image slices from the 3D seismic volume of differences and a mask;
train an artificial neural network utilizing the plurality of 2D image slices to generate a prediction model that predicts the reservoir changes during the production of the reservoir based on the seismic baseline and observed differences;
use the prediction model generated by the artificial neural network to generate actionable data to increase the reservoir production efficiency; and
use the actionable data to alter production methods in order to increase the reservoir production efficiency.
15. The system of claim 14 , wherein:
the seismic baseline is obtained by initiating and recording acoustic waves reflected by the one or more geological features of the reservoir prior to the production.
16. The system of claim 14 , wherein:
the at least one seismic monitor is obtained by periodically initiating and recording acoustic waves reflected by the one or more geological features of the reservoir as the one or more geological features change during the production.
17. The system of claim 16 , wherein:
the plurality of 2D image slices represent image planes derived from the 3D seismic volume of differences generated for the aligned at least one seismic monitor.
18. The system of claim 14 , wherein:
the mask is generated by applying a threshold to identify the one or more geological features of the reservoir.
19. The system of claim 18 , wherein:
the one or more geological features of the reservoir are a steam chamber or a heated zone.
20. The system of claim 14 , wherein:
the at least one seismic monitor is acquired over a duration of a 4D seismic study.
21. The system of claim 14 , wherein: the prediction model generated by the artificial neural network is configured to predict a location of a steam chamber or a heated zone during the production.
22. The system of claim 21 , wherein:
the prediction model generated by the artificial neural network is further trained from data obtained from a 4D seismic study in order to improve the prediction model for subsequent predictions.
23. The system of claim 22 , wherein:
the prediction model generated by the artificial neural network is trained utilizing a plurality of 4D seismic studies from a plurality of reservoirs.