Dynamic reservoir characterization
A method of operating a reservoir simulator can include performing a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that includes a reservoir to generate simulation results for a first time where the simulation results include a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model; predicting a position of the front for a subsequent time step for a corresponding second time using a trained machine model; discretizing the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and performing a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.
1. A method of operating a reservoir simulator comprising:
performing a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that comprises a reservoir to generate simulation results for a first time wherein the simulation results comprise a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model;
predicting a position of the front for a subsequent time step for a corresponding second time using a trained machine model;
discretizing the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and
performing a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.
2. The method of claim 1 comprising training a machine model to generate the trained machine model.
3. The method of claim 2 comprising generating training data via operation of the reservoir simulator.
4. The method of claim 3 wherein the generating comprises utilizing a spatial reservoir model that comprises a fine resolution and wherein the performing a time step of a reservoir simulation using a spatial reservoir model utilizes a coarser resolution spatial reservoir model.
5. The method of claim 1 wherein the discretizing comprises kD-tree discretization.
6. The method of claim 1 wherein the front comprises water.
7. The method of claim 1 wherein the front comprises surfactant.
8. The method of claim 1 wherein the front comprises gas.
9. The method of claim 1 wherein the front comprises an enhanced oil recovery (EOR) front.
10. The method of claim 1 wherein the front is defined by a salinity gradient.
11. The method of claim 1 comprising controlling a field operation of an enhanced oil recovery process using the generated simulation results for the second time.
12. The method of claim 1 wherein the reservoir simulator comprises at least one processor and memory accessible to at least one of the at least one processor.
13. A system comprising:
a processor;
memory operatively coupled to the processor; and
processor-executable instructions stored in the memory to instruct the system, the instructions comprising instructions to:
perform a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that comprises a reservoir to generate simulation results for a first time wherein the simulation results comprise a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model;
predict a position of the front for a subsequent time step for a corresponding second time using a trained machine model;
discretize the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and
perform a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.
14. The system of claim 13 wherein the instructions comprise instructions to train a machine model to generate the trained machine model.
15. The system of claim 14 wherein the instructions comprise instructions to generate training data via operation of the reservoir simulator.
16. The system of claim 13 wherein the instructions to discretize utilize kD-tree discretization.
17. One or more non-transitory computer-readable storage media comprising computer-executable instructions to instruct a computer, the instructions comprising instructions to:
perform a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that comprises a reservoir to generate simulation results for a first time wherein the simulation results comprise a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model;
predict a position of the front for a subsequent time step for a corresponding second time using a trained machine model;
discretize the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and
perform a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.
18. The one or more non-transitory computer-readable storage media of claim 17 wherein the instructions comprise instructions to train a machine model to generate the trained machine model.
19. The one or more non-transitory computer-readable storage media of claim 18 wherein the instructions comprise instructions to generate training data via operation of the reservoir simulator.
20. The one or more non-transitory computer-readable storage media of claim 17 wherein the instructions to discretize utilize kD-tree discretization.