Methods and systems for reference-based inversion of seismic image volumes
Accordingly, there are disclosed herein geologic modeling methods and systems employing reference-based inversion of seismic image volumes. An illustrative method embodiment includes: (a) obtaining a measured seismic image volume; (b) determining a reference seismic image volume based on a reference model; (c) deriving a synthesized seismic image volume from a geologic model; (d) detecting at least one geologic model region where the synthesized seismic image volume and the measured seismic image volume are mismatched; (e) finding a reference model region where the reference seismic image volume best matches the measured seismic image volume; (f) replacing content of the at least one geologic model region with content of the reference model region to obtain an improved geologic model; and (g) outputting the improved geologic model.
1. A geologic modeling method that comprises:
obtaining a measured seismic image volume for a subsurface region of interest;
determining a reference seismic image volume based on a reference model, wherein the reference model comprises a geologic model for another subsurface region that is similar to the subsurface region of interest;
deriving a synthesized seismic image volume from a geologic model for the subsurface region of interest;
creating a locality sensitive hashing (LSH) database using windowed regions of the synthesized seismic image volume;
detecting at least one geologic model region within the geologic model for the subsurface region of interest where the synthesized seismic image volume and the measured seismic image volume are mismatched by comparing the windowed regions of the synthesized seismic image volume with windowed regions of the measured seismic image volume;
finding a reference model region within the reference model where the reference seismic image volume best matches the measured seismic image volume by calculating a target LSH value from a windowed region of the measured seismic image volume and performing an approximate nearest-neighbor search of the LSH database;
replacing content of the at least one geologic model region within the geologic model for the subsurface region of interest with content of the reference model region from the reference model to obtain an improved geologic model for the subsurface region of interest; and
outputting the improved geologic model.
2. The method of claim 1 , further comprising:
constructing the reference model by systematically varying internal structure of regions in the reference model.
3. The method of claim 1 , further comprising:
creating an auto-encoding using windowed regions of the synthesized seismic image volume.
4. The method of claim 1 , further comprising, before said outputting:
deriving an improved seismic image volume from the improved geologic model; and
verifying that the improved seismic image volume matches the measured seismic image volume.
5. The method of claim 1 , wherein the said outputting includes:
storing the improved geologic model on a non-transitory information storage device; and
displaying a visual representation of the improved geologic model.
6. The method of claim 1 , further comprising: using the improved geologic model to evaluate one or more well placement and production strategies.
7. The method of claim 1 , further comprising using the improved geologic model to determine where to drill one or more wells and causing one or more wells to be drilled.
8. A geologic modeling system that comprises:
a memory having geologic modeling software; and
one or more processors coupled to the memory to execute the geologic modeling software, the software causing the one or more processors to perform operations including:
obtaining a measured seismic image volume for a subsurface region of interest;
determining a reference seismic image volume based on a reference model, wherein the reference model comprises a geologic model for another subsurface region that is similar to the subsurface region of interest;
deriving a synthesized seismic image volume from a geologic model for the subsurface region of interest;
creating a locality sensitive hashing (LSH) database using windowed regions of the synthesized seismic image volume;
detecting at least one geologic model region within the geologic model for the subsurface region of interest where the synthesized seismic image volume and the measured seismic image volume are mismatched by comparing the windowed regions of the synthesized seismic image volume with windowed regions of the measured seismic image volume;
finding a reference model region within the reference model where the reference seismic image volume best matches the measured seismic image volume by calculating a target LSH value from a windowed region of the measured seismic image volume and performing an approximate nearest-neighbor search of the LSH database;
replacing content of the at least one geologic model region within the geologic model for the subsurface region of interest with content of the reference model region from the reference model to obtain an improved geologic model for the subsurface region of interest; and
storing the improved geologic model on a non-transitory information storage device.
9. The system of claim 8 , wherein the operations further include:
using the improved geologic model to evaluate one or more well placement and production strategies.
10. The system of claim 8 , further comprising:
creating an auto-encoding using windowed regions of the synthesized seismic image volume.
11. The system of claim 8 , wherein the operations further include, before said outputting:
deriving an improved seismic image volume from the improved geologic model; and
verifying that the improved seismic image volume matches the measured seismic image volume.
12. A non-transitory information storage product having computer readable program code embodied therein, which when executed implements a geological modeling method that comprises:
obtaining a measured seismic image volume for a subsurface region of interest;
determining a reference seismic image volume based on a reference model, wherein the reference model comprises a geologic model for another subsurface region that is similar to the subsurface region of interest;
deriving a synthesized seismic image volume from a geologic model for the subsurface region of interest;
creating a locality sensitive hashing (LSH) database using windowed regions of the synthesized seismic image volume;
detecting at least one geologic model region within the geologic model for the subsurface region of interest where the synthesized seismic image volume and the measured seismic image volume are mismatched by comparing the windowed regions of the synthesized seismic image volume with windowed regions of the measured seismic image volume;
finding a reference model region within the reference model where the reference seismic image volume best matches the measured seismic image volume by calculating a target LSH value from a windowed region of the measured seismic image volume and performing an approximate nearest-neighbor search of the LSH database;
replacing content of the at least one geologic model region within the geologic model for the subsurface region of interest with content of the reference model region from the reference model to obtain an improved geologic model for the subsurface region of interest; and
outputting the improved geologic model.
13. The product of claim 12 , wherein said outputting includes:
storing the improved geologic model on a non-transitory information storage device; and
displaying a visual representation of the improved geologic model.
14. The product of claim 12 , further comprising:
using the improved geologic model to evaluate one or more well placement and production strategies.