System and method for classifying seismic data by integrating petrophysical data
A computer-implemented method is described for seismic facies identification including receiving a seismic dataset representative of a subsurface volume of interest; applying a model conditioned by petrophysical classifications to the seismic dataset to identify seismic facies and generate a classified seismic image; and identifying geologic features based on the classified seismic image. The method generates seismic facies probability volumes.
1. A computer-implemented method to predict heterogeneous shale properties and distribution from seismic data, comprising:
a. obtaining, at a computer processor, a seismic dataset representative of a subsurface volume of interest;
b. obtaining, at the computer processor, a model conditioned by petrophysical classifications;
c. applying the model conditioned by petrophysical classifications to the seismic dataset to identify seismic facies and generate a classified seismic image; and
d. identifying geologic features based on the classified seismic image.
2. The computer-implemented method of claim 1 wherein the applying the model conditioned by petrophysical classifications comprises:
a. obtaining regional petrophysical trends;
b. obtaining local petrophysical data;
c. comparing the local petrophysical data to the regional petrophysical trends to identify local deviations;
d. generating local petrophysical classifications using the local deviations to classify shale facies; and
e. extracting a seismic volume around the local petrophysical data and generating seismic facies probability volumes using supervised machine learning.
3. The method of claim 1 further comprising generating probability cubes for lithologies in the classified seismic image, wherein the lithologies include at least two of sand, soft shale, and hard shale.
4. The method of claim 2 wherein the supervised machine learning is using random forest to classify the seismic facies probability volumes.
5. The method of claim 3 wherein the probability cubes are co-rendered with the seismic volume to visualize the seismic facies with structural elements in the seismic volume.
6. A computer system, comprising:
one or more processors;
memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions that when executed by the one or more processors cause the device to:
a. receive, at the one or more processors, a seismic dataset representative of a subsurface volume of interest;
b. receive, at the one or more processors, a model conditioned by petrophysical classifications;
c. apply the model conditioned by petrophysical classifications to the seismic dataset to identify seismic facies and generate a classified seismic image; and
d. identify geologic features based on the classified seismic image.
7. The system of claim 6 wherein applying the model conditioned by petrophysical classifications comprises:
a. obtaining regional petrophysical trends;
b. obtaining local petrophysical data;
c. comparing the local petrophysical data to the regional petrophysical trends to identify local deviations;
d. generating local petrophysical classifications using the local deviations to classify shale facies; and
e. extracting a seismic volume around the local petrophysical data and generating seismic facies probability volumes using supervised machine learning.
8. The system of claim 6 further comprising generating probability cubes for lithologies in the classified seismic image, wherein the lithologies include at least two of sand, soft shale, and hard shale.
9. The system of claim 7 wherein the supervised machine learning is using random forest to classify the seismic facies probability volumes.
10. The system of claim 8 wherein the probability cubes are co-rendered with the seismic volume to visualize the seismic facies with structural elements in the seismic volume.
11. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device with one or more processors and memory, cause the device to:
a. receive, at one or more processors, a seismic dataset representative of a subsurface volume of interest;
b. receive, at the one or more processors, a model conditioned by petrophysical classifications;
c. apply the model conditioned by petrophysical classifications to the seismic dataset to identify seismicfacies and generate a classified seismic image; and
d. identify geologic features based on the classified seismic image.
12. The non-transitory computer readable storage medium of claim 11 wherein applying the model conditioned by petrophysical classifications comprises:
a. obtaining regional petrophysical trends;
b. obtaining local petrophysical data;
c. comparing the local petrophysical data to the regional petrophysical trends to identify local deviations;
d. generating local petrophysical classifications using the local deviations to classify shale facies; and
e. extracting a seismic volume around the local petrophysical data and generating seismic facies probability volumes using supervised machine learning.
13. The non-transitory computer readable storage medium of claim 11 wherein the instructions further cause the device to generate probability cubes for lithologies in the classified seismic image, wherein the lithologies include at least two of sand, soft shale, and hard shale.
14. The non-transitory computer readable storage medium of claim 12 wherein the supervised machine learning is using random forest to classify the seismic facies probability volumes.
15. The non-transitory computer readable storage medium of claim 13 wherein the instructions further cause the device to co-render the probability cubes with the seismic volume to visualize the seismic facies with structural elements in the seismic volume.