Mitigation of fiber optic cable coupling for distributed acoustic sensing
The disclosed technology provides solutions for identifying noise in seismic profile data sets. In some aspects, a process of the disclosed technology includes steps for receiving wellbore data including seismic measurements, processing the wellbore data to generate a seismic input image including visual representations of the one or more seismic measurements, and processing the seismic input image to identify a noise region in the seismic input image. Systems and machine-readable media are also provided.
1. A computer-implemented method, comprising:
receiving wellbore data comprising one or more seismic measurements;
generating a seismic input image based on the one or more seismic measurements;
processing the seismic input image to identify zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more seismic measurements;
applying a noise reduction technique to eliminate the zigzag noise in the seismic input image; and
analyzing the seismic input image to determine formation properties.
2. The computer-implemented method of claim 1 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise in the seismic input image using a bounded polygon.
3. The computer-implemented method of claim 1 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise using time and wellbore depth coordinates.
4. The computer-implemented method of claim 1 , wherein the seismic input image represents a spatial relationship between wellbore depth, and time, with respect to the one or more seismic measurements.
5. The computer-implemented method of claim 1 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a convolutional neural network.
6. The computer-implemented method of claim 1 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a deep-learning network.
7. The computer-implemented method of claim 1 , wherein the wellbore data comprises optical data that is communicated up a wellbore using one or more fiber optic channels.
8. A system comprising:
one or more processors; and
a non-transitory computer-readable medium comprising instructions stored therein, which when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving wellbore data comprising one or more seismic measurements;
generating a seismic input image based on the one or more seismic measurements;
processing the seismic input image to identify zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more seismic measurements;
applying a noise reduction technique to eliminate the zigzag noise in the seismic input image; and
analyzing the seismic input image to determine formation properties.
9. The system of claim 8 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise in the seismic input image using a bounded polygon.
10. The system of claim 8 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise using time and wellbore depth coordinates.
11. The system of claim 8 , wherein the seismic input image represents a spatial relationship between wellbore depth, and time, with respect to the one or more seismic measurements.
12. The system of claim 8 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a convolutional neural network.
13. The system of claim 8 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a deep-learning network.
14. The system of claim 8 , wherein the wellbore data comprises optical data that is communicated up a wellbore using one or more fiber optic channels.
15. A non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving wellbore data comprising one or more seismic measurements;
generating a seismic input image based on the one or more seismic measurements;
processing the seismic input image to identify zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more seismic measurements;
applying a noise reduction technique to eliminate the zigzag noise in the seismic input image; and
analyzing the seismic input image to determine formation properties.
16. The non-transitory computer-readable storage medium of claim 15 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise in the seismic input image using a bounded polygon.
17. The non-transitory computer-readable storage medium of claim 15 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model is configured to identify the zigzag noise using time and wellbore depth coordinates.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the seismic input image represents a spatial relationship between wellbore depth, and time, with respect to the one or more seismic measurements.
19. The non-transitory computer-readable storage medium of claim 15 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a convolutional neural network.
20. The non-transitory computer-readable storage medium of claim 15 , wherein processing the seismic input image to identify the zigzag noise further comprises:
providing the seismic input image to a machine-learning model, and
wherein the machine-learning model comprises a deep-learning network.