Method and system for mapping fiber optic distributed acoustic sensing measurements to particle motion
A method for mapping fiber optic distributed acoustic sensing (DAS) measurements to particle motion involves obtaining, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave; obtaining, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave; generating training data from the first set of DAS data and the measured particle motion data; training a machine learning model using the training data; obtaining a second set of DAS data associated with a second seismic wave; and determining a predicted particle motion in response to the second seismic wave using the machine learning model applied to the second set of DAS data.
1. A method for mapping fiber optic distributed acoustic sensing (DAS) measurements to particle motion data, the method comprising:
obtaining, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave;
obtaining, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave, wherein the measured particle motion data comprises electrical signal measurements generated by the discrete seismic receiver;
generating training data from the first set of DAS data and the measured particle motion data;
training a machine learning model using the training data;
obtaining a second set of DAS data associated with a second seismic wave;
generating predicted particle motion data in response to the second seismic wave using the machine learning model applied to the second set of DAS data, wherein the predicted particle motion data is formatted as electrical signal measurements generated by the discrete seismic receiver; and
inputting the predicted particle motion data to a seismic inversion workflow to determine formation characteristics near the wellbore.
2. The method of claim 1 , wherein the machine learning model is a long short-term memory (LSTM) network.
3. The method of claim 2 , wherein the LSTM network comprises a bidirectional LSTM layer.
4. The method of claim 1 , wherein the measured particle motion is one selected from a group consisting of a velocity and an acceleration.
5. The method of claim 1 , wherein the first set of DAS data is for a plurality of DAS channels simultaneously recorded in spatial proximity to the discrete seismic receiver.
6. The method of claim 1 , wherein the discrete seismic receiver is a geophone.
7. The method of claim 1 , further comprising, prior to training the machine learning model:
temporally aligning the first set of DAS data and the particle motion data.
8. The method of claim 1 ,
wherein the first set of DAS data is obtained from a first set of DAS channels of the fiberoptic DAS system,
wherein the second set of DAS data is obtained from a second set of DAS channels of the fiberoptic DAS system, different from the first set of DAS channels.
9. A system for mapping fiber optic distributed acoustic sensing (DAS) measurements to particle motion data, the system comprising:
a seismic data processing system configured to:
obtain, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave;
obtain, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave, wherein the measured particle motion data comprises electrical signal measurements generated by the discrete seismic receiver;
generate training data from the first set of DAS data and the measured particle motion data;
train a machine learning model using the training data;
obtain a second set of DAS data associated with a second seismic wave;
generate predicted particle motion data in response to the second seismic wave using the machine learning model applied to the second set of DAS data, wherein the predicted particle motion data is formatted as electrical signal measurements generated by the discrete seismic receiver; and
input the predicted particle motion data to a seismic inversion workflow to determine formation characteristics near the wellbore.
10. The system of claim 9 , further comprising:
the fiber optic DAS system.
11. The system of claim 9 , further comprising:
the discrete seismic receiver.
12. The system of claim 9 , wherein the discrete seismic receiver is a geophone.
13. The system of claim 9 , wherein the machine learning model is a long short-term memory (LSTM) network.
14. The system of claim 13 , wherein the LSTM network comprises a bidirectional LSTM layer.
15. The system of claim 9 , wherein the measured particle motion is one selected from a group consisting of a velocity and an acceleration.
16. The system of claim 9 , wherein the first set of DAS data is for a plurality of DAS channels simultaneously recorded in spatial proximity to the discrete seismic receiver.
17. The system of claim 9 , wherein the seismic data processing system is further configured to, prior to training the machine learning model:
temporally align the first set of DAS data and the particle motion data.
18. The system of claim 9 ,
wherein the first set of DAS data is obtained from a first set of DAS channels of the fiberoptic DAS system,
wherein the second set of DAS data is obtained from a second set of DAS channels of the fiberoptic DAS system, different from the first set of DAS channels.
19. A non-transitory machine-readable medium comprising a plurality of machine-readable instructions executed by one or more processors, the plurality of machine-readable instructions causing the one or more processors to perform operations comprising:
obtaining, from a fiber optic distributed acoustic sensing (DAS) system in a wellbore, a first set of DAS data associated with a first seismic wave;
obtaining, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave, wherein the measured particle motion data comprises electrical signal measurements generated by the discrete seismic receiver;
generating training data from the first set of DAS data and the measured particle motion data;
training a machine learning model using the training data;
obtaining a second set of DAS data associated with a second seismic wave;
generating predicted particle motion data in response to the second seismic wave using the machine learning model applied to the second set of DAS data, wherein the predicted particle motion data is formatted as electrical signal measurements generated by the discrete seismic receiver; and
inputting the predicted particle motion data to a seismic inversion workflow to determine formation characteristics near the wellbore.
20. The non-transitory machine-readable medium of claim 19 ,
wherein the first set of DAS data is obtained from a first set of DAS channels of the fiberoptic DAS system,
wherein the second set of DAS data is obtained from a second set of DAS channels of the fiberoptic DAS system, different from the first set of DAS channels.