METHOD AND SYSTEM FOR GENERALIZABLE DEEP LEARNING FRAMEWORK FOR SEISMIC VELOCITY ESTIMATION ROBUST TO SURVEY CONFIGURATION

1 . A method, comprising:

obtaining an initial velocity model;

perturbing the initial velocity model to form a first plurality of velocity models;

using a forward model to simulate a first plurality of seismic data sets from the first plurality of velocity models;

transforming the first plurality of seismic data sets to a wavenumber-time domain to form a first plurality of transformed seismic data sets;

training a machine-learned model using the first plurality of velocity models and the first plurality of transformed seismic data sets, wherein the machine-learned model is configured to accept transformed seismic data sets;

obtaining a second seismic data set for a subsurface region of interest, wherein the second seismic data set is acquired according to a second survey configuration;

transforming the second seismic data set to the wavenumber-time domain to form a second transformed seismic data set; and

processing the second transformed data set with the trained machine-learned model to predict a second velocity model for the subsurface region of interest.

2 . The method of claim 1 ,

wherein transforming the first plurality of seismic data sets and transforming the second seismic data set further comprises:

sorting the data to a common middle point; and

applying a Fourier transform to the sorted data.

3 . The method of claim 1 ,

wherein the machine-learned model comprises a long-short-term-memory network.

4 . The method of claim 1 , further comprising:

constructing a subsurface model for the subsurface region of interest based, at least in part, on the second velocity model, wherein the subsurface model informs oil and gas field planning and lifecycle management decisions.

5 . The method of claim 1 , further comprising:

obtaining a seismic data database of various data types;

selecting a third seismic data set from the seismic data database according to a data type; and

processing the third seismic data set with a benchmark model to determine the initial velocity model.

6 . The method of claim 1 ,

wherein the forward model is configured according to a first survey configuration which is non-identical to the second survey configuration.

7 . The method of claim 1 ,

wherein the initial velocity model is perturbed according to a prior knowledge and a plurality of perturbation parameters, wherein the prior knowledge comprises:

petrophysical information about the subsurface region of interest.

8 . A non-transitory computer readable medium storing instructions executable by a compute processor, the instructions comprising functionality for:

obtaining an initial velocity model;

perturbing the initial velocity model to form a first plurality of velocity models;

using a forward model to simulate a first plurality of seismic data sets from the first plurality of velocity models;

transforming the first plurality of seismic data sets to a wavenumber-time domain to form a first plurality of transformed seismic data sets;

training a machine-learned model using the first plurality of velocity models and the first plurality of transformed seismic data sets, wherein the machine-learned model is configured to accept transformed seismic data;

obtaining a second seismic data set for a subsurface region of interest, wherein the second seismic data set is acquired according to a second survey configuration;

transforming the second seismic data set to the wavenumber-time domain to form a second transformed seismic data set; and

processing the second transformed data set with the trained machine-learned model to predict a second velocity model for the subsurface region of interest.

9 . The non-transitory computer readable medium of claim 8 ,

wherein transforming the first plurality of seismic data sets and transforming the second seismic data set further comprises:

sorting the data to a common middle point; and

applying a Fourier transform to the sorted data.

10 . The non-transitory computer readable medium of claim 8 ,

wherein the machine-learned model comprises a long-short-term-memory network.

11 . The non-transitory computer readable medium of claim 8 , further comprising instructions for:

constructing a subsurface model for the subsurface region of interest based, at least in part, on the second velocity model, wherein the subsurface model informs oil and gas field planning and lifecycle management decisions.

12 . The non-transitory computer readable medium of claim 8 , further comprising instructions for:

obtaining a seismic data database of various data types;

selecting a third seismic data set from the seismic data database according to a data type; and

processing the third seismic data set with a benchmark model to determine the initial velocity model.

13 . The non-transitory computer readable medium of claim 8 ,

wherein the forward model is configured according to a first survey configuration which is non-identical to the second survey configuration.

14 . The non-transitory computer readable medium of claim 8 ,

wherein the initial velocity model is perturbed according to a prior knowledge and a plurality of perturbation parameters, wherein the prior knowledge comprises:

petrophysical information about the subsurface region of interest.

15 . A system, comprising:

an initial velocity model;

a forward modelling procedure;

a machine-learned model;

a second seismic data set for a subsurface region of interest, wherein the second seismic data set is acquired according to a second survey configuration; and

a computer comprising:

one or more computer processors, and

a non-transitory computer readable medium storing instructions executable by a computer processor, the instructions comprising functionality for:

perturbing the initial velocity model to form a first plurality of velocity models;

using the forward modelling procedure to simulate a first plurality of seismic data sets from the first plurality of velocity models;

transforming the first plurality of seismic data sets to a wavenumber-time domain to form a first plurality of transformed seismic data sets;

training the machine-learned model using the first plurality of velocity models and the first plurality of transformed seismic data sets, wherein the machine-learned model is configured to accept transformed seismic data;

transforming the second seismic data set to the wavenumber-time domain to form a second transformed seismic data set; and

processing the second transformed data set with the trained machine-learned model to predict a second velocity model for the subsurface region of interest.

16 . The system of claim 15 ,

wherein transforming the first plurality of seismic data sets and transforming the second seismic data set further comprises:

sorting the data to a common middle point; and

applying a Fourier transform to the sorted data.

17 . The system of claim 15 ,

wherein the machine-learned model comprises a long-short-term-memory network.

18 . The system of claim 15 , the instructions further comprising functionality for:

constructing a subsurface model for the subsurface region of interest based, at least in part, on the second velocity model, wherein the subsurface model informs oil and gas field planning and lifecycle management decisions.

19 . The system of claim 15 , further comprising:

a seismic data database of various data types; and

a third seismic data set selected from the seismic data database according to a data type;

wherein, the initial velocity model is determined by processing the third seismic data set with a benchmark model.

20 . The system of claim 15 ,

wherein the initial velocity model is perturbed according to a prior knowledge and a plurality of perturbation parameters, wherein the prior knowledge comprises:

petrophysical information about the subsurface region of interest.