Method and system for augmented inversion and uncertainty quantification for characterizing geophysical bodies

Patent metadata

Field	Value
Publication number	US-2023032044-A1
Application number	US-202217806627-A
Country	US
Kind code	A1
Filing date	Jun 13, 2022
Priority date	Jul 13, 2021
Publication date	Feb 2, 2023
Grant date	—

Abstract

A computer-implemented method for augmented inversion and uncertainty quantification for characterizing geophysical bodies is disclosed. The method includes machine-learning-augmented inversion that also facilitates the characterization of uncertainties in geophysical bodies. The method may further estimate wavelets without a well-log calibration, thereby enabling a pre-discovery exploration phase when well log data is unavailable. The machine learning component incorporates a priori knowledge about the subsurface and physics, such as distributions of expected rock types and rock properties, geological structures, and wavelets, through learning from examples. The methodology also allows for conditioning the characterization with the information extracted a priori about the geobodies, such as probabilities of rock types, using other analysis tools. Thus, the conditioning strategy may make the inversion more robust even when a priori distributions are not well balanced. Using the method, a scenario testing workflow may evaluate different candidate subsurface models, facilitating the management of uncertainty in decision-making processes.

First claim

What is claimed is:

1 . A computer-implemented method of performing geophysical inversion comprising:
accessing measured data for a subsurface region; accessing prior subsurface data; solving an inversion problem using the measured data and the prior subsurface data tailored in at least one aspect to rock types, facies, or fluid types in order to generate an inversion solution tailored in the at least one aspect to the rock types, the facies or the fluid types; and using the inversion solution tailored in the at least one aspect to the rock types, the facies or the fluid types for hydrocarbon management.

2 . The method of claim 1 , wherein solving the inversion problem tailored in the at least one aspect to the rock types, the facies, or the fluid types comprises conditioning inversion based on scenarios of the rock types, the facies, or the fluid types.

3 . The method of claim 2 , wherein the conditioning of the inversion is based on the scenarios of at least one of the rock types, the facies, or the fluid types obtained from seismic processing tools independent from priors based on knowledge bases and upstream to the inversion.

4 . The method of claim 1 , wherein solving the inversion problem tailored in the at least one aspect to at least one of the rock types, the facies or the fluid types comprises generating a function (f) that maps from latent space Z into parameter space of subsurface properties tailored to the rock types, the facies, or the fluid types.

5 . The method of claim 1 , wherein the inversion problem solved comprises at least one of: velocity model building; wave-equation-based velocity analysis; tomography; full-wavefield inversion (FWI); least-squares migration; electromagnetic (EM) inversion; petrophysical inversion; or amplitude-versus-offset (AVO) inversion.

6 . The method of claim 1 , wherein the prior subsurface data comprises rock types scenarios or facies scenarios;
further comprising forming an augmented forward model based on machine-learning with the rock types scenarios or the facies scenarios; and wherein solving the inversion problem is augmented based on machine-learned augmented forward model for the rock types or the facies scenarios.

7 . A computer-implemented method of machine learning-augmented geophysical inversion comprising:
accessing measured data for a subsurface region; accessing prior subsurface data; accessing conditioning data; forming an augmented forward model based on:
a machine-learning model representing the prior subsurface data conditioned with the conditioning data, and
a physics model mapping output of the machine-learning model to seismic data;
initializing a plausible model by sampling latent space of a priori network model; solving, using the plausible model, an inverse problem described by the augmented forward model to find one or more solutions which are consistent with the seismic data, the prior subsurface data and the conditioning data; and using the one or more solutions for hydrocarbon management.

8 . The method of claim 7 , wherein a distribution of latent space vectors is based on a normal distribution during the inversion, such that solving the inversion problem traverses within a subspace of high-resolution plausible subsurface models with augmentation from the a priori network model.

9 . The method of claim 7 , wherein solving the inversion problem based on multiple scenarios generates multiple solutions; and
wherein the machine-learning model evaluates the multiple solutions in order to rank the multiple scenarios.

10 . The method of claim 7 , wherein an augmented inversion method is combined with a nullspace search algorithm to find equally-likely or almost equally-likely solutions connected to the one or more solutions.

11 . The method of claim 10 , wherein the nullspace search algorithm is one of the following methods: Hamiltonian nullspace shuttles; or Hamiltonian Monte Carlo.

12 . A computer-implemented method of machine learning-augmented geophysical inversion comprising:
obtaining measured data for a subsurface region; obtaining prior subsurface data; forming an augmented forward model based on machine-learning with the prior subsurface data conditional on scenarios of at least one of geologic systems, rock types, facies, or fluid types; solving an inversion problem using the augmented forward model in order to generate multiple scenario solutions; testing at least one of the multiple scenario solutions; and using the at least one of the multiple scenario solutions for hydrocarbon management.

13 . The method of claim 12 , wherein testing the at least one of the multiple scenario solutions comprises using the augmented forward model in order to evaluate the multiple scenario solutions.

14 . The method of claim 12 , wherein testing the at least one of the multiple scenario solutions comprises evaluating a loss function using the measured data for a subsurface region.

15 . The method of claim 12 , wherein the at least one of the multiple scenario solutions comprises a model; and
further comprising:
creating a map of categorical labels or probabilities of scenarios for each pixel or element in the model; and
creating, by the augmented forward model, examples that match the labels.

16 . The method of claim 12 , wherein the multiple scenario solutions are engineered for uncertainty quantification.

17 . The method of claim 12 , wherein testing comprises generating a respective probability for each of the multiple scenario solutions.

18 . The method of claim 12 , wherein uncertainty of the multiple scenario solutions at each spatial location is evaluated by optimization.

19 . The method of claim 12 , wherein uncertainty of the at least one of the multiple scenario solutions is evaluated by latent space projection and interpolation.

20 . The method of claim 12 , wherein uncertainty of the at least one of the multiple scenario solutions is evaluated by extreme bounds analysis.

21 . A computer-implemented method of machine learning-augmented geophysical inversion comprising:
obtaining measured data for a subsurface region; obtaining prior subsurface data; forming an augmented forward model based on machine-learning with the prior subsurface data conditional on scenarios of at least one of geologic systems, rock types or facies; solving an augmented Hamiltonian null-space exploration problem to find multiple equally plausible solutions; and using the at least one of the multiple equally plausible solutions for hydrocarbon management.

22 . A computer-implemented method for simultaneously estimating wavelets and geophysical or petrophysical properties, the method comprising:
obtaining measured data for a subsurface region; estimating initial wavelets; estimating, based on the measure data, initial geophysical or petrophysical properties; solving an inversion problem by simultaneously updating the initial wavelets and the initial geophysical or petrophysical properties; and using the solved inversion problem for hydrocarbon management.

23 . The method of claim 22 , wherein the initial wavelets are estimated based on statistical wavelet estimations, elastic FWI results, or transferred from overlapping or nearby seismic surveys with well ties.

24 . The method of claim 23 , wherein the initial wavelets comprise a distribution of wavelets as a prior to infer wavelets during the

Assignees

• Exxonmobil Upstream Res Co

Inventors

• Li Dongzhuo
• Denli Huseyin
• Macdonald Cody
• Basler-Reeder Kyle J

Classifications

• G01V3/38

  Processing data, e.g. for analysis, for interpretation, for correction · CPC title

• G01V1/303

  for determining velocity profiles or travel times · CPC title

• G01V2210/614

  Synthetically generated data · CPC title

• G01V1/282 Primary

  Application of seismic models, synthetic seismograms · CPC title

• G01V2210/1234

  Hydrocarbon reservoir, e.g. spontaneous or induced fracturing · CPC title