Automated Seismic Interpretation Guided Inversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current seismic analysis methods are inefficient and inaccurate due to non-uniqueness in geophysical inversion, lack of convexity in objective functions, and computational costs, leading to subjective and time-consuming processes that often produce models not consistent with observed data.
Innovation Solution
Implementing Automated Seismic Interpretation (ASI) guided inversion methods that use deep neural networks and shape-constrained inversion to iteratively update geophysical models based on seismic interpretation, incorporating geologic features and reducing non-uniqueness by constraining inversion with geobody shapes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Full Wavefield Inversion (FWI) is performed with naive parameterization using uniform discretization, then the inversion attempts to match simulated data to observed seismic data, but the computational cost becomes extremely high and the process requires many volume elements to achieve adequate resolution
Solution Approach 1:
The patent segments the subsurface model into geobodies with distinct geological characteristics rather than using uniform discretization. This segmentation allows the inversion to focus computational resources on geologically relevant features, reducing the number of volume elements needed while maintaining inversion accuracy.
Solution Approach 2:
The patent applies local quality by using different parameterizations for different geological features. Instead of uniform discretization, the model uses shape-constrained parameterization for geobodies and background parameterization for surrounding areas, allowing each region to be modeled with appropriate detail level based on its geological significance.
2Ease of manufacture
If sequential seismic analysis is performed with separate inversion and interpretation stages, then the process follows conventional workflow, but the models produced are not consistent with observed data and the process is time-consuming with no guarantee of convergence
Solution Approach 1:
The patent merges the inversion and interpretation stages into a unified iterative process. The ASI-guided inversion continuously integrates interpretation feedback during the inversion process, ensuring that the final model is consistent with both observed seismic data and geological interpretation, eliminating the inconsistency problem of sequential approaches.
Solution Approach 2:
The patent implements feedback by using Automated Seismic Interpretation to provide continuous guidance during the inversion process. The interpretation results feed back into the inversion to constrain the model, creating an iterative loop that ensures convergence to a geologically reasonable and data-consistent solution.
3Productivity
If inversion is performed without geological constraints, then the mathematical inversion can be completed, but the results suffer from non-uniqueness and may not represent geologically reasonable models
Solution Approach 1:
The patent performs preliminary action by conducting Automated Seismic Interpretation before the inversion to identify geobodies and their characteristics. This preliminary interpretation provides geological constraints that guide the subsequent inversion process, ensuring that the inversion converges to geologically reasonable models while maintaining efficiency.
Solution Approach 2:
The patent changes the parameterization approach by introducing shape-constrained parameters for geobodies identified through ASI. This parameter change transforms the inversion from an unconstrained mathematical problem to a geologically-constrained problem, improving model accuracy without significantly increasing computational cost.
Data Source
AI summary
A method and apparatus for seismic analysis include obtaining an initial geophysical model and seismic data for a subsurface region; producing a subsurface image of the subsurface region with the seismic data and the geophysical model; generating a map of one or more geologic features of the subsurface region by automatically interpreting the subsurface image; and iteratively updating the geophysical model, subsurface image, and map of geologic features by: building an updated geophysical model based on the geophysical model of a prior iteration constrained by one or more geologic features from the prior iteration; imaging the seismic data with the updated geophysical model to produce an updated subsurface image; and automatically interpreting the updated subsurface image to generate an updated map of geologic features. The method and apparatus may also include post-stack migration, pre-stack time migration, pre-stack depth migration, reverse-time migration, gradient-based tomography, and/or gradient-based inversion methods.