Fault Skeletonization for Subterranean Fault Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for imaging faults in seismic data generate blurry faults, and deep learning approaches lack the ability to predict structural dip and strike angles, making it difficult to thin fault likelihood data effectively.
Innovation Solution
The method involves fault skeletonization, where fault likelihood data is converted to binary distribution data using a binary mask filter, and then thinned without requiring dip and strike angle data, forming thinned fault identification data that can be converted back to seismic volume data for clearer fault representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional deterministic approaches are used to image faults in seismic data, then fault identification is achieved, but the faults appear blurry and lack precision
Solution Approach 1:
The patent extracts only the essential fault-related information from the binary distribution data by applying skeletonization algorithms that reduce fault zones to their central skeletal structures. This extraction process removes redundant blurred information while preserving the essential fault geometry and location, thereby improving both measurement precision and image sharpness without requiring dip and strike angle data.
2Productivity
If deep learning approaches are used to predict faults, then processing speed is improved, but the ability to predict dip and strike angles is lost, making thinning difficult
Solution Approach 1:
The patent implements a self-service approach where the skeletonization algorithm automatically processes the binary distribution data generated by deep learning models without requiring additional dip and strike angle inputs. The algorithm independently identifies and thins fault structures by analyzing pixel connectivity patterns, enabling deep learning models to maintain their speed advantage while still producing thinned fault outputs through self-sufficient processing.
3Manufacturing precision
If thinning algorithms are applied to fault likelihood data using dip and strike angle data, then fault sharpness is improved, but significant time and compute power are required
Solution Approach 1:
The patent employs computationally inexpensive skeletonization algorithms that process binary distribution data using simple pixel connectivity rules rather than complex dip and strike angle calculations. This approach uses lightweight, disposable processing methods that achieve fault thinning with minimal computational resources and time, sacrificing the sophistication of traditional methods for efficiency and speed.
Data Source
AI summary
A system can receive fault likelihood data about a subterranean environment and apply a binary mask filter using a tuning parameter to convert the fault likelihood data to binary distribution data having a plurality of pixels arranged in a plurality of profiles in at least two directions. The system can perform, for each profile of the plurality of profiles, fault skeletonization on the binary distribution data to form fault skeletonization data with pixels connected that represent part of a fracture. The system can convert the fault skeletonization data to seismic volume data and combine and filter the seismic volume data in the at least two directions to form combined seismic volume data. The system can output the combined seismic volume data as an image for use in detecting objects to plan a wellbore operation.