3D Mechanical Earth Modeling via Neural Network Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current three-dimensional mechanical earth modeling techniques face challenges in accurately characterizing rock properties with high lateral and vertical resolution, especially in fields with anisotropic rock properties, faults, and sparse wellbore information, leading to issues like rock failure, subsidence, and wellbore problems during oil or gas reservoir production.
Innovation Solution
A method that combines seismic and wellbore data to create a high-resolution 3-D mechanical earth model by correlating rock properties from seismic surveys with those from wellbore logging data, using neural networking to distribute rock properties spatially and honor structural elements, even in areas with limited wellbore information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional 3-D rock property modeling is used, then the modeling process is simpler, but the lateral and vertical resolution of rock property characterization is insufficient
Solution Approach 1:
The patent combines seismic data with wellbore data to create an integrated 3-D mechanical earth model. This merging of multiple data sources enables high-resolution rock property characterization throughout the entire field, not just near wellbores, resolving the contradiction between measurement precision and model completeness.
Solution Approach 2:
The patent transitions from traditional 2-D or limited 3-D modeling to comprehensive 3-D mechanical earth modeling that incorporates spatial distribution of rock properties in three dimensions. This dimensional expansion enables accurate characterization of lateral and vertical variations in rock properties across the entire field.
2Reliability
If high-resolution 3-D mechanical earth modeling is implemented, then rock property distribution is accurately characterized, but data processing complexity and computational requirements increase
Solution Approach 1:
The patent employs neural networking as an intermediary tool to automatically integrate seismic and wellbore data. The neural network learns the complex relationships between different data types and rock properties, enabling accurate 3-D modeling without requiring manual integration of multiple complex datasets.
Solution Approach 2:
The patent replaces traditional mechanical data integration methods with neural networking algorithms. This substitution automates the complex process of combining seismic and wellbore data, reducing manual processing complexity while maintaining or improving the accuracy of rock property characterization.
3Area of stationary object
If seismic data alone is used for modeling, then coverage across the entire field is achieved, but the resolution and accuracy of rock property predictions are insufficient
Solution Approach 1:
The patent merges seismic data, which provides broad field coverage, with wellbore data, which provides high-resolution rock property measurements. This combination allows the model to maintain comprehensive spatial coverage while achieving high prediction resolution through the calibration provided by wellbore observations.
Solution Approach 2:
The patent applies local quality by using wellbore data to calibrate and enhance the resolution of rock property predictions in specific locations, while maintaining the broad spatial coverage provided by seismic data. The model adapts the level of detail locally based on data availability and quality.
Data Source
AI summary
A technique includes receiving a first dataset that is indicative of seismic data acquired in a seismic survey of a field of wells and receiving a second dataset that is indicative of wellbore data acquired in a wellbore survey conducted in at least one of the wells. The technique includes determining a mechanical earth model for the field based at least in part on the seismic data and the wellbore data.