Automated Seismic Interpretation via AVA Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current seismic interpretation methods are inefficient and inaccurate in identifying 3-D distributions of seismic facies, particularly in complex geology, leading to bottlenecks in hydrocarbon reservoir exploration and characterization.
Innovation Solution
The method employs machine learning algorithms to identify seismic facies based on AVA clusters, generating 3-D digital images of seismic interpretations using pre-stack seismic datasets, leveraging computational power to uncover patterns that human interpreters may miss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If trace-by-trace classification methods are used, then detailed analysis is achieved, but processing time increases and accuracy decreases
Solution Approach 1:
The method segments the seismic volume into discrete 3-D blocks representing different seismic facies types. Each block is characterized by specific AVA cluster sequences, allowing the system to process and classify large volumes efficiently while maintaining detailed facies identification accuracy through the block-based approach.
Solution Approach 2:
The invention transitions from traditional 2-D trace-by-trace analysis to 3-D volumetric analysis. By processing seismic data in three dimensions and identifying cluster sequences through depth at multiple spatial locations, the method achieves both improved accuracy and efficiency by leveraging the additional spatial dimension.
2Productivity
If traditional seismic interpretation methods are used, then manual analysis is performed, but productivity decreases and interpretation accuracy is reduced
Solution Approach 1:
The system implements automated seismic interpretation where the computer algorithm independently performs facies identification without requiring manual intervention. The method uses machine learning models to automatically classify seismic blocks, generate 3-D distributions, and produce interpretation results, thereby dramatically improving productivity while maintaining or enhancing accuracy through consistent algorithmic application.
Solution Approach 2:
The invention replaces manual mechanical interpretation processes with automated computational algorithms. By substituting human analysts with machine learning-based automated systems that process AVA clusters and generate 3-D facies distributions, the method achieves both higher productivity and improved consistency in interpretation accuracy.
3Measurement precision
If complex geology is analyzed using conventional methods, then detailed interpretation is attempted, but the process becomes too time-consuming and inaccurate
Solution Approach 1:
The method transforms the interpretation approach by changing key parameters: instead of analyzing individual traces or 2-D sections, the system processes 3-D volumetric data using AVA cluster sequences as classification parameters. This parameter transformation enables accurate delineation of subsurface features in complex geology while managing process complexity through automated algorithms.
Data Source
AI summary
A computer-implemented method is described for automated seismic interpretation that includes receiving, at one or more processors, a pre-stack seismic dataset representative of the subsurface volume of interest; performing, via the one or more processors, a machine learning algorithm on the pre-stack seismic dataset to identify seismic facies based on AVA clusters, wherein the identified seismic facies include cluster sequences in depth for a plurality of spatial x-y locations in the subsurface volume; performing, via the one or more processors, seismic interpretation of the seismic dataset based on the identified seismic facies to generate a digital image of the seismic interpretation; and displaying the digital image of the seismic interpretation on a user interface.