AI Seismic Interpretation for Accurate Subsurface Structure Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing seismic data interpretation methods struggle to accurately identify and locate subsurface structures such as horizons, faults, and geobodies, which are crucial for hydrocarbon trap identification and reservoir characterization, limiting the accuracy of subsurface modeling and resource extraction operations.
Innovation Solution
A system and method utilizing a framework like PETREL and OCEAN, integrated with DELFI cognitive exploration and production environment, employs machine learning and AI to enhance seismic data interpretation, enabling accurate modeling and simulation of geologic environments, including meshless techniques and computational frameworks for improved subsurface characterization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional seismic data interpretation methods are used, then the process is simpler and requires less computational resources, but the accuracy of identifying and locating subsurface structures is insufficient
Solution Approach 1:
The patent replaces traditional mechanical/manual seismic interpretation methods with an automated computer-based system that uses machine learning algorithms and artificial intelligence to analyze seismic data, identify subsurface structures, and generate geological models automatically
Solution Approach 2:
The patent introduces trained machine learning models and AI algorithms as intermediaries between raw seismic data and geological interpretation, enabling the system to automatically recognize patterns and features that would be difficult for traditional methods to detect
2Productivity
If traditional seismic interpretation methods are used, then the system is easier to operate, but the productivity and efficiency of subsurface modeling is limited
Solution Approach 1:
The patent enables the seismic interpretation system to perform automated analysis, model generation, and feature identification without requiring extensive manual intervention, allowing the system to serve itself in processing and interpreting seismic data
Solution Approach 2:
The patent employs pre-trained machine learning models and algorithms that have been prepared in advance to rapidly process seismic data, enabling quick generation of subsurface models and reducing overall processing time
3Reliability
If traditional interpretation methods are used, then less computational resources are required, but the accuracy of reservoir characterization is insufficient
Solution Approach 1:
The patent transforms the interpretation process by changing from deterministic algorithms to probabilistic machine learning models, allowing the system to handle uncertainty in seismic data and provide more reliable reservoir characterization through statistical analysis
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method can include accessing a trained machine model as trained to analyze digital seismic data of a region with respect to a structural feature of a geologic region; analyzing at least a portion of the digital seismic data using the trained machine model to generate results; and outputting the results as indicators of spatial locations of the structural feature of the geologic region.