Stratigraphic Layer Identification Using Knowledge Base Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional stratigraphic layer identification methods in petroleum reservoir management face challenges in accurately tying well data to seismic data for modeling stratigraphic layers across a seismic volume, leading to inconsistencies and reduced accuracy in reservoir modeling.
Innovation Solution
A system and method utilizing a stratigraphic knowledge base for machine learning, which processes seismic and well log data to identify features, matches them using a feature matching algorithm, and propagates these features to define stratigraphic layer interpretations, enhancing the accuracy and quality of reservoir modeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional stratigraphic layer identification methods are used, then the process can be completed with basic tools, but the accuracy and quality of stratigraphic layer identification deteriorates
Solution Approach 1:
The system segments the stratigraphic identification process into distinct functional modules: well feature extraction module that processes well log data, seismic feature extraction module that processes seismic data, feature matching module that aligns features between datasets, and layer propagation module that extends interpretations. This modular segmentation enables each component to specialize in specific tasks, improving overall identification accuracy while maintaining manageable system complexity through clear separation of concerns.
Solution Approach 2:
The feature matching module serves as an intermediary between well feature extraction and seismic feature extraction modules. It systematically matches features from both data sources, using correlation algorithms to identify corresponding stratigraphic features across different measurement domains. This intermediary component bridges the gap between disparate data types, enabling accurate integration of well log and seismic data without requiring direct complex interactions between all system components.
2Productivity
If manual well-tie analysis is performed, then flexibility in interpretation is maintained, but productivity and consistency deteriorate
Solution Approach 1:
The system implements self-service through automated feature extraction from well log data and seismic data. The well feature extraction module automatically identifies and extracts stratigraphic features from well logs, while the seismic feature extraction module independently extracts features from seismic volumes. These modules operate autonomously to generate candidate features that are then systematically matched, eliminating manual intervention bottlenecks and ensuring consistent application of extraction criteria across all data, thereby improving both productivity and interpretation consistency.
Solution Approach 2:
The layer propagation module implements feedback mechanisms by using matched features from well and seismic data to iteratively refine and extend stratigraphic interpretations across the seismic volume. The system propagates identified layers through the seismic data, continuously comparing predicted layer positions with actual seismic features and adjusting interpretations accordingly. This feedback loop ensures that interpretations remain consistent with both well data constraints and seismic observations, maintaining reliability while automating the expansion of interpretations across large volumes.
3Measurement precision
If feature matching algorithms are selected based on stratigraphic knowledge base, then matching accuracy improves, but computational complexity increases
Solution Approach 1:
The system manages algorithm selection complexity by dynamically changing parameters based on the specific characteristics of the input data. The feature matching module assesses the properties of extracted features from well and seismic data, then selects appropriate matching algorithms and adjusts their parameters accordingly. For example, it may switch between different correlation methods or adjust weighting factors based on data quality, feature types, and geological context. This parameter-based adaptation enables high matching accuracy across diverse scenarios without requiring manual configuration of complex algorithmic settings.
Data Source
AI summary
A system, method and program product for stratigraphic layer identification using a stratigraphic knowledge base for machine learning. Reservoir data includes seismic data and well log data for a reservoir area. The well log data is processed to identify well stratigraphic layer features and the seismic data is processed to identify seismic stratigraphic layer features. A feature matching algorithm based on a stratigraphic knowledge base is selected to match the well stratigraphic layer features to the seismic stratigraphic layer features. The matched features are used to define a stratigraphic layer interpretation for the reservoir area and the interpretation is presented to a user.