Geological Analog Recommendation via Vector Embeddings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing volume of information from well logs makes it challenging to identify useful information for decisions in oil and gas production or exploration, and existing methods are inefficient in discovering and recommending well and geological analogs.
Innovation Solution
A method and system that receive text-based characterizations of wells, generate vector representations of these characterizations, identify analog wells using these vectors, and output updated well characterizations based on the identified analogs, facilitating the discovery of wells and locations with similar petrophysical and geological characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis of well logs is performed, then identification accuracy of useful information is maintained, but time consumption and operational efficiency deteriorate
Solution Approach 1:
The patent replaces manual mechanical analysis of well logs with an automated computational system that uses natural language processing and vector embeddings. The system automatically extracts features from well logs, generates embeddings, and identifies analog wells through computational algorithms, eliminating the need for manual review of extensive log data while maintaining or improving identification accuracy.
Solution Approach 2:
The system enables self-service by allowing the automated analog identification process to operate independently without requiring continuous manual intervention. The computational model automatically processes well logs, generates embeddings, and identifies analogs based on predefined criteria, freeing operators from repetitive manual analysis tasks while preserving the ability to review and refine results when needed.
2Loss of information
If comprehensive well log data is collected, then information completeness is improved, but data processing complexity and difficulty increase
Solution Approach 1:
The patent segments the comprehensive well log data into distinct feature categories (geological, petrophysical, production characteristics) and processes each segment separately through specialized extraction algorithms. This segmentation allows the system to handle large volumes of diverse data systematically, reducing processing complexity while maintaining information completeness by ensuring each feature type is appropriately analyzed.
Solution Approach 2:
The system introduces vector embeddings as an intermediary representation that bridges raw well log data and analog identification results. The embedding process transforms complex, multi-dimensional log features into a condensed numerical space where similarities can be efficiently computed, simplifying the processing of comprehensive data while preserving the essential information needed for accurate analog matching.
3Productivity
If automated analog identification system is implemented, then operational efficiency is improved, but system complexity increases
Solution Approach 1:
The patent implements a universal automated system that handles multiple well log types, feature categories, and analysis requirements through a single integrated platform. The system can process various well log formats, extract different feature types, and identify analogs across diverse geological settings using the same core architecture, reducing the need for multiple specialized systems while maintaining high operational efficiency.
Solution Approach 2:
The system manages complexity by dynamically adjusting processing parameters such as embedding dimensions, similarity thresholds, and feature weighting based on the specific analysis requirements and data characteristics. This parameter adaptability allows the automated system to optimize performance for different scenarios without requiring fundamental changes to the system architecture, balancing efficiency gains with manageable complexity.
Data Source
AI summary
Aspects of the present disclosure relate to a well analog recommendation system. The well analog recommendation system may generate numerical representations indicative of text-based descriptions within a well report and/or well log associated with a well. Further, the well analog recommendation system may generate a well analog output that may include one or more text-based characterizations associated with one or more additional wells that are determined based on the numerical representation. For example, the well analog recommendation system may compare the numerical representation of the well to one or more numerical representations associated with the one or more additional wells and output the one or more text-based characterizations when the numerical representations are approximately equal or above a threshold.