AI Carbonate Core Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual identification and description of carbonate cores in hydrocarbon reservoirs are labor-intensive, time-consuming, and subjective, leading to increased costs and inconsistencies in reservoir characterization.
Innovation Solution
An AI-based model is used to automatically detect and describe carbonate core features from core images by separating images into blocks, predicting features, and generating core descriptions based on confidence values, employing techniques like depth convolutional neural networks and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual identification and description of carbonate cores is used, then human expertise and flexibility are leveraged, but labor intensity and time consumption increase significantly
Solution Approach 1:
The patent replaces manual mechanical inspection and description of carbonate cores with an automated image processing system using deep learning neural networks. The system automatically analyzes core images, identifies features, and generates descriptions without human intervention, thereby maintaining accuracy while dramatically increasing productivity.
Solution Approach 2:
The patent creates digital copies of physical carbonate core images and analyzes these copies using AI models. Instead of physically handling and describing each core manually, the system processes digital representations, enabling rapid automated analysis that maintains descriptive accuracy while reducing labor intensity and time consumption.
2Reliability
If manual identification and description of carbonate cores is used, then contextual understanding and nuance are captured, but subjectivity and inconsistency increase
Solution Approach 1:
The patent replaces subjective manual description with an objective automated AI-based system. The neural network applies consistent criteria and algorithms to analyze core images, eliminating the variability introduced by different operators' expertise levels and preferences, thereby improving consistency while reducing operational complexity through automation.
Solution Approach 2:
The system incorporates confidence values in its predictions and can iteratively refine its analysis. The AI model provides feedback on the quality and consistency of its descriptions, enabling automated quality control that maintains high reliability while simplifying the operational process through algorithmic standardization.
3Adaptability or versatility
If manual identification and description of carbonate cores is used, then flexibility in handling complex cases is maintained, but cost and time investment increase
Solution Approach 1:
The patent replaces time-consuming manual analysis with automated AI-based image processing. The deep learning model rapidly analyzes core images and generates descriptions in seconds, maintaining adaptability to complex geological cases while reducing the time investment from days or weeks to minutes, thereby eliminating significant time losses.
Data Source
AI summary
A method and system is provided for detection of carbonate core features from core images. An input carbonate core image is separated into a plurality of first blocks, each of the plurality of first blocks having a first block size. An image of each of the separated plurality of first blocks is input into an artificial intelligence (AI) model. The AI model being trained to predict for each first block, one of a plurality of carbonate core features and a corresponding confidence value indicating a confidence of the predicted carbonate core feature being imaged in the first block. Any bounding boxes of a first set of bounding boxes are detected in the input core image based on the predicted one of the plurality of carbonate core features and the corresponding confidence values for each first block.