Fracture Hydraulic Property Estimation via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies fail to effectively estimate dynamic hydraulic properties of natural fractures in rocks, which are crucial for modeling fluid flow and hydrocarbon reservoir recovery, due to their complex and heterogeneous nature, requiring costly and limited physical measurements.
Innovation Solution
A method and system that utilize high-resolution images and machine-learning models to automatically detect fractures and estimate dynamic hydraulic properties, such as permeability and hydraulic aperture, enabling efficient and cost-effective reservoir simulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physical measurements are used to determine fracture conductivity, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of the fracture through high-resolution images and machine learning models. Instead of physical measurements, the system generates a digital representation (fracture detection) that can be analyzed to estimate hydraulic properties. This virtual copying approach eliminates the need for complex physical measurement equipment while maintaining estimation accuracy.
Solution Approach 2:
The patent replaces mechanical/physical measurement systems with an information-processing system. High-resolution images combined with machine learning algorithms substitute for traditional physical conductivity measurements. The system processes image data through computational models to derive hydraulic properties, eliminating the need for complex physical measurement devices.
2Measurement precision
If physical measurements are used to determine fracture conductivity, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary actions by capturing high-resolution images of the fracture and generating fracture detections through machine learning models. These preliminary processing steps create a ready-to-use virtual representation that can be quickly analyzed to estimate hydraulic properties, eliminating the time-consuming physical measurement process.
Solution Approach 2:
By creating a virtual copy of the fracture through image processing and machine learning, the system enables rapid estimation of hydraulic properties without repeated physical measurements. The digital replica can be analyzed multiple times quickly, significantly reducing the time required compared to physical measurement methods.
3Productivity
If high-resolution images and machine learning models are used, then productivity is improved, but device complexity increases
Solution Approach 1:
The system uses high-resolution images as digital copies of the fracture geometry. These images serve as input data that feed into machine learning models, enabling automated fracture detection and hydraulic property estimation. The copying approach allows for rapid processing and multiple analyses without physical intervention, significantly improving productivity.
Solution Approach 2:
The patent replaces traditional mechanical measurement systems with an automated image-processing and machine learning-based system. This substitution enables high-speed fracture detection and hydraulic property estimation through computational algorithms, dramatically improving productivity while the system complexity is managed through software-based solutions rather than hardware complexity.
Data Source
AI summary
A method for fracture dynamic hydraulic properties estimation and reservoir simulation may include obtaining a first set of images of a first fracture. The method may include obtaining a first set of fracture detections from the first set of images, generating a plurality of numerical calculations based on the first set of fracture detections, and generating a second model based on the plurality of numerical calculations and the first set of fracture detections. The method may further include obtaining a second set of images of a second fracture of a new reservoir, generating a second set of fracture detections of the second fracture, and generating dynamic hydraulic estimations of the second fracture. The method may also include generating a three-dimensional reservoir simulation and determining a plurality of recovery schemes for the new reservoir.