Self-Organizing Maps for Facies Cluster Modeling in Geosteering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual interpretation of petrophysical log data from target wells to offset wells in geosteering operations is prone to errors due to sparse datasets, noise, and complexity, especially in high-angle or horizontal wells, leading to inconsistent correlations and challenges in identifying wellbore positioning across discontinuous geology.
Innovation Solution
A data clustering process using unsupervised machine learning techniques, such as Self-Organizing Maps, to generate facies cluster models from petrophysical log data, which improves data interpretation and visualization, enabling more accurate wellbore correlation and positioning by identifying facies groups and stratigraphic positions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual interpretation of petrophysical log data is used, then human expertise and flexibility are utilized, but interpretation accuracy decreases due to sparse datasets, noise, and complexity
Solution Approach 1:
The patent replaces manual mechanical interpretation processes with automated computational algorithms. Specifically, it uses machine learning models and automated correlation algorithms to process petrophysical log data, substituting human manual analysis with systematic computational methods that can handle sparse datasets, noise, and complexity more reliably and consistently.
Solution Approach 2:
The patent transforms the interpretation process by changing from subjective manual parameter assessment to objective computational parameter analysis. It applies automated algorithms that systematically evaluate multiple parameters simultaneously (gamma-ray, resistivity, density, porosity logs) and their relationships, enabling more accurate and consistent interpretation even with noisy or sparse data.
2Productivity
If automated clustering processes are implemented, then interpretation speed and consistency improve, but system complexity increases
Solution Approach 1:
The patent implements self-service through automated clustering algorithms that autonomously process petrophysical log data without requiring manual intervention. The system automatically performs data preprocessing, clustering analysis, facies identification, and correlation tasks, enabling rapid and consistent interpretation while reducing the need for complex manual processing workflows.
3Measurement precision
If traditional well correlation methods are used, then simplicity is maintained, but accuracy of wellbore positioning across discontinuous geology decreases
Solution Approach 1:
The patent extends traditional 1D well log correlation into multi-dimensional analysis by incorporating spatial coordinates, directional drilling data, and 3D geological modeling. This dimensional expansion enables accurate wellbore positioning across discontinuous geology by analyzing correlations in multiple dimensions simultaneously, including lateral and vertical spatial relationships.
Solution Approach 2:
The patent applies segmentation by dividing the geological formation into discrete facies units and stratigraphic intervals based on automated clustering of log data. This segmentation creates distinct, identifiable geological units that can be correlated across multiple wells, improving wellbore positioning accuracy by providing clear reference points even in discontinuous geology.
Data Source
AI summary
The disclosure provides a data clustering process for interpreting formation data, such as delineating reservoirs in well placement models. The data clustering process can be used with correlating offset well data and high angle or horizontal (HAHZ) target well data. Facies distribution and thus stratigraphy and the position of a borehole within the stratigraphic setting can also be assessed using the data clustering process via unsupervised computer learning techniques. A method of performing a well operation associated with a wellbore and an automated directional drilling system are provided herein. In one example, the method includes: (1) obtaining target well data from a wellbore in a subterranean formation, (2) generating a facies cluster model for the subterranean formation using a clustering process on the target well data, and (3) performing a well operation associated with the wellbore using the facies cluster model.