Reservoir Grid Cell Properties from Point Cloud Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Characterizing geological formations for hydrocarbon well placement and performance is challenging due to the heterogeneity of rock properties, which affects hydrocarbon extraction efficiency and increases carbon emissions.
Innovation Solution
A computing device uses a machine-learning model to cluster data points from a grid-less point cloud model based on a heterogeneity index, determining cell properties for a grid that accurately represents the geological formation, thereby optimizing flow simulations and reducing computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a detailed grid model is used to accurately represent geological formation heterogeneity, then measurement precision and reliability improve, but device complexity and computational resources increase
Solution Approach 1:
The patent divides the geological formation into discrete grid cells with specific properties (porosity, permeability, rock type) that can be independently characterized and processed. This segmentation allows accurate representation of heterogeneity while enabling efficient computational handling through modular processing of individual cells rather than continuous complex models
Solution Approach 2:
The patent transforms complex geological formation data into standardized cell properties (rock type, porosity, permeability values) that simplify the representation of heterogeneity. By changing parameters to discrete, categorized values rather than continuous complex functions, the model maintains accuracy while reducing computational complexity
2Reliability
If traditional flow simulation methods are used, then reliability of hydrocarbon extraction prediction is maintained, but productivity and computational efficiency decrease
Solution Approach 1:
The patent creates a simplified digital twin or representative model of the geological formation using standardized cell properties that replicates the essential heterogeneity features. This copied model enables faster simulations while maintaining predictive reliability by preserving key geological characteristics without requiring full-resolution complex modeling
Solution Approach 2:
The patent changes the parameters from continuous complex geological functions to discrete cell-based properties (rock type categories, standardized porosity/permeability values) that enable more efficient computational processing while maintaining the reliability of hydrocarbon flow predictions through accurate representation of formation heterogeneity
Data Source
AI summary
A system can receive a grid-less point cloud model of a geological formation, the grid-less cloud point model that includes data points. The system can determine, by a machine-learning model for clustering data points, clusters for the data points according to a heterogeneity index. The system can determine an outline for each cluster. The system can generate a grid corresponding to the geological formation, the grid comprising a plurality of cells for each cluster of the plurality of clusters, each cluster having cell properties. The system can output the grid for the geological formation to a graphical user interface, the grid usable for executing a flow simulation at the graphical user interface.