Underground Resource Extraction Mapping Under Geological Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating the exploitation potential of underground formations, such as geothermal and hydrocarbon resources, suffer from low spatial resolution due to buffering or interpolation of sparse measurements, failure to account for geological constraints, and lack of uncertainty maps, leading to suboptimal decision-making.
Innovation Solution
A method that uses supervised machine learning to determine weighting coefficients based on geological constraints, improves spatial resolution through property value prediction, and optionally generates uncertainty maps, incorporating AHP analysis to assess resource potential.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If buffering or interpolation methods are used to handle sparse measurements, then the evaluation process can be completed, but the spatial resolution of the resulting maps is low
Solution Approach 1:
The patent changes the parameter of spatial resolution by using machine learning algorithms that can predict property values at unsampled locations with higher precision than traditional buffering or interpolation methods, thereby improving map resolution without requiring increased data density
Solution Approach 2:
The patent replaces traditional mechanical/geological buffering methods with computational machine learning models (such as neural networks or regression algorithms) that can process sparse measurements and generate high-resolution spatial distributions of formation properties
2Reliability
If traditional multi-criteria analysis is applied without considering geological constraints, then the analysis is simpler, but the reliability of the exploitation potential assessment is reduced
Solution Approach 1:
The patent applies local quality by incorporating geological constraints that are specific to different spatial locations and formation types, allowing the multi-criteria analysis to adapt its parameters and weightings based on local geological conditions rather than using uniform criteria throughout
Solution Approach 2:
The patent segments the analysis into multiple stages: first evaluating individual formation properties, then integrating geological constraints, and finally performing the multi-criteria synthesis, thereby managing complexity through systematic decomposition of the assessment process
3Loss of information
If sparse measurements are used directly without processing, then data loss is minimized, but the coverage and utility of the evaluation is insufficient
Solution Approach 1:
The patent creates copies of the sparse measurement data through machine learning predictions that generate estimated property values for unsampled locations, effectively copying the information pattern from measured to unmeasured areas without physically moving or duplicating the original measurements
Solution Approach 2:
The patent makes the evaluation system universal by developing a multi-functional approach that can handle various types of formation properties (porosity, permeability, saturation) and different data sparsity patterns using the same machine learning framework, thereby expanding coverage across diverse geological settings
Data Source
Figure 1~2
Figure 3~4
AI summary
The present invention relates to a method for extracting a resource from an underground formation. Based on measurements, a meshed representation having values of properties of the formation in each mesh cell is constructed. To each mesh cell, a score representing the relevance of each property value to the extraction of the resource is attributed. Sets of mesh cells are defined depending on a spatially variable geological constraint and, for each set of mesh cells, weighting coefficients of the properties are determined by applying an analytic hierarchy process. For each mesh cell, a score representative of the extraction potential of the resource is determined by summing the scores attributed to each property weighted by the weighting coefficients of the properties in the mesh cell. Based on the scores representative of extraction potential, a scheme of extraction of the resource is determined and the resource is extracted according to the extraction scheme.