Seismic Attribute Clustering for Hydrocarbon Reservoir Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for identifying prospective hydrocarbon reservoirs using seismic data are time-consuming and labor-intensive, requiring manual comparison of large seismic attribute datasets, and existing automated approaches are not robust to noisy data or missing data.

Innovation Solution

A computer-based method for within-seismic attribute clustering, identifying an anchor attribute and subordinate attributes, linking objects across attribute datasets using a proximity measure, and forming cross-attribute clusters to identify regions potentially containing hydrocarbon reservoirs, which is robust and computationally efficient.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual comparison of seismic attribute datasets is used, then identification accuracy can be maintained through expert judgment, but time consumption and labor intensity increase significantly

Engineering Contradiction:

Improveidentification accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical comparison with automated computer-based image processing and pattern recognition algorithms. The system automatically compares seismic attribute datasets, performs cross-attribute clustering, and identifies prospective regions without human intervention, thereby maintaining accuracy while dramatically reducing time consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates processed copies of seismic attribute data through multiple attribute volumes and image representations. These copied and transformed data representations enable automated analysis while preserving the original information content, allowing rapid comparison and identification without requiring experts to manually examine raw data.

Inventive Principle:

Principle #26Copying

2Loss of time

If existing automated approaches are used, then time consumption is reduced, but robustness to noisy data and missing data deteriorates

Engineering Contradiction:

Improvetime consumptionVSAvoidrobustness to noisy data

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The patent applies preprocessing steps that cushion against noisy and missing data before automated analysis. The system performs data quality assessment, applies appropriate filtering and noise reduction techniques, and uses robust clustering algorithms that can handle incomplete data, thereby maintaining reliability while achieving automated efficiency.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Solution Approach 2:

The patent incorporates feedback mechanisms where the system evaluates the quality and reliability of automated identification results. The feedback loop allows the system to adjust processing parameters, re-analyze problematic regions, and validate findings against multiple attributes, thereby improving robustness to noisy and missing data while maintaining automated operation.

Inventive Principle:

Principle #23Feedback

3Loss of information

If multiple seismic attribute datasets are manually reviewed, then comprehensive analysis can be performed, but complexity of operation increases

Engineering Contradiction:

Improvecomprehensive analysisVSAvoidcomplexity of operation

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The patent merges multiple seismic attribute datasets into a unified automated analysis framework. The system simultaneously processes multiple attribute volumes, performs cross-attribute clustering, and integrates results from different attributes, thereby maintaining comprehensive analysis while reducing operational complexity through automation.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a universal automated system that handles multiple types of seismic attributes and analysis tasks through a single integrated platform. The system performs clustering, comparison, identification, and validation across different attribute types, eliminating the need for separate manual analysis procedures for each attribute.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Productivity

If automated clustering algorithms are implemented, then productivity increases, but computational complexity increases

Engineering Contradiction:

Improveidentification efficiencyVSAvoidcomputational complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the computational task into distinct processing stages: data preprocessing, attribute volume generation, cross-attribute clustering, and result identification. This segmentation allows each stage to be optimized independently and enables parallel processing, thereby increasing productivity while managing computational complexity through structured decomposition.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11086035B2Clustering algorithm for geoscience data fusion

Publication Date: 2021.08.10 BAKER YULIA

AI summary

A method, including: performing, with a computer, within-seismic-attribute clustering for each of a plurality of seismic attribute datasets for N different attributes, N being greater than or equal to two; identifying an anchor attribute and N−1 subordinate attributes from the N different attributes; linking, with a computer, objects within the seismic attribute data sets corresponding to the N−1 subordinate attributes to related objects within the seismic attribute data set corresponding to the anchor attribute; and identifying, with a computer, cross-attribute clusters, wherein the objects of any subordinate attribute that are linked to a same object of the anchor attribute are part of a single cross-attribute cluster.