Structured Subsurface Representations for Hydrocarbon Reasoning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current geophysical prospecting methods, particularly seismic interpretation, face inefficiencies in detecting and interpreting subsurface features due to unstructured data and the lack of explicit representations, leading to ambiguous interpretations and difficulties in reasoning about hydrocarbon systems.

Innovation Solution

The use of structured representations, such as graphs and embeddings, to identify geologic and fluid objects and their relationships from seismic data, enabling more effective geological reasoning and hydrocarbon system analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If unstructured seismic data is used for subsurface feature detection, then data processing flexibility is maintained, but interpretation accuracy and reasoning capability deteriorate due to lack of explicit representations

Engineering Contradiction:

Improveinterpretation accuracyVSAvoiddata structure complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments unstructured seismic data into structured components by identifying and extracting specific geologic objects (faults, horizons, geobodies) and their relationships. This segmentation transforms the continuous unstructured data into discrete, organized elements that can be systematically analyzed, thereby improving interpretation accuracy while managing complexity through structured representation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces structured representations (graphs, ontologies, knowledge bases) as intermediary layers between raw seismic data and interpretation results. These intermediaries organize and contextualize the data, enabling more accurate reasoning about hydrocarbon systems without requiring direct complex processing of the original unstructured data.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If traditional seismic interpretation methods are used, then existing workflows are maintained, but productivity deteriorates due to labor-intensive manual interpretation processes

Engineering Contradiction:

Improveinterpretation efficiencyVSAvoidinterpreter time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent enables the system to perform interpretation tasks autonomously by using structured representations and automated reasoning algorithms. The structured data format allows computers to automatically identify geologic objects, determine their relationships, and draw conclusions without requiring continuous human intervention, thereby significantly improving productivity and reducing interpreter time investment.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical interpretation processes with automated computational systems. By structuring the data in machine-readable formats with explicit relationships, the system enables algorithms to automatically perform tasks that previously required human interpreters to manually examine images and documents, thereby accelerating the interpretation workflow.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If explicit structured representations are implemented, then reasoning capability about hydrocarbon systems is improved, but data processing complexity increases

Engineering Contradiction:

Improvereasoning capabilityVSAvoidprocessing system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal structured representation framework that can handle multiple types of geologic objects and relationships through a unified model. The graph-based structure and ontology can represent diverse subsurface features (faults, horizons, geobodies) and their various relationships in a single flexible system, enhancing reasoning capability while avoiding the need for separate processing systems for each feature type.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20230161061A1Structured representations of subsurface features for hydrocarbon system and geological reasoning

Publication Date: 2023.05.25 EXXONMOBIL UPSTREAM RESEARCH COMPANY(US)

AI summary

A method and apparatus for utilizing a structured representation of a subsurface region. A method includes obtaining subsurface data for the subsurface region; and extracting the structured representation from the seismic data by: identifying geologic and fluid objects in the seismic images, wherein each object corresponds to a node of the structured representation; and identifying relationships among the identified geologic and fluid objects, wherein each relationship corresponds to an edge of the structured representation. A method further includes determining object attributes, edge attributes, and/or global attributes from the subsurface data. A method further includes inferring information from the structured representation.