Seismic Navigation CRS Matching With Metadata Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing seismic data analysis systems face challenges in accurately matching seismic data to cartographic reference systems (CRS), leading to incorrect geo-referencing and increased user effort, which can result in costly mistakes during hydrocarbon reservoir exploration and production.

Innovation Solution

A machine learning system is trained to associate seismic data with CRSs by parsing meta data to determine names, areas, or codes, generating a seismic data-CRS match, and updating a CRS model to improve matching accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual CRS matching is performed by users, then matching accuracy can be maintained through expert judgment, but user effort and time consumption increase significantly

Engineering Contradiction:

ImproveCRS matching accuracyVSAvoiduser effort and time consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by allowing seismic data to automatically match with CRS through machine learning models that parse metadata and perform matching without human intervention, eliminating the need for manual expert judgment while maintaining accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual user matching with an automated machine learning-based system that uses metadata parsing and trained models to perform CRS matching automatically, substituting human effort with computational processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If automated CRS matching is implemented using traditional methods, then user effort is reduced, but matching accuracy deteriorates due to inability to handle diverse metadata formats from different sources

Engineering Contradiction:

Improveuser effort reductionVSAvoidCRS matching accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system achieves universality by creating a standardized CRS model that can handle diverse metadata formats from different government agencies and countries through unified parsing rules and multiple CRS associations, making the system adaptable to various data sources while maintaining accuracy

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent applies parameter changes by transforming diverse metadata parameters into a standardized format that the machine learning model can process, converting various metadata structures from different sources into consistent features for accurate CRS matching

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If seismic data from multiple sources with different metadata formats is processed, then data coverage and versatility improve, but matching difficulty and system complexity increase

Engineering Contradiction:

Improvedata coverage from multiple sourcesVSAvoidsystem complexity for handling diverse formats

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system introduces an intermediary layer of standardized CRS model and unified parsing rules that mediate between diverse metadata formats from different sources and the matching process, simplifying the handling of multiple formats without requiring complex source-specific processing logic

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12442946B2Seismic navigation data quality analysis

Publication Date: 2025.10.14 LANDMARK GRAPHICS CORP

AI summary

Processes can be employed to select cartographic reference system (CRS) recommendations from a CRS model where the CRS recommendations are matched to received seismic data. A learning mode can be used to build the CRS model where seismic data is matched to CRS. The learning mode can be automated using natural language processing system to parse the meta data for the seismic data, such as the name, area, or code, or label. The CRS model can be updated using an output from a user system, such as when a user manually matches a CRS to seismic data. The matched seismic data to CRS can be used as input to a user system or a computing system, such as a borehole operation system.