Machine Learning Network for Predicting Geological Data from Geochemical Samples

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The manual organization and interpretation of vast geochemical data from oil samples by geochemists is time-consuming and inefficient, hindering the determination of geological data necessary for oil field management.

Innovation Solution

A method and system utilizing machine learning networks trained with geochemical and geological data to automatically predict new geological data from new oil samples, leveraging gas chromatography and AI algorithms to classify and categorize data, reducing the need for manual interpretation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual organization and interpretation of geochemical data is performed by geochemists, then accurate geological data can be obtained, but the process is time-consuming and inefficient

Engineering Contradiction:

Improveaccuracy of geological data interpretationVSAvoidtime required for data organization and interpretation

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

A machine learning model is introduced as an intermediary between geochemical data and geological interpretation. The model is trained on existing geochemical data paired with expert-interpreted geological data, then automatically predicts geological data for new samples, eliminating the need for manual interpretation while maintaining accuracy through learned patterns from training data.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The manual mechanical process of geochemical data organization and interpretation by geochemists is replaced with an automated computational system. The machine learning model performs the interpretation function that previously required human expertise, transforming a manual intellectual task into an automated algorithmic process.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual interpretation methods are used, then geological data can be determined, but the efficiency of oil field management planning is hindered

Engineering Contradiction:

Improvereliability of geological data for management decisionsVSAvoidefficiency of oil field management planning

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The machine learning model is trained in advance on a comprehensive dataset of geochemical data and corresponding geological interpretations. This preliminary training phase allows the model to learn and internalize the relationships between geochemical indicators and geological conditions, so that during actual oil field management, predictions can be made rapidly without compromising reliability.

Inventive Principle:

Principle #10Preliminary action

3Quantity of substance

If vast amounts of geochemical data are collected from multiple hydrocarbon reservoirs, then comprehensive information is available, but the data requires extensive manual organization

Engineering Contradiction:

Improveamount of geochemical dataVSAvoidcomplexity of data organization process

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The machine learning model performs self-service by automatically processing and interpreting geochemical data without requiring manual organization. The model takes raw geochemical data as input and directly outputs interpreted geological data, eliminating the complex intermediate organization step that previously required significant human effort.

Inventive Principle:

Principle #25Self-service

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Automates the organization and interpretation of geochemical data, significantly reducing the time and effort required for determining geological data, enhancing the efficiency of oil field management planning.

Implementation Method 1

determining new geochemical data for the new oil sample using gas chromatography

Methodology Applied

Scientific EffectGas chromatography: Chromatography

Data Source

PatentUS20240168002A1Interactive correlation and prediction of source rock organofacies, oil families and reservoir alteration using machine learning

Publication Date: 2024.05.23 SAUDI ARABIAN OIL CO

AI summary

Systems and methods are disclosed. The method includes obtaining geochemical data and geological data for a number of oil samples and training a machine learning network using the geochemical data and the geological data. Each oil sample includes hydrocarbon molecules and the geochemical data includes abundances of the hydrocarbon molecules. The method further includes obtaining a new oil sample from a subterranean region of interest and determining new geochemical data for the new oil sample using gas chromatography. The method still further includes predicting new geological data for the new oil sample by inputting the new geochemical data into the trained machine learning network.