Machine Learning Formation Top Depth Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current formation top predictions in the oil and gas industry are subjective and prone to errors due to their reliance on human expertise, leading to potential inaccuracies in hydrocarbon exploration and production.
Innovation Solution
A method and system utilizing seismic data, well log data, and a machine-learning model to determine formation top depth, where the machine-learning model assigns features from seismic and well log data to formations in a stratigraphic column, enabling objective and accurate predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual prediction methods are used by geologists, then expertise-based judgment can be applied, but subjectivity and errors are introduced
Solution Approach 1:
The patent replaces the manual mechanical process of geological analysis with an automated machine learning system. The ML model processes seismic and well log data objectively, eliminating human subjectivity while maintaining predictive accuracy through computational algorithms trained on geological patterns.
Solution Approach 2:
The machine learning model performs self-learning from training data consisting of seismic and well log datasets with known formation top depths. The system automatically improves its prediction capabilities through iterative training without requiring continuous manual intervention, achieving reliable automated predictions.
2Measurement precision
If automated machine-learning models are used, then objectivity and accuracy are improved, but system complexity increases
Solution Approach 1:
The machine learning model serves multiple functions: it processes both seismic data and well log data, performs feature extraction and assignment, and predicts formation top depths across different geological formations. This multi-functionality consolidates what would otherwise require multiple separate systems into a single unified platform.
Solution Approach 2:
The patent introduces a stratigraphic column as an intermediary framework that organizes formation data and provides a standardized structure for the ML model to process. This intermediary layer simplifies the complexity by providing a consistent organizational framework for diverse geological data.
Data Source
AI summary
A method may include obtaining, by a computer processor, seismic data regarding a geological region of interest. The method may further include obtaining, by the computer processor, well log data from a wellbore within the geological region of interest. The method may further include determining, by the computer processor, a formation top depth using the seismic data, the well log data, a stratigraphic column, and a machine-learning model. The stratigraphic column may describe an order of various formations within the geological region of interest. The machine-learning model may assign a feature among the seismic data and the well log data to a formation among the formations in the stratigraphic column to determine the formation top depth.