Well Property Interpretation Using Tier 1 Models for Noisy Well Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interpreting well properties from Tier 2 hydrocarbon wells with less sophisticated equipment is challenging due to limited and noisy measurements, making accurate quantitative analysis difficult.
Innovation Solution
An interpretation system that uses Tier 1 well measurements and pre-trained models to enhance the interpretation of Tier 2 well data, applying machine learning algorithms to predict well properties with higher accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If Tier 2 wells with less sophisticated equipment are used, then device complexity and cost are reduced, but measurement precision and data quality deteriorate
Solution Approach 1:
The patent introduces an interpretation system as an intermediary between Tier 2 wells and the analysis process. This system uses machine learning models and transfer learning techniques to bridge the gap between limited measurements and accurate property determination, allowing Tier 2 wells to achieve analysis quality previously only attainable with Tier 1 equipment.
Solution Approach 2:
The system changes the approach from direct measurement-based analysis to model-based prediction. By transforming the analysis methodology from relying solely on raw measurement parameters to using trained neural network models that process these parameters, the system achieves high accuracy despite limited input data quality.
2Measurement precision
If more measurement tools and data points are deployed, then measurement precision improves, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of Tier 1 well analysis capabilities through machine learning models trained on Tier 1 data. This allows Tier 2 wells to receive analysis of equivalent quality without actually deploying Tier 1 equipment, effectively copying the analytical capability rather than the physical infrastructure.
Solution Approach 2:
The system performs preliminary training of neural network models using Tier 1 well data before applying them to Tier 2 wells. This preliminary action encapsulates the complex analysis logic in pre-trained models, allowing rapid and accurate analysis of new Tier 2 well data without requiring complex real-time processing infrastructure.
Data Source
AI summary
A system may include processing circuitry and memory storing instructions, where the instructions, when executed by the processing circuitry, cause the processing circuitry to receive a first set of measurements associated with a first set of wells and generate a first well model representative of a property associated with the first set of wells. The processing circuitry may generate a well property model representative of an expected property relative to a measurement associated with a well, receive a second set of measurements associated with a second set of wells, and generate a second well model representative of a first set of predicted measurements. The processing circuitry may generate an adjusted second well model based on the well property model and the second well model, determine a second set of predicted measurements, and instruct a display to display the first set of predicted measurements and the second set of predicted measurements.