Formation Property Prediction with Automated Correlation Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting formation properties in unexplored regions are cumbersome and require manual calibration of empirical correlations, lacking flexibility and automation.
Innovation Solution
A method involving drilling a first well, obtaining well properties, determining a correlation function, calibrating coefficients, and applying the calibrated function to a second well to predict formation properties, with automated calibration and ranking of correlations using a database and optimization techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual calibration of correlation coefficients is performed for each region, then prediction accuracy for formation properties is improved, but the complexity and time required for the calibration process increases significantly
Solution Approach 1:
The system performs automated calibration where the software automatically adjusts correlation coefficients to match measured formation properties without requiring manual intervention. The calibration process is self-executing, using optimization algorithms to minimize the difference between predicted and actual formation properties, thereby eliminating the need for manual calibration while maintaining high prediction accuracy.
Solution Approach 2:
The system automatically modifies correlation coefficients (parameters) based on measured formation properties from new wells. By changing these parameters through automated optimization rather than manual adjustment, the system adapts correlations to different regions efficiently, improving prediction accuracy while reducing the complexity and time associated with manual parameter tuning.
2Reliability
If multiple correlations are calibrated manually to determine the best performing one, then prediction reliability is improved, but the time and effort required for calibration increases
Solution Approach 1:
The automated calibration system evaluates multiple correlations simultaneously without requiring manual intervention for each one. The software automatically performs calibration on multiple correlation functions, compares their performance against measured data, and identifies the best-performing correlation, thereby maintaining high prediction reliability while dramatically reducing the time and effort required.
Solution Approach 2:
The system performs preliminary automated calibration of multiple correlations before field decisions are made. By pre-calibrating and ranking multiple correlation functions using measured formation properties, the system prepares reliable prediction models in advance, eliminating the need for time-consuming manual calibration when predictions are actually needed.
3Measurement precision
If empirical correlations with region-specific coefficients are used, then prediction accuracy for local conditions is improved, but the adaptability of the method to different regions decreases
Solution Approach 1:
The system automatically adjusts correlation coefficients (parameters) for different regions through automated calibration. By modifying these parameters based on measured formation properties from each specific region, the system maintains high local prediction accuracy while simultaneously adapting to different geological conditions across various regions, thereby resolving the contradiction between local accuracy and regional adaptability.
Solution Approach 2:
The automated calibration system creates a universal framework that can adapt correlations to any region. The same correlation functions can be applied across different regions, and the automated calibration process adjusts their coefficients to fit local conditions, making the method universally applicable while maintaining region-specific accuracy through parameter optimization.
Data Source
AI summary
A method for predicting a formation property of a formation, including the steps of: drilling a first well that penetrates the formation, obtaining well properties from the first well, determining a measured formation property from the first well, determining a correlation function that estimates a predicted formation property from the well properties, wherein the correlation function comprises coefficients, calibrating the correlation function by modifying the coefficients until the predicted formation property best matches the measured formation property, drilling a second well that penetrates the formation, obtaining well properties from the second well, determining the formation property from the second well by applying the correlation function with the modified coefficients to the well properties.