Depth Blended Permeability Estimation from Well Logs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating permeability in carbonate reservoirs using well logs are inaccurate due to the complexity of porosity types and noise in well log data, making it challenging to predict permeability effectively.
Innovation Solution
A depth blended model is generated using a combination of regression algorithms, such as gradient boosting and random forest, trained on core-analysis-based permeability values from well logs to estimate permeability values, which are then applied to other well logs for hydrocarbon production planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to estimate permeability from well logs in carbonate reservoirs, then the process is simple, but the accuracy of permeability estimation is poor due to porosity type complexity and noise in well log data
Solution Approach 1:
The patent combines multiple regression algorithms (gradient boosting, random forest, and other algorithms) into a blended model that integrates their respective strengths. This merging approach allows the system to leverage the complementary capabilities of different algorithms to handle the complexity of carbonate reservoir porosity types and noise in well log data, thereby improving permeability estimation accuracy while managing model complexity through systematic integration
2Reliability
If multiple regression algorithms are combined to improve permeability estimation accuracy, then the reliability of hydrocarbon production planning is improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary actions by pre-training multiple regression algorithms on historical well log data and core analysis data before actual permeability estimation is needed. The blended model is developed and validated in advance using training datasets, allowing the system to have a ready-to-use model that can quickly process new well log data without requiring extensive computation at the time of actual production planning
Solution Approach 2:
The patent segments the permeability estimation process into distinct phases: data preprocessing, model training with multiple algorithms, model blending, and validation. Each phase is handled separately with optimized computational resources, allowing the system to manage the complexity of multiple algorithms efficiently and reduce overall processing time through structured workflow division
Data Source
AI summary
Permeability values are estimated based on well logs using regression algorithms, such as gradient boosting and random forest. The training data is selected from well logs for which core-analysis-based permeability values are available. The estimated permeability values are used to plan hydrocarbon production. The well logs used to build the depth blended model may include total porosity, gamma ray, volume of calcite, density, resistivity, and neutron logs. Selecting the training data may include grouping the well logs according to regions expected to have similar characteristics, choosing a subset of the well logs corresponding to wells expected to provide stable models according to pre-determined criteria, and/or identifying training zones on the chosen well logs according to one or more rules. Validation and consistency checks may also be performed.