Well Integrity Classification for CO2 Storage Risk Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CO2 storage technologies face challenges in accurately assessing the risk of CO2 leakage and migration, particularly in depleted hydrocarbon reservoirs, due to limitations in well integrity evaluation and potential pathways for CO2 migration, which prolongs the lead time for site maturation and increases the GHG footprint.
Innovation Solution
A method involving a classification process using well integrity rules, including criteria such as cap rock seal, casing integrity, and proximity to groundwater zones, combined with machine learning techniques, to predict CO2 storage risk assessments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional well integrity evaluation methods are used, then expert knowledge can identify potential CO2 migration paths, but the lead time for site maturation is prolonged up to a year
Solution Approach 1:
The patent creates a virtual replica of the well integrity evaluation process through a classification model trained on historical expert assessments. This digital copy automates the expert knowledge, allowing rapid prediction of CO2 storage risk without requiring actual expert review time, thus reducing lead time while maintaining assessment accuracy
Solution Approach 2:
The classification model is trained in advance on historical well integrity data and expert assessments. This preliminary training phase enables the model to quickly evaluate new wells without requiring real-time expert analysis, thereby reducing the lead time for site maturation while preserving measurement precision
2Reliability
If extensive CO2 monitoring activities are conducted for a prolonged period, then CO2 containment can be ensured, but project delivery timelines are delayed
Solution Approach 1:
The classification model performs preliminary risk assessment by evaluating well integrity against multiple failure modes (casing failure, cement failure, formation fracture, caprock failure) before CO2 injection begins. This advance evaluation identifies high-risk wells that require extended monitoring, allowing low-risk wells to proceed with standard monitoring protocols, thus improving project delivery speed while maintaining containment safety
Solution Approach 2:
The patent applies differentiated monitoring strategies based on local well-specific risk characteristics. Wells classified as high-risk by the model receive intensified monitoring, while low-risk wells receive standard monitoring, optimizing the balance between reliability and productivity across the portfolio of injection wells
3Productivity
If compression of CO2 gas is applied to overcome water pressure in the formation, then CO2 injection can proceed, but energy consumption increases with related GHG footprint
Solution Approach 1:
The patent segments the CO2 storage system into distinct zones based on pressure characteristics and aquifer strength. By identifying formation water pressure zones through the classification model, injection strategies can be optimized to target zones requiring minimal compression, thereby reducing overall energy consumption while maintaining injection capacity in viable zones
Data Source
AI summary
A method for predicting a CO2 storage risk assessment includes determining a set of well integrity rules and determining a classification process based on the set of well integrity risks. Data relevant to the set of well integrity rules is extracted from data for a well located in a subsurface formation. The extracted data is provided to the classification process. A prediction for a subsurface CO2 storage risk assessment is computed for the well. In a preferred embodiment, subsurface CO2 storage risk assessment for two or more wells in the subsurface formation are used to compute a prediction of a formation CO2 storage risk assessment.