Geological CO2 Storage Capacity Assessment via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing geological carbon dioxide storage (GCS) capacity are subjective and prone to human error, lacking objectivity and failing to account for specific geologic conditions and mechanisms of different types of geologic bodies, leading to inadequate site selection for carbon capture and storage.
Innovation Solution
A system and method using machine learning algorithms to determine scores and weights of geologic indicators for GCS capacity assessment, based on training samples and storage capacity determination models tailored to specific geologic bodies, providing a quantitative and objective ranking of candidate sites.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning algorithms are used to determine geologic indicator scores and weights, then assessment objectivity and accuracy are improved, but system complexity increases
Solution Approach 1:
The assessment system is segmented into distinct functional modules: a data acquisition module that collects geologic indicator data, a machine learning model module that processes the data, and an assessment output module that generates results. This modular segmentation allows the complex ML-based assessment to be managed through independent, well-defined components, reducing the perceived system complexity while maintaining high assessment accuracy.
Solution Approach 2:
The machine learning model serves as an intermediary between the raw geologic indicator data and the final assessment results. This intermediary automatically determines indicator scores and weights through trained algorithms, eliminating the need for manual expert judgment while maintaining objectivity. The ML intermediary handles the computational complexity internally, presenting a simplified interface for users.
2Extent of automation
If machine learning algorithms are used to determine geologic indicator scores and weights, then human intervention is reduced, but computational requirements increase
Solution Approach 1:
The machine learning models are trained in advance using historical geologic data and expert assessments before deployment. This preliminary training action allows the models to automatically determine indicator scores and weights during actual assessments without requiring real-time computational resources for model development. The heavy computational work is performed beforehand, enabling automated assessments with reduced real-time energy consumption.
3Measurement precision
If storage capacity determination models tailored to specific geologic bodies are used, then assessment accuracy for different geologic conditions is improved, but model complexity increases
Solution Approach 1:
The system employs specialized storage capacity determination models tailored to specific types of geologic bodies (e.g., saline aquifers, depleted oil and gas reservoirs, unmineable coal seams). Each model is optimized for the local characteristics and storage mechanisms of its specific geologic type, improving assessment accuracy for that particular condition. The system selects the appropriate local model based on the geologic body type, ensuring high precision without requiring a single overly complex universal model.
Data Source
AI summary
The present disclosure provides a method for assessing GCS capacity. The method includes: determining scores of a plurality of geologic indicators of a target region belonging to a target type of geologic body for the GCS; and determining an assessment result of the GCS capacity of the target region based on the scores of the plurality of geologic indicators and weights of the plurality of geologic indicators.