Soil Gas Monitoring for Early Leakage Detection at CO2 Storage Sites
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current soil gas monitoring techniques face challenges in detecting early signs of leakage at underground carbon dioxide storage sites due to complex interactions among atmosphere-soil and biological systems, and fail to accurately interpret time-varying characteristics and interdependencies of soil gases and environmental variables.
Innovation Solution
A method involving multi-resolution time-frequency domain analysis and deep neural networks to identify and evaluate dynamic characteristics of soil gases, separate key environmental driving forces, and predict leakage by configuring a base dataset, performing state-space modeling, and constructing a deep learning model for real-time diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional soil gas monitoring techniques are used, then monitoring can be performed, but early leakage signals cannot be detected due to complex atmosphere-soil and biological system interactions
Solution Approach 1:
The patent segments the complex soil gas monitoring problem into distinct components: baseline variation analysis and leakage signal detection. By separating these functions and applying different analytical methods to each, the system can effectively detect leakage signals despite complex environmental interactions.
Solution Approach 2:
The patent applies dynamic analysis methods to model the time-varying characteristics of soil gases and environmental variables. This dynamic approach allows the system to adapt to changing conditions and distinguish between natural variations and leakage signals, improving detection precision in complex environments.
2Ease of operation
If fixed value-based interpretation methods are used, then data analysis is simplified, but time-varying characteristics and interdependencies of soil gases and environmental variables cannot be properly interpreted
Solution Approach 1:
The patent replaces static fixed-value interpretation with dynamic modeling that captures time-varying characteristics of soil gases and environmental variables. This dynamic approach preserves temporal information while maintaining analytical tractability through structured modeling frameworks.
Solution Approach 2:
The patent transforms the analysis from fixed parameter values to time-varying parameters that capture the dynamic behavior of soil gases and environmental variables. This parameter transformation allows the system to interpret temporal patterns and interdependencies without overwhelming complexity.
3Measurement precision
If high-resolution sensors are used, then measurement precision is improved, but interpretation difficulty increases due to nonstationary and interdependent data characteristics
Solution Approach 1:
The patent segments the complex high-resolution data interpretation task into manageable components: baseline modeling, deviation detection, and leakage identification. This segmentation reduces interpretation complexity while preserving the benefits of high-resolution measurements.
Solution Approach 2:
The patent applies dynamic modeling techniques to handle the nonstationary and interdependent characteristics of high-resolution sensor data. This dynamic framework provides a structured approach to interpreting complex temporal patterns without requiring overly complex analytical systems.
Data Source
AI summary
The present invention relates to an universal integrated environmental monitoring and management technique for operating underground storage sites of gaseous substances including CO2 capture and storage (CCS) site. According to the present invention, Firstly, a base dataset for observed soil gases and related surrounding environmental variables by a step of configuring/refining procedures. Next, extracting the time varying characteristics of the base dataset using wavelet-based multiresolution state-space modeling, and identifying the driving forces that governing the soil gases dynamics and evaluating their contributions through multiscale time-frequency domain correlation analysis. And finally, predicting and forecasting future scenarios with deep leaning models which intensively trained by the key driving forces. Furthermore, the present invention can provide quantitative based for analyzing the causation between driving forces and observed soil gases. In addition, the present invention can effectively be used to detect early leakage signs and to assess environmental impacts of leakage based on the identification, evaluation, and prediction results.