Seismic Risk Assessment Process Model Using Composite Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer-based modeling technologies are inadequate for accurately assessing seismic risk associated with fluid disposal in the energy infrastructure industry, particularly due to the complexity of geological formations and the variability of fluid injection parameters.
Innovation Solution
A computer-implemented method and system that derive a process model using training input parameters such as true injection depth, formation information, permeability, three-dimensional fault maps, and seismic activity to determine seismic risk, applying machine learning and simulation techniques to optimize the assessment of seismic risk at new locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional computer-based modeling technologies are used for seismic risk assessment, then the assessment process is simple, but the accuracy of seismic risk prediction is insufficient
Solution Approach 1:
The patent applies composite modeling by integrating multiple types of data (seismic activity data, formation data, injection data, fault data) into a unified process model, similar to how composite materials combine different properties to achieve superior performance. This composite approach enables accurate seismic risk assessment by synthesizing diverse geological and operational parameters.
Solution Approach 2:
The patent segments the seismic risk assessment into distinct components: training data collection, process model derivation, and risk prediction. By dividing the complex assessment task into manageable segments, the system achieves high accuracy while maintaining operational simplicity through automated processing of each segment.
2Measurement precision
If comprehensive training data including multiple parameters is used to derive the process model, then the seismic risk assessment accuracy improves, but the data processing time increases
Solution Approach 1:
The patent performs preliminary action by collecting and organizing training data before the actual risk assessment is needed. The process model is derived in advance using comprehensive training data, so that when real-time assessment is required, the pre-derived model can quickly provide accurate predictions without processing time constraints.
Solution Approach 2:
The patent creates a simplified copy of the complex geological system through the process model. This model copy captures the essential relationships between injection parameters and seismic risk, allowing rapid assessment without repeatedly processing the full complexity of the original system.
3Adaptability or versatility
If the system uses multiple input parameters such as injection depth, formation properties, and fault information, then the assessment comprehensiveness improves, but the complexity of data collection and processing increases
Solution Approach 1:
The patent implements a universal process model that handles multiple types of input data (seismic activity, formation properties, injection parameters, fault information) through a single integrated framework. This multi-functional model achieves comprehensive assessment across different geological conditions and injection scenarios without requiring separate processing systems for each data type.
Solution Approach 2:
The patent introduces the process model as an intermediary that mediates between diverse input parameters and the final risk assessment. This intermediary layer standardizes and integrates multiple data sources, simplifying the processing complexity while maintaining comprehensive assessment capabilities.
Data Source
AI summary
Systems and methods for assessing seismic risk. The system and methods disclose deriving a model that is used to assess seismic risk of operations at a given location. A first location is identified for which at least one training seismic risk value is known from independent sources. A plurality of training input parameters associated with the first location is received. The at least one training seismic risk value is received. A process model is derived that relates the plurality of training input parameters to the at least one training seismic risk value by determining influence values of the training input parameters. A second location is identified for which a seismic risk is to be determined. A plurality of working input parameters associated with the second location is received. The process model is applied to the plurality of working input parameters to determine a seismic risk value at the second location.