Space-Time Surrogate Models for Subsurface Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional surrogate models for subterranean regions are limited to a single response at a specific time, making them less accurate and less useful for modeling complex spatial and temporal behavior, and require frequent updating as computational capabilities and knowledge evolve.
Innovation Solution
The development of space-time surrogate models that are parametric with respect to design, space, and state variables, allowing them to reflect responsiveness over time, enabling more versatile and accurate predictions across varying conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional surrogate models are used for subterranean regions, then model simplicity and ease of use are improved, but modeling accuracy and ability to capture complex spatial-temporal behavior deteriorate
Solution Approach 1:
The surrogate model is transformed from a static representation to a dynamic one by incorporating time as an explicit dimension. The model uses time-varying parameters and dynamic update mechanisms to capture evolving subsurface conditions, allowing it to adapt to changing spatial-temporal behaviors while maintaining computational efficiency and ease of use.
Solution Approach 2:
The model transitions from conventional spatial-only representation to a space-time continuum by adding the temporal dimension. This dimensional expansion enables the model to capture complex spatial-temporal behaviors through multi-dimensional parameter relationships, improving accuracy without sacrificing the surrogate model's inherent simplicity and ease of operation.
2Productivity
If conventional surrogate models are used, then computational efficiency is improved, but ability to reflect responsiveness over time deteriorates
Solution Approach 1:
The surrogate model incorporates dynamic time-varying parameters that automatically adjust to reflect subsurface responsiveness over time. This dynamic structure allows the model to capture temporal evolution of geological processes while maintaining the computational efficiency characteristic of surrogate models, avoiding the need for repeated full-physics simulations.
Solution Approach 2:
The model utilizes parameter changes over time as a core mechanism, where key subsurface parameters are represented as time-dependent functions. This approach enables the model to reflect temporal responsiveness by tracking parameter evolution, achieving adaptability to time-varying conditions while preserving computational efficiency through the surrogate modeling framework.
3Measurement precision
If frequent model updates are conducted to improve accuracy, then modeling precision is improved, but time consumption and resource demands increase
Solution Approach 1:
The surrogate model is pre-configured with time-varying parameter structures and update mechanisms during the modeling setup phase. This preliminary action enables the model to automatically adapt to temporal changes without requiring frequent manual updates, reducing time consumption while maintaining modeling precision through built-in temporal evolution capabilities.
Solution Approach 2:
The model incorporates self-updating mechanisms that automatically adjust parameters based on time progression and observed subsurface responses. This self-service capability reduces the need for manual model updates, minimizing time consumption and resource demands while maintaining high modeling precision through continuous temporal adaptation.
Data Source
AI summary
Methods for creating and using space-time surrogate models of subsurface regions, such as subsurface regions containing at least one hydrocarbon formation. The created surrogate models are explicit models that may be created from implicit models, such as computationally intensive full-physics models. The space-time surrogate models are parametric with respect to preselected variables, such as space, state, and/or design variables, while also indicating responsiveness of the preselected variables with respect to time. In some embodiments, the space-time surrogate model may be parametric with respect to preselected variables as well as to time. Methods for updating and evolving models of subsurface regions are also disclosed.