Space-time surrogate models of subterranean regions

摘要

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.

主权项

1. A method for causing a computer processor to assist with creating a space-time surrogate model of a subsurface region, the method comprising:
(a) providing non-transitory computer readable instructions to the computer processor to cause the computer processor to generate a surrogate model of a full-physics model of a subsurface region for preselected variables at a first time value within a range of time values within at least a portion of the full-physics model and determining a corresponding surrogate model coefficient for the first time value; (b) repeating step (a) n times for n additional time values that are different than the first time value, wherein n is an integer greater than 1, wherein the first time value and the n additional time values define the range of time values and creates a matrix of surrogate model coefficients over the range of time values; (c) generating a time-varying function related to at least a portion of the matrix of surrogate model coefficients; and (d) thereafter, creating an explicit space-time surrogate model of the at least a portion of the full physics model based on (1)the surrogate models produced by the generating and the repeating and (2) the generated at least one time-varying function, wherein the created explicit space-time surrogate model is parametric for at least the preselected variables and also indicates changes in the preselected variables over at least the range of time values.