| CPC E21B 47/04 (2013.01) [G01V 1/345 (2013.01); G06N 20/00 (2019.01); E21B 2200/22 (2020.05); G01V 2210/74 (2013.01)] | 20 Claims |
|
1. A computer-implemented method for training a depth uncertainty model to generate depth uncertainty values as a function of position in a subsurface volume of interest, the method being implemented in a computer system that comprises a physical computer processor and non-transient storage medium, the method comprising:
obtaining an initial depth uncertainty model from the non-transient storage medium;
obtaining training depth uncertainty parameter values from the non-transient storage medium, wherein the training depth uncertainty parameter values are derived from subsurface data, wherein the depth uncertainty parameter values comprise image quality, depth below mud line, subsalt, and overburden complexity;
obtaining corresponding training depth uncertainty values from the non-transient storage medium, wherein the training depth uncertainty values correspond to the training depth uncertainty parameter values, and wherein a first training depth uncertainty value specifies a first training uncertainty corresponding to a first training depth value;
generating, with the physical computer processor, a trained depth uncertainty model by training the initial depth uncertainty model using the training depth uncertainty parameter values and the corresponding training depth uncertainty values;
generating, with the physical computer processor, a representation of depth uncertainty as a function of position in the subsurface volume of interest using a heat map of the subsurface volume of interest to depict at least a portion of the training depth uncertainty values; and
displaying the representation on the display.
|