Abstract: A method is described for property estimation including receiving a seismic dataset representative of a subsurface volume of interest and a well log from a well location within the subsurface volume of interest; identifying seismic traces in the seismic dataset that correspond to the well location to obtain a subset of seismic traces; windowing the subset of seismic traces and the well log to generate windowed seismic traces and a windowed well log; multiplying the windowed seismic traces and the windowed well log by a random matrix to generate a plurality of training datasets; and training a neural network using the plurality of training datasets. The method may be executed by a computer system.

Abstract: A method is described for estimating hydrocarbon reservoir attributes including obtaining a geophysical dataset and a geological dataset; obtaining a parameter model, the parameter model having been conditioned by training an initial parameter model using training data, wherein the geological data includes well data and the training data includes the well data; picking a surface in the geophysical dataset; assigning stratigraphic meaning to the at least one surface based on the geological dataset; identifying at least one region of interest on the at least one surface; generating statistical seismic attributes for the at least one region; identifying critical attributes among the statistical seismic attributes by applying the parameter model to generate response variable maps for the at least one region; and generating uncertainty maps for each of the critical attributes and for the response variables. The method may be executed by a computer system.

Abstract: A method is described for estimating hydrocarbon reservoir attributes including obtaining a geophysical dataset and a geological dataset; obtaining a parameter model, the parameter model having been conditioned by training an initial parameter model using training data, wherein the geological data includes well data and the training data includes the well data; picking a surface in the geophysical dataset; assigning stratigraphic meaning to the at least one surface based on the geological dataset; identifying at least one region of interest on the at least one surface; generating statistical seismic attributes for the at least one region; identifying critical attributes among the statistical seismic attributes by applying the parameter model to generate response variable maps for the at least one region; and generating uncertainty maps for each of the critical attributes and for the response variables. The method may be executed by a computer system.

Abstract: A method is described for property estimation including receiving a seismic dataset representative of a subsurface volume of interest and a well log from a well location within the subsurface volume of interest; identifying seismic traces in the seismic dataset that correspond to the well location to obtain a subset of seismic traces; windowing the subset of seismic traces and the well log to generate windowed seismic traces and a windowed well log; multiplying the windowed seismic traces and the windowed well log by a random matrix to generate a plurality of training datasets; and training a neural network using the plurality of training datasets. The method may be executed by a computer system.