| CPC G06T 17/05 (2013.01) [G06N 3/045 (2023.01); G06N 3/088 (2013.01)] | 18 Claims |

|
1. A method of geological modeling comprising:
in a training phase, training a generator neural network to map a first combination of a first noise vector and a first category code vector as input to a simulated image of geological facies to obtain a trained generator neural network, conditioning the simulated image of geological facies output by the generator neural network based on field measurement data, and training a discriminator neural network to map at least one image of geological facies provided as input to corresponding probability that the at least one image of geological facies provided as input is a training image of geological facies or a simulated image of geological facies produced by the generator neural network and to obtain a trained discriminator neural network; and
in an online phase, supplying input data comprising a second combination of a second noise vector and a second category code vector to the trained generator neural network to output a simulated image of geological facies, wherein the geological facies are defined by a texture, a minerology, a grain size, a depositional environment, or a combination thereof, and wherein each of the first category code vector and the second category code vector comprises an identification of a type of the depositional environment.
|