Abstract: A method for predicting an occurrence of a geological feature in a borehole image log using a backpropagation-enabled process trained by inputting a set of training images (12) of a borehole image log, iteratively computing a prediction of the probability of occurrence of the geological feature for the set of training images and adjusting the parameters in the backpropagation-enabled model until the model is trained. The trained backpropagation-enabled model is used to predict the occurrence of the geological features in non-training borehole image logs. The set of training images may include non- geological features and/or simulated data, including augmented images (22) and synthetic images (24).

Abstract: A method for predicting an occurrence of a geological feature in a geologic core image uses a backpropagation-enabled segmentation process trained by inputting multiple training geologic core images and a set of associated labels of geological features, iteratively computing a prediction of the probability of occurrence of the geological feature for the training images and adjusting the parameters in the backpropagation-enabled segmentation model until the model is trained. The trained backpropagation-enabled segmentation model is used to predict the occurrence of the geological features in non-training geologic core images. Geological features to be predicted with this method include structural features (such as veins, fractures, bedding contacts, etc.), and stratigraphic features (such as lithologic types, sedimentary structures, sedimentary facies, etc.).

Abstract: A distribution of sand sediment class in a subsurface of the Earth is identified. Three-dimensional stratigraphic images of sediment distribution in a subsurface of the Earth are constructed, including at least two depositional domains, by simulating sediment transport and deposition over a selected time interval of sediments originating from one or more clastic sediment input sources. The simulation uses at least two equilibrium surfaces bounding the at least two depositional domains and at least two sediment classes, and updates the equilibrium surfaces in a sequence of timesteps, by accounting for sediment feed from the one or more clastic sediment input sources, erosion and deposition in accordance with mass-balance equality constraints. The images are used to identify a distribution of sand sediment class in the subsurface of the Earth suitable for acquiring hydrocarbons or fresh water, or for storing gas or liquids.

Abstract: A modified direct search Neighborhood Algorithm (NA), similar to genetic or evolutionary algorithms, is used for automatic calibration of Stratigraphic Forward Models (SFM) to data constraints. The modified NA comprises explicit escape clauses from local minima and admissible solutions, thereby preventing a natural tendency of conventional NAs to converge and oversample a single minimum. The density of models in parameter space is used to define local minima. Admissible solutions are defined by considering error thresholds taking into account that SFM may be imperfect and that calibration constraints may be uncertain. The modified NA algorithm obtains a plurality of geological scenarios that agree with the data, and which can be used for further analysis and prediction.

Abstract: A distribution of sand sediment class in a subsurface of the Earth is identified. Three-dimensional stratigraphic images of sediment distribution in a subsurface of the Earth are constructed, including at least two depositional domains, by simulating sediment transport and deposition over a selected time interval of sediments originating from one or more clastic sediment input sources. The simulation uses at least two equilibrium surfaces bounding the at least two depositional domains and at least two sediment classes, and updates the equilibrium surfaces in a sequence of timesteps, by accounting for sediment feed from the one or more clastic sediment input sources, erosion and deposition in accordance with mass-balance equality constraints. The images are used to identify a distribution of sand sediment class in the subsurface of the Earth suitable for acquiring hydrocarbons or fresh water, or for storing gas or liquids.

Abstract: A modified direct search Neighborhood Algorithm (NA), similar to genetic or evolutionary algorithms, is used for automatic calibration of Stratigraphic Forward Models (SFM) to data constraints. The modified NA comprises explicit escape clauses from local minima and admissible solutions, thereby preventing a natural tendency of conventional NAs to converge and oversample a single minimum. The density of models in parameter space is used to define local minima. Admissible solutions are defined by considering error thresholds taking into account that SFM may be imperfect and that calibration constraints may be uncertain. The modified NA algorithm obtains a plurality of geological scenarios that agree with the data, and which can be used for further analysis and prediction.