Landmark Graphics Corporation

Total Se

Jiazuo Zhang

Graham Baines

Gavin Henry Graham

According to some aspects, machine-learning models can be executed to classify a subsurface rock. Examples include training numerous machine-learning models using training data sets with different probability distributions, and then selecting a model to execute on a test data set. The selection of the model may be based on the similarity of each data point of the test data set and the probability distribution of each training class. Examples include detecting and recommending a pre-trained model to generate outputs predicting a classification, such as a lithology, of a test data set. Recommending the trained model may be based on calculated prior probabilities that measure the similarity between the training and test data sets. The model with a training data set that is most similar to the test data set can be recommended for classifying a physical property of the subsurface rock for hydrocarbon formation.

Probability distribution assessment for classifying subterranean formations using machine learning

Disclosed embodiments include methods and systems for classifying test data. In one embodiment a method includes determining one or more variable types in a multivariate test vector within a data set, and for a plurality of machine-learning models, determining a closest match between variable types used by (to train) the machine-learning models and the determined variable types for the test vector. In response to determining a closest match for one machine-learning model, a corresponding machine-learning model is selected and the test vector is classified using the selected model. In response to determining a closest match for multiple machine-learning models, a similarity is determined between a probability distribution for the test data set and the probability distributions for the multiple machine-learning models to generate similarity values for each of the models. In response to one of the similarity values exceeding a threshold value, a machine-learning model is selected that corresponds to the exceeding similarity value and the test vector is classified using the selected model.

Classifying downhole test data

Disclosed is a method of conditioning one or more parametric models. The method comprises obtaining a plurality of candidate parametric models, each describing a sequence of domains characterising a subsurface region and determining whether each sequence of domains described by one or more of said candidate parametric models is a valid sequence of domains. For each valid sequence of domains, each candidate parametric model describing that valid sequence of domains (or a subset of these models) is conditioned simultaneously, for example by using an Ensemble Kalman Filter or artificial neural network.

Growing community of inventors

London, United Kingdom

Jiazuo Zhang