Landmark Graphics Corporation

Marc Paul Servais

Graham Baines

Olutobi Adeyemi

Zainab Diana Titus

Christine Yallup

Annabel Causer

A method for performing wellbore correlation across multiple wellbores includes predicting a depth alignment across the wellbores based on a geological feature of the wellbores. Predicting a depth alignment includes selecting a reference wellbore, defining a control point in a reference signal of a reference well log for the reference wellbore, and generating an input tile from the reference signal, the control points, and a number of non-reference well logs corresponding to non-reference wellbores. The well logs include changes in a geological feature over a depth of a wellbore. The input tile is input into a machine-learning model to output a corresponding control point for each non-reference well log. The corresponding control point corresponds to the control point of the reference log. Based on the corresponding control points output from the machine-learning model, the non-reference well logs are aligned with the reference well log to correlate the multiple wellbores.

Supervised machine learning-based wellbore correlation

A heat flow modeler preprocesses geological and heat flow data for an earth formation for inputting into a plurality of supervised learning models. The heat flow modeler trains the plurality of supervised learning models on the preprocessed geological data to estimate heat flow throughout the earth formation. The heat flow modeler interpolates the estimated heat flow values to a set of desired locations in the earth formation and cosimulates the preprocessed heat flow values with the interpolated heat flow values as auxiliary variables to generate a cosimulated heat flow map. A final heat flow map is generated by rasterizing the cosimulated heat flow map.

Estimation of global thermal conditions via cosimulation of machine learning outputs and observed data

A method for correlating data comprises acquiring a first sequence signal and a second sequence signal, wherein the first sequence signal comprises at least a first data point including a first set of components and the second sequence signal comprises at least a second data point including a second set of components; acquiring a first set of user picks and a second set of user picks, wherein the first and the second sets of user picks each contain a respective first and second correspondence between a component in the first set of components and a component in the second set of components; combining the first and second sets of user picks with the first and second sequence signals to create a first hyper-complex signal and a second hyper-complex signal; and performing signal alignment on the first and second hyper-complex signals.

Dynamic time warping of signals plus user picks

A method for correlating data includes acquiring a first sequence of data and a second sequence of data, wherein the first sequence of data comprises at least a first data point including a first set of signal components and the second sequence of data comprises at least a second data point including a second set of signal components, wherein the signal components in the first and second sets of signal components contain valid data, nulls, or a combination thereof; identifying one or more nulls in at least one of the first set of signal components or the second set of signal components; defining a difference between the one or more nulls and a component value as a real value; and calculating a distance between the first data point and the second data point based on the difference between the one or more nulls and the component value.

Growing community of inventors

Reading, United Kingdom

Marc Paul Servais