Abstract: A method for estimating in-situ porosity based on cutting images employs a neural network trained with labeled images, the labels indicating wireline porosity values. The method may be used to obtain porosity values along a vertical, deviated or horizontal well, where wireline logging data is not available or unreliable. The method uses machine learning. Training and validating the neural network may be ongoing processes in the sense that any new labeled image that becomes available can be added to the training set and the neural network being retrained to enhance its predictive performance.

Abstract: A method for estimating breakdown pressure values along a wellbore starts from analyzing cuttings from locations along the wellbore to determine rock properties, including rock texture information associated with the locations. The anisotropic elastic and mechanical properties at the locations are calculated based on the rock properties and using at least one rock physics model. Rock weakness index values corresponding to the locations are then calculated based on the anisotropic elastic and mechanical properties and the rock texture information. The breakdown pressure values at the locations are estimated from the rock weakness index values.

Abstract: A method for estimating in-situ porosity based on cutting images employs a neural network trained with labeled images, the labels indicating wireline porosity values. The method may be used to obtain porosity values along a vertical, deviated or horizontal well, where wireline logging data is not available or unreliable. The method uses machine learning. Training and validating the neural network may be ongoing processes in the sense that any new labeled image that becomes available can be added to the training set and the neural network being retrained to enhance its predictive performance.

Abstract: A method for estimating breakdown pressure values along a wellbore starts from analyzing cuttings from locations along the wellbore to determine rock properties, including rock texture information associated with the locations. The anisotropic elastic and mechanical properties at the locations are calculated based on the rock properties and using at least one rock physics model. Rock weakness index values corresponding to the locations are then calculated based on the anisotropic elastic and mechanical properties and the rock texture information. The breakdown pressure values at the locations are estimated from the rock weakness index values.

Abstract: Predicting and quantifying free silicon in a geological formation generates free silicon data for a physical sample obtained from within the geological formation. The free silicon data include identification of portions of the physical sample containing free silicon and a quantification of the free silicon contained in the portions of the physical sample containing free silicon. A modified petro-elastic model for the geological formation comprising rock constituents is generated that incorporates free silicon as one of the rock constituents and that quantitatively models how free silicon changes elastic properties within the geological formation. A three-dimensional model of the geological formation is created that indicates volumes of free silicon throughout the geological formation. The three-dimensional model is created using geophysical data obtained from the physical sample, seismic data covering the geological formation and the modified petro-elastic model.

Abstract: Predicting and quantifying free silicon in a geological formation generates free silicon data for a physical sample obtained from within the geological formation. The free silicon data include identification of portions of the physical sample containing free silicon and a quantification of the free silicon contained in the portions of the physical sample containing free silicon. A modified petro-elastic model for the geological formation comprising rock constituents is generated that incorporates free silicon as one of the rock constituents and that quantitatively models how free silicon changes elastic properties within the geological formation. A three-dimensional model of the geological formation is created that indicates volumes of free silicon throughout the geological formation. The three-dimensional model is created using geophysical data obtained from the physical sample, seismic data covering the geological formation and the modified petro-elastic model.

Abstract: Mechanical and elastic rock properties of a subsurface are predicted using actual physical samples from the subsurface as an alternative to wireline data obtained from wells. Geological rock data are generated from a physical geological sample of the subsurface. These geological rock data include elemental data, mineralogical data and textural data for the subsurface. The geological rock data are used in a rock physics model to generate elastic and mechanical rock properties of the subsurface.

Abstract: A method is provided for predicting a value of a designated rock or fluid property in a subterranean geologic volume. A first predicted value of the designated rock or fluid property is also assigned to a volume of a multi-dimensional, multi-scale model. A first predicted value of seismic response for the model volume is calculated from a response model using the first predicted value of the designated rock or fluid property, wherein the response model is responsive to changes in predicted values of the designated rock or fluid property. A synthetic trace is generated and iteratively compared to the corresponding trace obtained from one or more sets of actual seismic data to determine a difference while consistency is maintained between the types, scales and dimensions of values and data.

Abstract: A method is provided for predicting a value of a designated rock or fluid property in a subterranean geologic volume. A first predicted value of the designated rock or fluid property is also assigned to a volume of a multi-dimensional, multi-scale model. A first predicted value of seismic response for the model volume is calculated from a response model using the first predicted value of the designated rock or fluid property, wherein the response model is responsive to changes in predicted values of the designated rock or fluid property. A synthetic trace is generated and iteratively compared to the corresponding trace obtained from one or more sets of actual seismic data to determine a difference while consistency is maintained between the types, scales and dimensions of values and data.