Abstract: Processes for characterizing reservoir formation parameters such as water salinity and water saturation. In some embodiments, the process can include directing a heat impulse into a formation sample that can include a matrix component and a fluid component at an input location. The heat impulse can be allowed to pass through the formation sample such that a matrix impulse forms through the matrix component and a fluid impulse forms through the fluid component. The matrix and fluid impulses can convolve at a measurement location to provide a convolved impulse. A derivative analysis of the convolved impulse can be performed to derive thermal transient measurements. A fluid thermal model can be developed using the thermal transient measurements. The fluid thermal model can be integrated with one or more downhole logs and/or input parameters to create an integrated model. One or more reservoir parameters can be determined from the integrated model.

Abstract: Systems and methods are configured to receive one or more photographs depicting a plurality of cuttings, to identify one or more individual cuttings of the plurality of cuttings depicted in the one or more photographs, to extract morphological, color, texture, grain size, and grain distribution data from each individual cutting of the one or more individual cuttings, to perform lithological classification of the one or more individual cuttings at a plurality of hierarchical levels based at least in part on the extracted morphological, color, texture, grain size, and grain distribution data or based at least in part on features directly extracted from the one or more individual cuttings that represent the morphological, color, texture, grain size, and grain distribution data, and to present a consolidated results summary of the lithological classification of the one or more individual cuttings at the plurality of hierarchical levels via the analysis and control system.

Abstract: Systems and methods are provided to analyze rock cuttings and measure physical lithological features of the rock cuttings. An image analysis workflow is provided, which includes multiple computational modules to automatically estimate relevant geological information from rock cuttings. Reference data, manual descriptions, and well log values are associated and used to determine rock properties of the rock cuttings. A software is developed for the image analysis, and results are displayed in various views.

Abstract: Systems are provided for capturing carbon dioxide that includes a water source supplying a flow of source water, a gas source supplying a flow of source gas, a carbonation chamber, sensors, and a controller. The chamber has a first inlet fluidly coupled to the water source by a first valve, a second inlet fluidly coupled to the gas source by a second valve, and an outlet. The sensors measure fluid properties for i) source water that flows into the chamber, ii) fluid within the chamber, and iii) fluid that exits the chamber. The controller is configured to automatically control the first and second valves based on evaluation of time-series data representing the measured fluid properties to provide flows of the source water and the source gas into the chamber that produces a continuous carbonation reaction in the chamber concurrent with fluid outflow from the chamber.

Abstract: Systems and methods presented herein are configured to train a neural network model using a first set of photographs, wherein each photograph of the first set of photographs depicts a first set of objects and include one or more annotations relating to each object of the first set of objects; to automatically create mask images corresponding to a second set of objects depicted by a second set of photographs; to enable manual fine tuning of the mask images; to re-train the neural network model using the second set of photographs, wherein the re-training is based at least in part on the manual fine tuning of the mask images; and to identify one or more individual objects in a third set of photographs using the re-trained neural network model.

Abstract: Methods and systems are provided for predicting thermal properties of a subsurface rock formation. A training dataset is derived from petrophysical properties of a plurality of formation rock samples and thermal properties of the plurality of formation rock samples. The training dataset is used to train a machine learning model that predicts label data representing the predefined set of thermal properties given input data representing the predefined set of petrophysical properties of an arbitrary formation rock sample. The machine learning model can be validated and deployed for use in predicting thermal properties of subsurface rock formations.

Abstract: Digital image processing a digital image of sample drill cuttings retrieved from a geological formation and related methods include identifying individual zones in the image that depict at least a predetermined minimum heterogeneity of a first physical property, extracting particles in each identified zone that depict a second physical property within a predetermined quantitative range, and measuring a third physical property of each extracted particle. The first physical property may be texture, size, color, or spectral response within the zone. The second physical property may be brightness, color, contrast, hue, saturation, or wavelet energy. The third physical property may be size or color.

Abstract: Systems and methods presented herein generally relate to measuring physical lithological features based on calibrated photographs of cuttings and, more specifically, to the analysis of individual cuttings that are identified in the calibrated photographs of the cuttings.

Abstract: Systems and methods presented herein are configured to train a neural network model using a first set of photographs, wherein each photograph of the first set of photographs depicts a first set of objects and include one or more annotations relating to each object of the first set of objects; to automatically create mask images corresponding to a second set of objects depicted by a second set of photographs; to enable manual fine tuning of the mask images corresponding to the second set of objects depicted by the second set of photographs; to re-train the neural network model using the second set of photographs, wherein the re-training is based at least in part on the manual fine tuning of the mask images corresponding to the second set of objects depicted by the second set of photographs; and to identify one or more individual objects in a third set of photographs using the re-trained neural network model.

Abstract: Well log data may be used in well log operations by facilitating the identification of hydrogen carbon deposits. More specifically, the well log data may be used to generate visual representations. Aspects of the present disclosure relate to generating a color composite image based on multiple types of well log data and transforming the well log data into a color space. In further embodiments, the color composite image may be modified and/or objects within the color composite image may be identified.

Abstract: Well log data may be used in well log operations by facilitating the identification of hydrogen carbon deposits. More specifically, the well log data may be used to generate visual representations. Aspects of the present disclosure relate to generating a color composite image based on multiple types of well log data and transforming the well log data into a color space. In further embodiments, the color composite image may be modified and/or objects within the color composite image may be identified.