Abstract: A method may include obtaining a petrographic image. The method may further include determining various region proposals based on the petrographic image and a selective searching function. A respective region proposal among the region proposals may correspond to various pixels in the petrographic image according to a predetermined dimension. The method may further include determining color histogram data for the petrographic image. The method may further include determining input image data based on the petrographic image, the region proposals, and the color histogram data. The method may further include determining a rock object using the input image data and a machine-learning model.

Abstract: A method for remediating fractures in a cement structure including heating the cement structure to a temperature at or above the melting temperature of the eutectic metal alloy particles to allow the particles to flow in liquid state into the fractures in the cement structure until the heat source is discontinued, allowing the particles to cool and solidify.

Abstract: A method of estimating dissolution progress of a salt in construction of a salt cavern includes: defining, for each of a plurality of parameters, an operable range of respective parameter and an average value of the operable range of respective parameter; performing a plurality of flooding tests, by varying one particular parameter among the plurality of parameters from a lowest value to a highest value in the operable range of the one particular parameter and keeping all other parameters at the average value of respective parameter; and obtaining an analytical relationship of a mass of dissolved salt versus the one particular parameter.

Abstract: A method and a system for generating a labeled benchmark dataset are disclosed. The method includes obtaining a plurality of sources related to a thin section using web scraping and extracting a plurality of images from the plurality of sources related to the thin section, the plurality of images including a plurality of thin section images and a plurality of non-thin section images. Further, the method includes determining the plurality of thin section images from the plurality of extracted images and generating a classification of the plurality of thin section images based on a given classification criteria. The geological thin-section based machine learning models is trained based on the generated classification of the plurality of thin section images and a wellbore drilling plan is generated based on the geological thin-section based machine learning models.

Abstract: A method for evaluating and controlling a washout region of a wellbore placed in a formation includes: obtaining information about the wellbore and the formation; establishing a washout indicator function as a function of time and location; computationally determining whether the washout region exists by calculating the washout indicator function on a cross section of the wellbore and the formation, at each depth in a specific depth range; and upon finding presence of the washout region in the specific depth range, quantifying the washout region. The washout indicator function returns: a negative value for a point within the formation; a positive value for a point within the washout region; and zero for a point on a boundary.

Abstract: A method for analyzing rock cores of a subterranean formation is disclosed. The method includes capturing low resolution core images of the rock cores, selecting, by a computer processor and based on a pre-determined quality threshold for qualifying the low resolution core images, a number of qualified rock cores, capturing high resolution core images of the qualified rock cores, generating, by the computer processor and based on a high resolution core image evaluation model, a ranking of the qualified rock cores, and analyzing, based at least on the ranking, the qualified rock cores to generate a core analysis result.

Abstract: A fluid composition including a mixed metal oxide viscosifier, a clay viscosifier, and solid eutectic metal alloy particles. A method including pumping a drilling fluid downhole in a wellbore. The drilling fluid including water, a mixed metal oxide viscosifier, a clay viscosifier, and solid eutectic metal alloy particles. The method further including allowing the drilling fluid to reach a target zone with elevated permeability and forming a filter cake containing solid eutectic metal alloy particles in the target zone. The method including heating the filter cake to a temperature greater than the melting temperature of the eutectic metal alloy particles, allowing the particles to melt and become liquid eutectic metal alloy particles. The method including discontinuing heating and allowing the filter cake to cool to a temperature lower than the melting temperature of the solid eutectic metal alloy particles to produce a strengthened filter cake.

Abstract: A method to perform a field operation of an unconventional reservoir is disclosed. The method includes selecting, from rock samples and based on test reports of corresponding companion rock samples, selected rock samples representing rock characteristics of formation zones in the unconventional reservoir, performing, using a rock sample test apparatus, a sequence of rock sample test cycles on each selected rock sample to generate rock sample test results, generating, based on the rock sample test results, a ranking of the selected rock samples representing enhanced oil recovery (EOR) potential of the formation zones, selecting, from the formation zones and based on the ranking, a target formation zone having an EOR potential meeting a pre-determined criterion, and performing, based at least on the EOR potential of the target formation zone, the field production of the unconventional reservoir.

Abstract: An untethered device includes a tool and a ballast weight. The ballast weight includes an attachment plate that is securable to the tool, a dissolvable ballast, and attachment elements that secure the dissolvable ballast to the attachment plate. At least one of the attachment elements is dissolvable to release the dissolvable ballast from the attachment plate.

Abstract: Method and systems for generating a reservoir simulation grid for a subterranean reservoir are disclosed. The method may include, using a reservoir simulation system, to obtain a reservoir model, where the reservoir model comprises a plurality of wellbore trajectories, define a coarse simulation grid pertaining to, at least a portion, of the reservoir model, and determine a grid refinement field based, at least in part, on the reservoir model. The method may further include, using a reservoir simulation system, to form a tree based on the coarse simulation grid, refine the tree at least in part, on an intersection of the grid refinement field and the coarse simulation grid, and define the reservoir simulation grid based, at least in part, on the refined tree and the coarse simulation grid.

Abstract: Methods and systems include obtaining a correlation and obtaining a salt sample from a salt formation. The methods and systems further include, for each of N cycles, exposing, using an injection system, the salt sample to an nth amount of a gas and determining an nth value of a property by subjecting the salt sample, using an atomic force microscopy (AFM) system, to an AFM test. The methods and systems further include determining a relationship using the N values of the property, determining, using the correlation, a macroscale relationship based on the relationship, and generating a fit constitutive model by fitting the constitutive model to the macroscale relationship. The methods and systems include generating a model of a salt cavern within the salt formation based on the fit constitutive model and designing a salt cavern for withdrawal cycles of the gas using the model.

Abstract: Systems and methods for automatic well log normalization are disclosed. The methods include acquiring a target log in a target well and a reference log in a reference well; identifying a stratigraphic interval in the target well and in the reference well; projecting the target log from the target well onto a pseudo target log in a pseudo target well and projecting the reference log from the reference well onto a pseudo reference log in a pseudo reference well; identifying lithologies from a first histogram of the pseudo target log and a second histogram of the pseudo reference log; determining, using the first histogram and the second histogram a regression relationship between the pseudo target log and the pseudo reference log; applying the regression relationship to the pseudo target log to generate a normalized pseudo target log; and determining a reservoir quality of the reservoir that produces hydrocarbons.

Abstract: Methods and systems are disclosed. The methods may include obtaining vertical seismic profile (VSP) data and a seismic velocity model for a subterranean region of interest and determining, using the seismic velocity model and reverse time migration, a pre-stacked migrated seismic image based on the VSP data. The pre-stacked migrated seismic image includes seismic slices. The methods may further include, for each of the seismic slices in turn, determining a coherency map, determining a weighting map based on the coherency map, and determining a corrected seismic slice by applying the weighting map to each of the seismic slices. The methods may still further include determining a post-stacked corrected migrated seismic image based on the corrected seismic slices and determining a location of a geological feature within the subterranean region of interest based, at least in part, on the post-stacked corrected migrated seismic image.

Abstract: A method for determining drilling fluid properties. The method includes obtaining current drilling fluid properties for a drilling fluid used in a drilling operation, obtaining operational parameters related to the drilling operation, and obtaining a treatment, wherein the treatment describes one or more additives or processes to be applied the drilling fluid. The method further includes processing the current drilling fluid properties, the operational parameters, and the treatment with a treatment prediction system to determine a prediction for drilling fluid properties after treatment. The method further includes applying the treatment to the drilling fluid and using the drilling fluid, after application of the treatment, in the drilling operation.

Abstract: A method of preparing an enhanced oil recovery composition is described. The method includes carbonizing a biomass waste material to provide carbon microparticles. The method includes functionalizing the carbon microparticles through an acid treatment such that the carbon microparticles have a hydrophilic surface. The method further includes grinding the carbon microparticles to provide carbon nanoparticles, where the carbon nanoparticles have a hydrophilic surface and a hydrophobic surface. A method of enhanced oil recovery is also described.

Abstract: A method for selecting lost circulation materials (LCM) for boring a well involves determining, for a multitude of LCM blends, a multitude of overall scores based on characteristics associated with each of the multitude of LCM blends, and establishing a list of LCM blend candidates. Establishing the list of LCM blend candidates involves including a first of the multitude of LCM blends in a list of LCM blend candidates based on a first overall score associated with the first LCM blend, and excluding a second of the multitude of LCM blends from the list of LCM blend candidates, based on a second overall score associated with the second LCM blend. The first overall score is greater than the second overall score.

Abstract: Methods and systems for training a machine learning (ML) network to predict a likelihood of a presence of a geological fracture from an observed drill-bit seismic dataset are disclosed. The method may include obtaining, using a seismic processing system, a plurality of geophysical models, where each geophysical model includes a location of a drill bit. The method may further include simulating, for each geophysical model a corresponding simulated drill-bit seismic dataset for seismic waves emanating from the drill bit and recorded by at least one seismic receiver and forming a training dataset including a plurality of training pairs, with each training pair including a geophysical model from the plurality of geophysical models and the corresponding simulated drill-bit seismic dataset. The method may still further include training, using the training dataset, the ML network to predict the likelihood of the presence of the geological fracture from the observed drill-bit seismic dataset.

Abstract: A computer-implemented method for determining near-wellbore stress and state in a drilled well includes: importing input data of a form of data files; calculating stress and pressure parameters along a wellbore path from the input data imported; displaying one or more of the input data and the calculated stress and pressure parameters along a well path of the drilled well; receiving, by a graphical user interface (GUI), a user selection of a depth at which distribution of the near-wellbore stress and state around a wellbore is determined; in response to receiving the user selection, calculating near-wellbore parameters describing the near-wellbore stress and state around the wellbore; and displaying, by the GUI, the calculated near-wellbore parameters around the wellbore.

Abstract: A system for enhancing traveltime information in a seismic dataset and determining a velocity model. The system includes a first initial velocity model, a forward modelling procedure, a machine-learned model, a drilling system with a wellbore planning system, and a computer. The computer is configured to: receive a non-synthetic seismic data set for a subsurface region of interest; perturb the first initial velocity model forming a first plurality of velocity models; simulate, with the forward modelling procedure, a first plurality of seismic data sets; form a first plurality of transformed seismic data sets with enhanced traveltime; train the machine-learned model using the first plurality of velocity models and the first plurality of transformed seismic data sets; transform the non-synthetic seismic data set to a non-synthetic transformed seismic data set; and process the non-synthetic seismic data set with the trained machine-learned model to predict a velocity model for the subsurface region.

Abstract: A hydrogen-diesel dual-fuel engine that includes an engine block, where the engine block includes a cylinder outfitted with at least two hydrogen fuel injectors and a piston. The engine further includes an air-handling system that includes an intake manifold, an intake pipe, an exhaust pipe, a variable geometry turbocharger, and an exhaust gas recirculation system configured to recirculate exhaust gases from the exhaust pipe to the intake manifold. The engine further includes a two-step camshaft, where the two-step camshaft is configured with the air-handling system for exhaust re-breathing and late intake valve closing, and a port fuel injector system that provides hydrogen gas to the at least two hydrogen fuel injectors. The engine further includes a diesel injector, a common-rail fuel injection system, a plurality of sensors, and a controller configured to receive engine data from the plurality of sensors and to control operation of the hydrogen-diesel dual-fuel engine.