Abstract: System and methods of petrophysical modeling are disclosed. Measurements of formation parameters are received from one or more measurement tools during a first stage of a downhole operation within a reservoir formation. A correlation between each of the formation parameters and a target parameter of the formation is determined based on the measurements. One or more formation parameters are selected as input parameters for a symbolic regression model, based on the correlation. A symbolic regression model is trained to generate candidate formation models representing the target parameter, based on the selected input parameters. One or more optimizations are applied to the candidate models to determine a target petrophysical model of the formation. Values of the target parameter are estimated for at least one formation layer, based on the target petrophysical model. A second stage of the downhole operation is performed within the formation layer(s) based on the estimated values.

Abstract: Systems and techniques are provided for integrating laboratory generated nuclear magnetic resonance (NMR) data and NMR logging data. An example method can include obtaining NMR logging data describing one or more downhole NMR measurements captured during a drilling operation in a borehole; modifying the NMR logging data to be compatible with a temperature correction algorithm, yielding modified NMR logging data, the temperature correction algorithm having been determined based on laboratory generated NMR data; and applying the temperature correction algorithm to the modified NMR logging data, yielding temperature corrected NMR logging data.

Abstract: Noise in drilling operation measurements can be eliminated or reduced using machine learning. For example, a system described herein can receive one or more measured signals in a logging-while-drilling process for drilling a wellbore. The system can determine a coupling factor for noise in the one or more measured signals. The system can generate a corrected signal by removing the noise multiplied by the coupling factor from the one or more measured signals. The system can output the corrected signal for use in drilling operations in the wellbore.

Abstract: A measurement tool may be positioned downhole in a wellbore for measuring formation properties and drilling mud properties during a drilling operation. The measurement tool may include a body and an antenna. The body may include magnets for generating a magnetic field and a transmitter for transmitting a radiofrequency pulse. The antenna may be positioned proximate to the body to measure properties using nuclear magnetic resonant frequencies. The antenna may measure formation properties in a first volume of a formation using a first frequency. The antenna may measure drilling mud properties in a second volume in a borehole using a second frequency.

Abstract: A NMR tool for use in a wellbore in a subterranean region includes a magnet assembly to produce a magnetic field in a volume in the subterranean region; an antenna to produce an excitation in the volume, and to receive a plurality of spin echo waveforms from the volume; and a computing system coupled to the antenna and configured to: apply a first acquisition window having a first duration to the spin echo waveforms to generate a corresponding first echo train including a first plurality of NMR echo signal amplitudes; apply a second acquisition window having a second duration different than the first duration, to at least some of the spin echo waveforms to generate a corresponding second echo train including a second plurality of NMR echo signal amplitudes; and determine a relaxation parameter based on a single inversion of the first and second echo trains.

Abstract: System and methods for nuclear magnetic resonance (NMR) fluid substitution are provided. NMR logging measurements of a reservoir rock formation are acquired. Fluid zones within the reservoir rock formation are identified based on the acquired measurements. The fluid zones include water zones comprising water-saturated rock and at least one oil zone comprising rock saturated with multiphase fluids. Water zones having petrophysical characteristics matching those of the oil zone(s) within the formation are selected. NMR responses to multiphase fluids resulting from a displacement of water by hydrocarbon in the selected water zones are simulated. A synthetic dataset including NMR T2 distributions of multiphase fluids is generated based on the simulation. The synthetic dataset is used to train a machine learning (ML) model to substitute NMR T2 distributions of multiphase fluids with those of water. The trained ML model is applied to the NMR logging measurements acquired for the oil zone(s).

Abstract: System and methods of petrophysical modeling are disclosed. Measurements of formation parameters are received from one or more measurement tools during a first stage of a downhole operation within a reservoir formation. A correlation between each of the formation parameters and a target parameter of the formation is determined based on the measurements. One or more formation parameters are selected as input parameters for a symbolic regression model, based on the correlation. A symbolic regression model is trained to generate candidate formation models representing the target parameter, based on the selected input parameters. One or more optimizations are applied to the candidate models to determine a target petrophysical model of the formation. Values of the target parameter are estimated for at least one formation layer, based on the target petrophysical model. A second stage of the downhole operation is performed within the formation layer(s) based on the estimated values.

Abstract: A method and microfluidic device to perform reservoir simulations using pressure-volume-temperature (“PVT”) analysis of wellbore fluids.

Abstract: System and methods of petrophysical modeling are disclosed. Measurements of formation parameters along a planned path of a wellbore are received during a current stage of a downhole operation. A correlation coefficient between each of the formation parameters and at least one target parameter for the reservoir formation is determined based on the received measurements. Input parameters are selected from among the formation parameters for a symbolic regression model, based on the correlation coefficient calculated for each formation parameter. A symbolic regression model is trained to generate a target petrophysical model, based on the selected input parameters and the corresponding measurements received from the downhole tool. One or more properties of the formation are estimated for a subsequent stage of the downhole operation, based on the generated petrophysical model. The subsequent stage is performed along the wellbore, based on the one or more estimated properties of the reservoir formation.

Abstract: A method includes generating a temperature-corrected nuclear magnetic resonance (NMR) measurement-derived value corresponding to a target temperature using a correlation model that is based on a difference between the target temperature and a sample temperature. The method also includes determining a formation property based on the temperature-corrected NMR measurement-derived value corresponding to the target temperature.

Abstract: A method for measuring a carbon capture and sequestration site. The method may comprise acquiring one or more core samples from a carbon capture and sequestration site, performing a nuclear magnetic resonance (NMR) measurement on the one or more core samples to form a first NMR measurementperforming a surface roughness measurement on the one or more core samples to determine a Rs,before wherein the Rs,before is a surface roughness of the one or more core samples before the one or more core samples are aged in a cell, and determining at least one property of the one or more core samples from at least the first NMR measurement and the Rs,before.

Abstract: System and methods for nuclear magnetic resonance (NMR) fluid substitution are provided. NMR logging measurements of a reservoir rock formation are acquired. Fluid zones within the reservoir rock formation are identified based on the acquired measurements. The fluid zones include water zones comprising water-saturated rock and at least one oil zone comprising rock saturated with multiphase fluids. Water zones having petrophysical characteristics matching those of the oil zone(s) within the formation are selected. NMR responses to multiphase fluids resulting from a displacement of water by hydrocarbon in the selected water zones are simulated. A synthetic dataset including NMR T2 distributions of multiphase fluids is generated based on the simulation. The synthetic dataset is used to train a machine learning (ML) model to substitute NMR T2 distributions of multiphase fluids with those of water. The trained ML model is applied to the NMR logging measurements acquired for the oil zone(s).

Abstract: A method and microfluidic device to perform reservoir simulations using pressure-volume-temperature (“PVT”) analysis of wellbore fluids.

Abstract: An NMR based wettability index determination method for CO2-liquid-solid system for CO2 and liquid phase wettability assessment may comprise acquiring 1H NMR relaxation time measurements, analyzing brine signals for the comparable brine-filled pores from various step, applying a wettability index model constructed with NMR alone and calibrated with another wettability measurement, and applying the wettability index model to interpret wettability of CO2-containing rock system from corresponding NMR measurements.

Abstract: A method for training a model. The method may include forming a data set from one or more measurements of core samples, selecting one or more parameters from the data set, inputting the one or more parameters into a kernel estimation function, determining a kernel density estimation from the kernel estimation function based at least in part on the one or more parameters, and selecting an input value based at least in part on the kernel density estimation. The method may further include creating a corresponding synthetic target value based at least in part on the input value, augmenting the data set with the corresponding synthetic target value and input value to form a synthetic data set, and training a petrophysical interpretation machine learning model from the data set and the synthetic data set.

Abstract: A measurement tool may be positioned downhole in a wellbore for measuring formation properties and drilling mud properties during a drilling operation. The measurement tool may include a body and an antenna. The body may include magnets for generating a magnetic field and a transmitter for transmitting a radiofrequency pulse. The antenna may be positioned proximate to the body to measure properties using nuclear magnetic resonant frequencies. The antenna may measure formation properties in a first volume of a formation using a first frequency. The antenna may measure drilling mud properties in a second volume in a borehole using a second frequency.

Abstract: Methods for correcting a gradient distribution in downhole NMR logging are described herein. NMR data is inverted using an effective gradient to obtain an apparent T2 distribution having a first main peak and a distortion caused by a second spurious peak. The first main peak corresponds to the effective gradient. The distortion in the apparent T2 distribution is then corrected by integrating the signal corresponding to the spurious peak into the signal corresponding to the main peak. The corrected apparent T2 distribution and the effective gradient are then used to interpret the NMR data. Thereafter, the interpreted data is used to determine one or more characteristics of the surrounding subsurface rock formation media.

Abstract: A fluid extraction tool can include a body, a sealing pad extending from a portion of the elongated body, a container holding a selective permeability agent (SPA), and a device. The sealing pad can have an opening for establishing fluidic communication between an earth formation and the elongated body, an outer surface to hydraulically seal a region along an inner surface of a wellbore and a recess within the sealing pad establishing a fluid flow channel along the inner surface of the wellbore. The device can inject the SPA through an outlet of the body into the earth formation, and extract a formation fluid through the opening, wherein the formation fluid being collected is from the region along the inner surface of the wellbore sealed off by the sealing pad.

Abstract: System and methods for image gap-filling are provided. An image of a rock formation is obtained from an imaging tool disposed within a borehole. The obtained image is analyzed to identify gaps of missing image data. One or more image masks corresponding to the identified gaps are generated. A machine learning model is trained to produce modeled image data for filling in the missing image data in the identified gaps, based on the generated image mask(s). The image is reconstructed by filling the gaps of missing image data with the modeled image data. The reconstructed image is analyzed to identify geological features of the rock formation.

Abstract: To separate porosity from surface roughness, length scales for pore size and surface roughness are identified. These length scales are determined from surface roughness measurements and confirmed via NMR pore body calculations and pore size capillary pressure measurements. A filter removes pore contribution to surface roughness measurements and delivers intrinsic surface roughness. Additional filters and methods determine the minimum magnification on which to base surface roughness calculation, based on size of the field of view and where measured surface roughness approaches intrinsic surface roughness as magnification increases but larger magnification increase sampling time and difficulty. Sample irregularities, such as saw marks, are also filtered out or determined to be too large to remove via filter and another area of measurement is located. With the pore corrected quantification of surface roughness, surface relaxivity and pore distribution can be calculated with greater accuracy.