Abstract: A method and system for identifying one or more petrophysical properties in a formation. The method and system may include disposing a pulsed-neutron logging tool into a borehole that is disposed in a formation, emitting a neutron from a neutron source on the pulsed-neutron logging tool into the formation, and capturing one or more gammas expelled from formation in response to the neutron from the neutron source to form a plurality of pulsed neutron logging (PNL) measurements in a log. The method and system may further include comparing the log to a database with a cost function to form a solution; and identifying a plurality of petrophysical properties based at least in part on the solution.

Abstract: The techniques as described herein enhance the accuracy and precision of mineralogy analysis in elemental spectroscopy logging by utilizing oxide standards and/or rock-forming mineral compounds as reference materials that provide more representative and realistic signatures of geological formations. A method comprises logging a wellbore with a tool and fitting reference spectra from oxide compounds and/or rock-forming mineral compounds against measured gamma spectra obtained with the tool, to characterize a subterranean formation that the wellbore extends through.

Abstract: In some implementations, a method for controlling a learning machine to predict fluid holdup in a borehole comprises generating an expanded dataset of simulated pulsed neutron logging (PNL) data based, at least in part, on an original dataset of empirical PNL data, converting, using one or more calibration coefficients, the simulated PNL data into lab-equivalent synthetic data, and training an ensemble of machine learning models based on the lab-equivalent synthetic data.

Abstract: The techniques as described herein result in a single set of intrinsic carbon-oxygen (CO) measurements that can be used for various borehole and formation saturation conditions, enhancing the reliability and robustness of formation evaluation in oil and gas wells. A method comprises formulating an intrinsic CO ratio for a subterranean formation, based on theoretical atomic concentrations of carbon and oxygen, and porosity and fluid saturation parameters.

Abstract: Aspects of the subject technology relate to performing gamma spectral analysis based on machine learning. Gamma spectrum data, which can be associated with a gamma spectrum can be gathered. The gamma spectrum data can include an energy channel and a count rate for gamma rays detected by one or more gamma detectors. A spectral image can be constructed based on the gamma spectrum data. One or more machine learning models can be trained based on the spectral image. Additionally, one or more features of the gamma spectrum can be extracted from the spectral image through the one or more machine learning models.

Abstract: Aspects of the subject technology relate to determining holdup compensated formation saturation while refraining from calculating holdup. Inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore can be accessed. Further, capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore can be accessed. A model that accounts for holdup measurement can be applied to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums.

Abstract: Aspects of the subject technology relate to determining a holdup measurement based on a gamma spectrum through machine learning. A spectral image based on a gamma spectrum generated downhole in a wellbore can be accessed. A component of a holdup measurement for the wellbore can be classified into a specific quantized level through application of a machine learning classification model to the spectral image. A continuous value for the component of the holdup measurement for the wellbore can be quantified by applying a machine learning quantization model associated with the quantized level.

Abstract: A method and system for identifying formation porosity and formation lithology. The method may include disposing a PNL tool into a borehole that is disposed in a formation, emitting a neutron from a neutron source on the PNL tool into the formation, and capturing one or more gammas expelled from formation in response to the neutron from the neutron source to form a plurality of pulsed neutron logging (PNL) measurements in a log. The method may further include identifying a formation porosity and a formation lithology with an artificial neural network that at least partially incorporates the PNL measurements.

Abstract: A method and system for identifying one or more petrophysical properties in a formation. The method and system may include disposing a pulsed-neutron logging tool into a borehole that is disposed in a formation, emitting a neutron from a neutron source on the pulsed-neutron logging tool into the formation, and capturing one or more gammas expelled from formation in response to the neutron from the neutron source to form a plurality of pulsed neutron logging (PNL) measurements in a log. The method and system may further include comparing the log to a database with a cost function to form a solution; and identifying a plurality of petrophysical properties based at least in part on the solution.

Abstract: In some embodiments, a method includes emitting, from a transmitter positioned in a wellbore formed in a subsurface formation, a pulse of neutrons into the subsurface formation and detecting gamma ray emissions at a near field and a far field generated in response to the pulse of neutrons being emitted into the subsurface formation. The method includes determining a single elemental decay for one chemical element of a number of chemical elements present in the subsurface formation based on the gamma ray emissions and determining at least one geophysical property of the subsurface formation based on the single elemental decay of the one chemical element.

Abstract: A unified framework has been designed to create and maintain a set of adaptable general models that can be deployed and efficiently trained to fit to various deployments. The unified framework incrementally fills the feature space of a high dimensionality training dataset with field observations to reduce sparseness, trains and retrains a model set with the changing global training dataset, and then deploys a selected adaptable general model for training/fitting to a specified deployment scenario. Data that is generated by deployment adapted models can be validated and then added to the global training dataset that is used to train and update the general models. With the increasing density of the global training dataset, the general models can more quickly converge for a deployment scenario.

Abstract: Systems and methods may utilize information collected by a pulsed-neutron logging tool along with modeling a characterization of a borehole to form a 3-stage correction algorithm. This algorithm may be used to find an oil, water, and gas holdup in the borehole. During operations, a pulsed neutron logging tool which emits neutrons to interact with nuclei inducing gamma radiation. The gamma radiation is detected into a response which may be correlated to the location of a holdup in a borehole by using the entire spectrum or ratios of selected peaks. In examples, a borehole density index may be implemented to complement the response and improve accuracy and measurement confidence.

Abstract: In some embodiments, a method includes emitting, from a transmitter positioned in a wellbore formed in a subsurface formation, a pulse of neutrons into the subsurface formation and detecting gamma ray emissions at a near field and a far field generated in response to the pulse of neutrons being emitted into the subsurface formation. The method includes determining a single elemental decay for one chemical element of a number of chemical elements present in the subsurface formation based on the gamma ray emissions and determining at least one geophysical property of the subsurface formation based on the single elemental decay of the one chemical element.

Abstract: Aspects of the subject technology relate to determining holdup compensated formation saturation while refraining from calculating holdup. Inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore can be accessed. Further, capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore can be accessed. A model that accounts for holdup measurement can be applied to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums.

Abstract: Systems and methods employed measure borehole density by neutron induced gammas using a pulsed neutron tool. Traditional nuclear density methods only measure a bulk average density of the surrounding material. As discussed below, methods to measure only the borehole density excluding the contamination from the formation are disclosed. Specifically, the proposed methods use unique signatures from each geometric region to directly measure the borehole density or compensate for the contamination from formation. This method may be achieved by a borehole density measurement using differential attenuation of capture gamma from casing iron, a borehole density measurement using differential attenuation of inelastic gamma from oxygen, a differential attenuation of any induced gamma from any element from borehole and formation, or any combination thereof.

Abstract: Systems and methods for determining holdup in a wellbore using a neutron-based downhole tool. In examples, the tool includes nuclear detectors that may measure gammas induced by highly energized pulsed-neutrons emitted by a generator. The characteristic energy and intensity of detected gammas indicate the elemental concentration for that interaction type. A detector response may be correlated to the borehole holdup by using the entire spectrum or the ratios of selected peaks. As a result, measurements taken by the neutron-based downhole tool may allow for a two component (oil and water) or a three component (oil, water, and gas) measurement. The two component or three component measurements may be further processed using machine learning (ML) and/or artificial intelligence (AI) with additional enhancements of semi-analytical physics algorithms performed at the employed network's nodes (or hidden layers).

Abstract: Systems and methods of the present disclosure relate to determining a borehole holdup. A method comprises logging a well with a pulsed-neutron logging (PNL) tool; receiving, via the PNL tool, transient decay measurements, capture spectrum measurements, and inelastic spectrum measurements; extracting information from each of the capture spectrum measurements, the inelastic spectrum measurements, and the transient decay measurements; inputting all of the extracted information as a single input into artificial neural networks; and determining the borehole holdup with the artificial neural networks.

Abstract: A nuclear density tool may comprise a gamma source, a gamma detector, wherein the gamma detector and the gamma source are disposed on a longitudinal axis of the nuclear density tool, and a housing, wherein the gamma source and the gamma detector are disposed in the housing. The nuclear density tool may further comprise a first cutout in the housing positioned to allow the gamma source to emit an energy through the housing and a second cutout in the housing posited to allow the gamma detector to detect the energy through the housing.

Abstract: Aspects of the subject technology relate to determining a holdup measurement based on a gamma spectrum through machine learning. A spectral image based on a gamma spectrum generated downhole in a wellbore can be accessed. A component of a holdup measurement for the wellbore can be classified into a specific quantized level through application of a machine learning classification model to the spectral image. A continuous value for the component of the holdup measurement for the wellbore can be quantified by applying a machine learning quantization model associated with the quantized level.

Abstract: Aspects of the subject technology relate to performing gamma spectral analysis based on machine learning. Gamma spectrum data, which can be associated with a gamma spectrum can be gathered. The gamma spectrum data can include an energy channel and a count rate for gamma rays detected by one or more gamma detectors. A spectral image can be constructed based on the gamma spectrum data. One or more machine learning models can be trained based on the spectral image. Additionally, one or more features of the gamma spectrum can be extracted from the spectral image through the one or more machine learning models.