Abstract: Certain aspects of the present disclosure provide techniques and apparatus for efficient scaling of inputs to be processed by a machine learning model. An example method generally includes receiving, by a machine learning model, an input having a starting size in a plurality of dimensions. The method further includes scaling, by the machine learning model, the input in one or more dimensions of the plurality of dimensions to generate a scaled input, wherein the input is scaled in each respective dimension of the one or more dimensions based on a respective stride length determined based on a starting size in the respective dimension and a target size in the respective dimension, and the respective stride length associated with at least one dimension in the one or more dimensions comprises a non-integer value. The method further includes generating, by the machine learning model, an inference based on the scaled input.

Abstract: An interconnectable downhole instrument package has a downhole instrument disposed in a pressure housing; a male connector assembly connecting to a first end of the downhole instrument; and a female connector assembly connecting to a second end of the downhole instrument. The male connector assembly has a first housing and a male rotatable connector that are connected together, while the female connector assembly has a second housing and a female rotatable connector. The second housing is adapted to receive the female rotatable connector.

Abstract: Systems and techniques are provided for compressing data. A process can include generating a compressed sub-packet by removing one or more sparsity bytes from a sequence of values corresponding to a sub-packet, the sequence of values including one or more sparsity bytes each equal to a configured sparsity value and one or more non-sparsity bytes each corresponding to a respective data value different from the configured sparsity value. A sub-packet header can be generated for the compressed sub-packet, and indicative of a respective location within the sequence of values of each non-sparsity byte. A packet header can be generated for a plurality of compressed sub-packets, and indicative of the configured sparsity value and respective coding information for each compressed sub-packet. A compressed data packet can be generated to include at least the packet header, the sub-packet header, and the one or more non-sparsity bytes included in the sequence of values.

Abstract: A method for obtaining elemental concentration and determining the formation mineralogy uses a tool having multiple dual-function detectors that can detect both neutrons and gamma rays simultaneously. The method includes emitting neutrons into the formation, detecting neutron and gamma ray signals from the formation and discriminating the neutron signal and the gamma ray signal, obtaining the space, time and energy dependent fluence rates for fast neutrons and thermal neutrons, obtaining gamma ray energy spectra from inelastic scattering and neutron capture reactions from one or more detectors, obtaining the energy spectrum of inelastic gamma rays and/or capture gamma rays from a single element, calculating concentration of the element in the formation using its energy spectrum of inelastic gamma rays or capture gamma rays from one or more detectors and the space, time and energy dependent fluence rate of fast neutrons or thermal neutrons, and determining the formation mineralogy.

Abstract: A method for obtaining a gas saturation value of a subterrain formation involves a tool having multiple dual-function detectors that detect neutrons and gamma rays. The method includes steps of emitting neutrons into the formation, detecting neutrons and gamma ray signals form the formation using the detectors, determining formation parameters including the formation type and formation porosity, and further determining parameters such as the ratio of thermal neutron count rates from at least two of three detectors, the ratio of capture gamma count rates from at least two of three detectors, and calculating the real-time gas saturation value using the determined parameters.

Abstract: A method for measuring an oil saturation value of a subterrain formation uses a tool having multiple dual-function detectors that detect neutrons and gamma rays. The method includes emitting neutrons into the formation, detecting neutrons and gamma ray signals form the formation using the detectors, determining formation parameters including the formation type and formation porosity, and further determining parameters such as C/O ratios at each of the detectors, a total neutron count rate at each of detectors, a fast neutron count rate at each of detectors, and a thermal neutron count rate at each of the three or more detector, and calculating the oil saturation value using the determined parameters.

Abstract: A mud pulser includes an inlet assembly, a main-valve assembly, a servo-valve assembly, a motor assembly and a collar. The servo-valve assembly has a servo-valve, which includes a servo-valve plugging member and a servo-valve chamber housing the servo-valve plugging member and having a first orifice and a second orifice. A servo-valve shaft is connected to the servo-valve plugging member and configured to be driven to perform a reciprocating movement that causes the servo-valve plugging member to alternately block the first orifice and the second orifice. The alternate blocking of the first orifice and the second orifice triggers movements in the main-valve assembly to restrict or release mud flow to generate mud pulse.

Abstract: Systems and techniques are provided for compressing data. A process can include generating a compressed sub-packet by removing one or more sparsity bytes from a sequence of values corresponding to a sub-packet, the sequence of values including one or more sparsity bytes each equal to a configured sparsity value and one or more non-sparsity bytes each corresponding to a respective data value different from the configured sparsity value. A sub-packet header can be generated for the compressed sub-packet, and indicative of a respective location within the sequence of values of each non-sparsity byte. A packet header can be generated for a plurality of compressed sub-packets, and indicative of the configured sparsity value and respective coding information for each compressed sub-packet. A compressed data packet can be generated to include at least the packet header, the sub-packet header, and the one or more non-sparsity bytes included in the sequence of values.

Abstract: A method for measuring subterranean formation porosity includes the steps of: deploying a nuclear logging tool having one or more neutron sources and two or more dual-function detectors disposed in into a subterranean formation; causing the one or more neutron sources to emit neutrons in a plurality of neutron pulses into the subterranean formation and generating neutrons and gamma rays in the subterranean formation; obtaining one or more neutron count rates for each of the two or more detectors; determining a formation type of the subterranean formation based on gamma rays received at the one or more detectors; calculating one or more neutron count rate ratios between the neutron count rates of two detectors selected from the two or more detectors; and obtaining one or more formation porosities based on the formation type and the one or more neutron count rate ratios.

Abstract: A method for obtaining elemental concentration and determining the formation density uses a tool having multiple dual-function detectors that can detect both neutrons and gamma rays simultaneously. The method includes emitting neutrons into the formation, detecting neutron and gamma ray signals from the formation and discriminating the neutron signal and the gamma ray signal, obtaining the space, time and energy dependent fluence rates for fast neutrons and thermal neutrons, obtaining gamma ray energy spectra from initial inelastic gamma rays and backscattered inelastic gamma rays from one or more detectors. The formation density can be calculated based on one or more ratios between the gamma ray count rates at the one or more detectors to the gamma ray count rate at the near detector.

Abstract: A nuclear logging tool has a housing, one or more neutron sources, one or more shields, and two or more detectors disposed about the housing. Each of the one or more neutron sources is configured to generate neutrons in pulses or continuously and each of the two or more detectors is operable to detect neutrons and gamma rays. The two or more detectors include a first detector disposed at a first distance from a first neutron source and a second detector disposed at a second distance from the first neutron source. The first distance is shorter than the second distance. The first distance and the second distance is measured in the longitudinal direction of the housing. Each shield is operable to absorb neutrons and gamma rays and is disposed inside the housing between one of the one or more neutron source and one of the one or more detectors.

Abstract: Formation porosity is measured using a logging tool that has a pulsed neutron generator and multiple dual-function detectors that detect both neutrons and gamma rays. Ratios of thermal neutrons, epithermal neutrons, and capture gamma rays from multiple detectors are utilized to obtain multiple neutron porosities and multiple gamma-ray porosities within different depth of investigations. The neutron porosity and the gamma-ray porosity may be further corrected by excluding peak areas attributable to hydrogen and/or chlorine to reduce the shale effect and/or the chlorine effect. The neutron porosity and the gamma-ray porosity may be combined to provide improved porosity evaluations within different depth of investigations into the formation in the entire porosity measurement range (0-100 p.u.).

Abstract: An interconnector for connecting downhole instruments includes a male connector assembly and a female connector assembly. The male connector assembly has a first housing and a male rotatable connector that are connected together. The female connector assembly has a second housing and a female rotatable connector. The second housing is adapted to receive the female rotatable connector. The male rotatable connector has a first end having a plurality of cylinders that are sequentially and concentrically connected, and a second end adapted to receive a first plurality of electrical wires, and a first plurality of electrical contacts disposed on the plurality of cylinders. The female rotatable connector has a first end having a cavity having a plurality of steps adapted to receive the plurality of cylinders in the male rotatable connector, and a second end adapted to receive a second plurality of electrical wires.

Abstract: An interconnector for connecting downhole instruments includes a male connector assembly and a female connector assembly. The male connector assembly has a first housing and a male rotatable connector that are connected together. The female connector assembly has a second housing and a female rotatable connector. The second housing is adapted to receive the female rotatable connector. The male rotatable connector has a first end having a plurality of cylinders that are sequentially and concentrically connected, and a second end adapted to receive a first plurality of electrical wires, and a first plurality of electrical contacts disposed on the plurality of cylinders. The female rotatable connector has a first end having a cavity having a plurality of steps adapted to receive the plurality of cylinders in the male rotatable connector, and a second end adapted to receive a second plurality of electrical wires.

Abstract: A method for wireline or logging-while-drilling systems that uses pulsed neutron sources coupled to multiple dual-function radiation detectors of neutrons and gamma rays, as well as a non-transitory computer readable memory device that can distinguish using pulse shape discrimination techniques the neutrons from the gamma rays in order to measure thermal neutron time-decay signals and thermal neutron capture gamma ray time-decay signals that are later further process using the non-transitory computer readable memory device to obtain a borehole sigma and formation sigma that are not affected by near-wellbore environments.

Abstract: A computer-implemented method that uses a preprogrammed neural network and a trained neural network computer program product to predict and then compared borehole and formation sigmas, when using a pulse neutron source and at least three dual-function radiation detectors. These dual-function radiation detectors are used for detecting both neutrons and gamma rays and further pre-programmed to distinguish between neutrons and gamma rays by using pulse shape discrimination techniques. The trained neural network computer program product can be used on above-surface systems, as well as below surface systems like borehole assemblies in logging-while-drilling systems.

Abstract: A method for obtaining elemental concentration and determining the formation mineralogy uses a tool having multiple dual-function detectors that can detect both neutrons and gamma rays simultaneously. The method includes emitting neutrons into the formation, detecting neutron and gamma ray signals from the formation and discriminating the neutron signal and the gamma ray signal, obtaining the space, time and energy dependent fluence rates for fast neutrons and thermal neutrons, obtaining gamma ray energy spectra from inelastic scattering and neutron capture reactions from one or more detectors, obtaining the energy spectrum of inelastic gamma rays and/or capture gamma rays from a single element, calculating concentration of the element in the formation using its energy spectrum of inelastic gamma rays or capture gamma rays from one or more detectors and the space, time and energy dependent fluence rate of fast neutrons or thermal neutrons, and determining the formation mineralogy.

Abstract: A method for obtaining a gas saturation value of a subterrain formation involves a tool having multiple dual-function detectors that detect neutrons and gamma rays. The method includes steps of emitting neutrons into the formation, detecting neutrons and gamma ray signals form the formation using the detectors, determining formation parameters including the formation type and formation porosity, and further determining parameters such as the ratio of thermal neutron count rates from at least two of three detectors, the ratio of capture gamma count rates from at least two of three detectors, and calculating the real-time gas saturation value using the determined parameters.

Abstract: A computer-implemented method that uses a preprogrammed neural network and a trained neural network computer program product to predict and then compared borehole and formation sigmas, when using a pulse neutron source and at least three dual-function radiation detectors. These dual-function radiation detectors are used for detecting both neutrons and gamma rays and further pre-programmed to distinguish between neutrons and gamma rays by using pulse shape discrimination techniques. The trained neural network computer program product can be used on above-surface systems, as well as below surface systems like borehole assemblies in logging-while-drilling systems.

Abstract: A method for wireline or logging-while-drilling systems that uses pulsed neutron sources coupled to multiple dual-function radiation detectors of neutrons and gamma rays, as well as a non-transitory computer readable memory device that can distinguish using pulse shape discrimination techniques the neutrons from the gamma rays in order to measure thermal neutron time-decay signals and thermal neutron capture gamma ray time-decay signals that are later further process using the non-transitory computer readable memory device to obtain a borehole sigma and formation sigma that are not affected by near-wellbore environments.