Abstract: A model can be trained for discriminant analysis for substance classification and/or measuring calibration. One method includes interacting at least one sensor with one or more known substances, each sensor element being configured to detect a characteristic of the one or more known substances, generating an sensor response from each sensor element corresponding to each known substance, wherein each known substance corresponds to a known response stored in a database, and training a neural network to provide a discriminant analysis classification model for an unknown substance, the neural network using each sensor response as inputs and one or more substance types as outputs, and the outputs corresponding to the one or more known substances.

Abstract: Mutual-complementary modeling and testing methods are disclosed that can enable validated mapping from external oil and gas information sources to existing fluid optical databases through the use of forward and inverse neural networks. The forward neural networks use fluid compositional inputs to produce fluid principal spectroscopy components (PSC). The inverse neural networks apply PSC inputs to estimate fluid compositional outputs. The fluid compositional data from external sources can be tested through forward models first. The produced PSC outputs are then entered as inputs to inverse models to generate fluid compositional data. The degree of matching between reconstructed fluid compositions and the original testing data suggests which part of the new data can be integrated directly into the existing database as validated mapping. The applications of using PSC inputs to reconstruct infrared spectra and estimate oil-based-mud (OBM) contamination with endmember spectral fingerprints are also included.

Abstract: Disclosed are methods and systems for determination of fluid contamination of a fluid sample from a downhole fluid sampling tool.

Abstract: Disclosed is the detection of emulsions and microdispersions with an optical computing device. One disclosed method includes emitting electromagnetic radiation from an electromagnetic radiation source, optically interacting the electromagnetic radiation with a fluid and thereby generating fluid interacted radiation, detecting a portion of the fluid interacted radiation with a reference detector arranged within an optical channel of an optical computing device, generating a reference signal with the reference detector, and determining an emulsive state of the fluid based on the reference signal.

Abstract: Systems and methods for subterranean formation testing. A method may include lowering a formation testing tool into a subterranean formation, wherein the formation testing tool may comprise a plurality of chambers, a pump and a probe channel; extracting a fluid from the subterranean formation into the probe channel; determining fluid properties at different depths; generating a fluid property-depth gradient; moving the fluid into the plurality of chambers; and determining a concentration of an inorganic portion of a downhole flashed gas.

Abstract: The embodiments herein relate to sensors having reactive filter materials for detecting analytes in wellbores. The sensor includes at least one reactive filter material arranged in a flow line, wherein the reactive filter material sorbs an analyte in a wellbore fluid in the flow line; and at least one detector that detects a sorption signal specific to the analyte at at least a first location and a second location of the reactive filter material, wherein the first location is upstream in the flow line relative to the second location. The detector either (1) calculates a balanced measurement corresponding to the presence of the analyte in the wellbore or (2) relays the measurements to a signal processing unit to calculate a balanced measurement corresponding to the presence of the analyte in the wellbore.

Abstract: Disclosed are systems and methods that use discriminant analysis techniques and processing in order to reduce the time required to determine chemical and/or physical properties of a substance. One method includes optically interacting a plurality of optical elements with one or more known substances, each optical element being configured to detect a particular characteristic of the one or more known substances, generating an optical response from each optical element corresponding to each known substance, wherein each known substance corresponds to a known spectrum stored in an optical database, and training a neural network to provide a discriminant analysis classification model for an unknown substance, the neural network using each optical response as inputs and one or more fluid types as outputs, and the outputs corresponding to the one or more known substances.

Abstract: An optical computing device having a redundant light source and/or a plurality of optical elements (i.e., optical train) in order to simultaneously determine characteristics of a sample in real-time by deriving the characteristic data from the output of the optical elements.

Abstract: A method and system can obtain real time property measurements of a fluid comprising a formation fluid downhole, real time measurements of an amount of an interactive component of the fluid downhole, and real time measurements of an amount of a non-interactive component of the fluid downhole. The method and system further includes determining a total amount of the interactive component in the fluid or a contamination level of the formation fluid at a time of interest based on the real time property measurements of the fluid downhole and the real time measurements of the amounts of the interactive component and non-interactive component downhole. The real time measurements of the amount of the interactive component downhole are real time measurements of the amount of the interactive component in its free form downhole, and the property can be scaled with the contamination level.

Abstract: This disclosure includes methods for designing a simplified Integrated Computational Element (ICE) and for optimizing a selection of a combination of ICE designs. A method for fabricating a simplified ICE having one or more film layers includes predicting an optimal thickness of each of the one or more film layers of the simplified ICE using a neural network. A method for recalibrating the fabricated ICE elements for system implementation is also disclosed. The disclosure also includes the simplified ICE designed by and the ICE combination selected by the disclosed methods. The disclosure also includes an information handling system with machine-readable instructions to perform the methods disclosed herein.

Abstract: A downhole tool is positioned in a borehole of a geological formation at a given depth. A formation property is determined at the given depth. The positioning and determining is repeated to form data points of a data set indicative of formation properties at various depths in the borehole. One or more outlier data points is removed from the data set based on first gradients to form an updated data set. One or more properties associated with a reservoir compartment are determined based on second respective gradients associated with the updated data set.

Abstract: Systems and methods for subterranean formation testing. A method may include: lowering a formation testing tool into a subterranean formation, wherein the formation testing tool may include memory, a pump, a formation probe, at least two sample chambers, wherein the at least two sample chambers may include probes to measure pressure and temperature; extracting a fluid from the subterranean formation with the pump and the formation probe; flowing the fluid into the at least two sample chambers with the pump; storing pressure and temperature data of the fluid in the memory; and removing the at least two sample chambers from the formation testing tool.

Abstract: The present application relates sensing reactive components in fluids by monitoring band gap changes to a material having interacted with the reactive components via physisorption and/or chemisorption. In some embodiments, the sensors of the present disclosure include the material as a reactive surface on a substrate. The band gap changes may be detected by measuring conductance changes and/or spectroscopic changes. In some instances, the sensing may occur downhole during one or more wellbore operations like drilling, hydraulic fracturing, and producing hydrocarbons.

Abstract: Systems and methods for extracting and analyzing formation fluids from solids circulated out of a subterranean formation are provided. In one embodiment, the methods comprise: providing a sample of formation solids that have been separated from a fluid circulated in at least a portion of a well bore penetrating a portion of a subterranean formation at a well site; performing a solvent extraction on the sample of formation solids using one or more solvents at an elevated pressure at the well site, wherein at least a portion of one or more formation fluids residing in the formation solids is extracted into the one or more solvents to produce an extracted fluid; and analyzing the extracted fluid at the well site to determine the composition of the extracted fluid.

Abstract: System and methods for downhole fluid classification are provided. Measurements are obtained from one or more downhole sensors located along a current section of wellbore within a subsurface formation. The measurements obtained from the one or more downhole sensors are transformed into principal spectroscopy component (PSC) data. One or more fluid types are identified for the current section of the wellbore within the subsurface formation, based on the PSC data and a fluid classification model. The fluid classification model is refined for one or more subsequent sections of the wellbore within the subsurface formation, based at least partly on the one or more fluid types identified for the current section of the wellbore.

Abstract: Disclosed are methods and systems for determination of fluid contamination of a fluid sample from a downhole fluid sampling tool. A method may comprise obtaining a fluid sample, obtaining input parameters, wherein the input parameters comprise fluid properties obtained from measurement of the fluid sample and mud filtrate composition, obtaining initial values of iterative parameters, determining component mole fractions of the reservoir fluid using the initial values of the iterative parameters in a mole fraction distribution function, determining calculated fluid properties of the reservoir fluid using equation of state flash calculating, and repeating steps of determining component mole fractions and determining calculated fluid properties and further obtaining updated values of the iterative parameters for use in the mole fraction distribution function until a comparison of one or more of the calculated fluid properties with one or more of the input parameters is within a tolerance error.

Abstract: Various embodiments of microfluidic optical computing devices coupled with Integrated Computational Element cores are described.

Abstract: A device including at least two ICEs that optically interact with a sample light to generate a first and a second modified lights is provided. The at least two ICEs include alternating layers of material, each of the layers having a thickness selected such that the weighted linear combination of the transmission functions is similar to the regression vector associated with a characteristic of the sample. The device may also include a detector that measures a property of the first and second modified lights separately to generate a first and second signal, respectively, wherein the weighted average of first and second signals is linearly related to the characteristic of the sample. A method for fabricating the above device is also provided.

Abstract: A method is provided, including: forming an optical computing device having a first plurality of sensing elements selected to measure a characteristic of a sample, generating a transmission function from a first add-on integrated computational element (ICE), and evaluating, with a merit-function and the transmission function of the add-on ICE, a predictive performance of a modified optical computing device that includes the add-on ICE in addition to the first plurality of sensing elements. Also, modifying the first add-on ICE to improve the predictive performance of the modified optical computing device according to the merit-function and a modified transmission function of the add-on ICE.

Abstract: Systems and methods for extracting and analyzing formation fluids from solids circulated out of a subterranean formation are provided. In one embodiment, the methods comprise: providing a sample of formation solids that have been separated from a fluid circulated in at least a portion of a well bore penetrating a portion of a subterranean formation at a well site; performing a solvent extraction on the sample of formation solids using one or more solvents at an elevated pressure at the well site, wherein at least a portion of one or more formation fluids residing in the formation solids is extracted into the one or more solvents to produce an extracted fluid; and analyzing the extracted fluid at the well site to determine the composition of the extracted fluid.