Abstract: Example solutions for pluralistic salient object detection are disclosed. A received image shows multiple objects, such as a first object and a second object. A pluralistic object detector is trained to learn tokens. When provided with the image and the first token, it generates a first segmentation mask corresponding to the first object, but not the second object, and when provided with the image and the second token, it generates a second segmentation mask corresponding to at least the second object (and possibly also the first image). When the pluralistic object detector is trained on five tokens, up to five different segmentation masks, each corresponding to a different selection of up to five objects, may be generated. Additionally, a quality predictor is disclosed that assigns quality scores to each of the different segmentation masks, without requiring ground truth for the image.

Abstract: A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space.

Abstract: Systems and methods for generating synthetic borehole image logs include logging rate of penetration (ROP) data, resistivity data, and gamma ray data while drilling a borehole in a subsurface formation to generate logged data. The generating includes determining an effective dip angle of the subsurface formation along the borehole and generating a depth shift table based on the effective dip angle and a well deviation angle, the well deviation angle being between the borehole and a vertical reference. Datasets are generated based on the ROP data, resistivity data, and gamma ray data, the generated datasets having higher sampling rates than the logged data. Synthetic borehole images are generated based on the generated datasets and the depth shift table, and the synthetic borehole images are oriented with respect to a reference point of the borehole.

Abstract: The invention provides compositions and methods for detecting thyroid hormone blocking immunoglobulin (TBI). The invention's methods are sensitive and specific for TBI, and may be used for the dual detection of both TBI and TSI. The invention's compositions and methods are useful for the diagnosis of diseases that are associated with the presence of TBI and/or TSI, for monitoring the progress of disease and/or treatment regimens, therapeutics, vaccines, etc., and for assisting clinicians in making treatment decisions.

Abstract: Systems and methods include a computer-implemented method for creating artificial real-time gamma ray (GR) images for well placement. Real-time azimuthal density data is determined from drilling of a well. An azimuthal density data set is generated using the real-time azimuthal density data. The azimuthal density data set is generated with a greater sampling rate than a real-time sampling rate of the real-time azimuthal density data. An azimuthal density curve depth match is performed using the azimuthal density data set. Performing the azimuthal density curve depth match includes creating a depth shift match table. A high-resolution sector near-bit gamma ray (GR) image is generated using the azimuthal density curve depth match and the depth shift match table. The high-resolution sector near-bit GR image is oriented to a top of a wellbore for the well.

Abstract: A computer-implemented method that enables lithofacies guided core description using unsupervised machine learning is described herein. The method includes obtaining well log curves for a wells in a zone. The method also includes predicting lithofacies for the wells using a machine learning model. The machine learning model is trained with input data comprising additional well log curves and well cores. The method includes grouping the wells based on the predicted lithofacies, and updating core descriptions of the wells based on the grouped wells.

Abstract: The invention provides compositions and methods for detecting thyroid hormone blocking immunoglobulin (TBI). The invention's methods are sensitive and specific for TBI, and may be used for the dual detection of both TBI and TSI. The invention's compositions and methods are useful for the diagnosis of diseases that are associated with the presence of TBI and/or TSI, for monitoring the progress of disease and/or treatment regimens, therapeutics, vaccines, etc., and for assisting clinicians in making treatment decisions.

Abstract: Systems and methods include a computer-implemented method: Total clay, effective porosity (PHIE) values, and gas volume are determined for a tight gas sandstone reservoir characterization using petrophysical evaluation results. Regions of the tight gas sandstone reservoir are characterized, including performing diagenetic rock typing for the regions using the total clay and PHIE values, where the diagenetic rock typing reflects porosity/permeability and clay content change. Sweet spots are determined based on the diagenetic rock typing and gas volume variation. Ranked sweet spots are determined by indexing and ranking the sweet spots by category. Optimized infill drilling locations and target zones are determined, and well placements in the tight gas sandstone reservoir are assisted using the diagenetic rock typing and the ranked sweet spots.

Abstract: A computer-implemented method that enables lithofacies guided core description using unsupervised machine learning is described herein. The method includes obtaining well log curves for a wells in a zone. The method also includes predicting lithofacies for the wells using a machine learning model. The machine learning model is trained with input data comprising additional well log curves and well cores. The method includes grouping the wells based on the predicted lithofacies, and updating core descriptions of the wells based on the grouped wells.

Abstract: Systems and methods include a computer-implemented method for creating artificial real-time gamma ray (GR) images for well placement. Real-time azimuthal density data is determined from drilling of a well. An azimuthal density data set is generated using the real-time azimuthal density data. The azimuthal density data set is generated with a greater sampling rate than a real-time sampling rate of the real-time azimuthal density data. An azimuthal density curve depth match is performed using the azimuthal density data set. Performing the azimuthal density curve depth match includes creating a depth shift match table. A high-resolution sector near-bit gamma ray (GR) image is generated using the azimuthal density curve depth match and the depth shift match table. The high-resolution sector near-bit GR image is oriented to a top of a wellbore for the well.

Abstract: A horizontal or deviated core sample is received from a wellbore. A presence of geologic indicators within the horizontal or deviated core sample is determined. The horizontal or deviated core sample is rotated to a position based on the presence and orientation of the geologic indicators. A top of the horizontal or deviated core sample is marked after the core has been rotated.

Abstract: Disclosed is an echelon utilization battery pack with good seismic resistance. The echelon utilization battery pack involves a battery pack body and a battery, wherein the battery pack body is of a hollow cuboid structure, fixed seats are fixed at two ends of the inner bottom of the battery pack body, first fixed shafts are fixed between the two fixed seats, the first fixed shafts are slidably connected with a mounting seat in a sleeving mode, a first sliding groove is formed in the top of the mounting seat, second fixed shafts are fixed in the first sliding groove, and the two ends of the second fixed shafts are slidably connected with first sliding blocks.

Abstract: A horizontal or deviated core sample is received from a wellbore. A presence of geologic indicators within the horizontal or deviated core sample is determined. The horizontal or deviated core sample is rotated to a position based on the presence and orientation of the geologic indicators. A top of the horizontal or deviated core sample is marked after the core has been rotated.

Abstract: A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space.

Abstract: Systems and methods include a computer-implemented method: Total clay, effective porosity (PHIE) values, and gas volume are determined for a tight gas sandstone reservoir characterization using petrophysical evaluation results. Regions of the tight gas sandstone reservoir are characterized, including performing diagenetic rock typing for the regions using the total clay and PHIE values, where the diagenetic rock typing reflects porosity/permeability and clay content change. Sweet spots are determined based on the diagenetic rock typing and gas volume variation. Ranked sweet spots are determined by indexing and ranking the sweet spots by category. Optimized infill drilling locations and target zones are determined, and well placements in the tight gas sandstone reservoir are assisted using the diagenetic rock typing and the ranked sweet spots.

Abstract: Disclosed is an echelon utilization battery pack with good seismic resistance. The echelon utilization battery pack involves a battery pack body and a battery, wherein the battery pack body is of a hollow cuboid structure, fixed seats are fixed at two ends of the inner bottom of the battery pack body, first fixed shafts are fixed between the two fixed seats, the first fixed shafts are slidably connected with a mounting seat in a sleeving mode, a first sliding groove is formed in the top of the mounting seat, second fixed shafts are fixed in the first sliding groove, and the two ends of the second fixed shafts are slidably connected with first sliding blocks.

Abstract: The invention provides compositions and methods for detecting thyroid hormone blocking immunoglobulin (TBI). The invention's methods are sensitive and specific for TBI, and may be used for the dual detection of both TBI and TSI. The invention's compositions and methods are useful for the diagnosis of diseases that are associated with the presence of TBI and/or TSI, for monitoring the progress of disease and/or treatment regimens, therapeutics, vaccines, etc., and for assisting clinicians in making treatment decisions.

Abstract: The present invention provides methods and compositions useful in the diagnosis and management of autoimmune diseases. In particular, the present invention provides improved methods and compositions for the diagnosis and management of Graves' disease. The methods of the present invention not only avoids the need for radioactivity and are much simpler, economical, and rapid than methods traditionally used for the diagnosis of Graves' disease, but also improve upon the sensitivity and detection abilities of previous luciferase-based autoantibody detection assays. Such improvements are based upon the superior performance of assays comprising a chimeric TSH receptor in the presence of a glucocorticoid including, but not limited to, dexamethasone.

Abstract: The present invention provides methods and compositions useful in the diagnosis and management of autoimmune diseases. In particular, the present invention provides improved methods and compositions for the diagnosis and management of Graves' disease. The methods of the present invention not only avoids the need for radioactivity and are much simpler, economical, and rapid than methods traditionally used for the diagnosis of Graves' disease, but also improve upon the sensitivity and detection abilities of previous luciferase-based autoantibody detection assays. Such improvements are based upon the superior performance of assays comprising a chimeric TSH receptor in the presence of a glucocorticoid including, but not limited to, dexamethasone.

Abstract: The present invention provides methods and compositions useful in the diagnosis and management of autoimmune diseases. In particular, the present invention provides improved methods and compositions for the diagnosis and management of Graves' disease. The methods of the present invention not only avoids the need for radioactivity and are much simpler, economical, and rapid than methods traditionally used for the diagnosis of Graves' disease, but also improve upon the sensitivity and detection abilities of previous luciferase-based autoantibody detection assays. Such improvements are based upon the superior performance of assays comprising a chimeric TSH receptor in the presence of a glucocorticoid including, but not limited to, dexamethasone.