Abstract: A method for processing waveform data for determining a characteristic inside an object includes receiving raw waveform data collected with waveform sensors over a given object; pretraining a first neural network with the raw waveform data so that structural information within the raw waveform data is extracted; receiving a first task to be performed with regard to the object, based on the raw waveform data; fine-tuning a second neural network, based on (1) pretrained parameters from the first neural network, and (2) the first task; and generating an image of the object using the second neural network with refined parameters.

Abstract: Systems and methods are disclosed relating to image enhancement. In an example, a first training of a machine learning (ML) algorithm can be implemented using a synthetic training dataset to provide a first model. The synthetic training dataset can include low-resolution and high-resolution synthetic image pairs. A second training of the ML algorithm can be implemented using a real training dataset and an output of the first model to provide a second model. The real training dataset can include real low-resolution images. A low-resolution image can be enhanced using the second model to provide an enhanced image of the low-resolution image.

Abstract: Fault detection in seismic data using a latent representation of seismic data. Sample data may be created from seismic data and used to train an autoencoder. The autoencoder is used to generate a latent representation of seismic data. A fault attribute is computed by selecting two sets of traces in proximity to each other in the seismic data, generating their corresponding latent representations using the trained autoencoder, and computing a fault attribute between the two latent representations. The fault attribute is used to identify a fault in the seismic data.

Abstract: Systems and methods for generating seismic images of a subsurface formation include obtaining seismic data representing the subsurface formation. Velocity models are generated for the subsurface formation based on the seismic data. Green's functions for the subsurface formation are predicted using a neural network, where the inputs to the neural network include the velocity models, and seismic images of the subsurface formation are generated based on the seismic data and the predicted Green's functions.

Abstract: Systems and methods are configured for identifying faults or fractures in a subsurface region for performing hydrocarbon extraction. The systems and methods execute a Bayesian neural network on seismic images to generate, for locations in the seismic images, predictions of the presence or absence of faults and fractures in the subsurface region. The predictions are associated with uncertainty values. The locations of wells are selected for drilling based on the predictions and the associated uncertainty values.

Abstract: A method and system for identifying a feature in seismic datasets using a machine learning (ML) network is provided. The method includes training the ML network by obtaining a seismic dataset and forming a plurality of seismic patches having a labeled feature. Training the ML network continues by predicting a candidate labeled feature patch for each seismic patch, forming a metric measuring a mismatch of the candidate labeled feature patch and the labeled feature and updating the ML network based on finding an extremum of the mismatch to form a trained ML network. The method further includes forming a plurality of production seismic patches having unlabeled features and inputting the patches into a trained ML network to predict a labeled feature patch having a labeled manifestation of the feature. A predicted labeled feature image may then be formed by merging the plurality of predicted labeled feature patches.

Abstract: A silicon dioxide vaccine delivery system uses virus-like particles as templates. The particle morphology of the silicon dioxide vaccine system is 50-500 nm of nanoparticles, of which an antigenic component is 20-200 nm of virus-like particles, an adjuvant component is nano silicon dioxide, the silicon dioxide component is wrapped on the surface of the virus-like particle, and a mass ratio of silicon element to antigen is 50-0.5:1. The construction of the silicon dioxide vaccine delivery system includes steps of: (1) adding a proper amount of 3-aminopropyltriethoxysilane into an aqueous solution containing virus-like particles and stirring; (2) adding a proper amount of tetraethoxysilane into the dispersion system in step (1) and stirring; and (3) centrifuging a reactant obtained in step (2) and removing a supernatant to obtain a product. A vaccine constructed by means of the vaccine system can trigger a host to generate humoral and cellular immune levels.

Abstract: Methods and systems are disclosed. The methods may include obtaining M training pairs and training a machine learning (ML) model using the M training pairs. The methods may further include obtaining geological data from a subterranean region of interest and, for each of a sequence of N windows, inputting the geological data and an (n?1)th predicted feature image within an (n?1)th window into the ML model and producing an nth predicted feature image within an nth window from the ML model. The geological data includes a seismic image and a manifestation of a feature within the subterranean region of interest. The methods may still further include determining the predicted feature image for the geological data associated with the subterranean region of interest using the N predicted feature images. The predicted feature image includes a labeled manifestation of the feature.

Abstract: Methods and systems for performing simultaneous seismic interpretation are disclosed. The methods include obtaining a first seismic dataset pertaining to a first subterranean region of interest; and training a machine learning network to perform simultaneous seismic interpretation using the first seismic dataset, where simultaneous seismic interpretation includes completing a plurality of seismic interpretation tasks. The methods further include obtaining a second seismic dataset pertaining to a second subterranean region of interest and determining a simultaneous seismic interpretation of the second seismic dataset by performing simultaneous seismic interpretation using the trained machine learning network.

Abstract: A method for calculating a velocity model for a subsurface of the earth. The method includes receiving (200) measured seismic data d; calculating (204) predicted seismic data p; selecting (206) a matching filter w that when applied to one of the measured seismic data d or the predicted seismic data p reproduces the other one of the measured seismic data d or the predicted seismic data p; selecting (208) a misfit function J that calculates (1) a distance between the matching filter w and a Dirac Delta function or (2) a travel time shift associated with the measured seismic data; and calculating (218) a new velocity model using the misfit function J, the measured seismic data d, and the predicted seismic data p. The measured seismic data d includes wavefields generated by a seismic source and the wavefields propagate through the subsurface where they are attenuated and reflected, and the attenuated and reflected wavefields are recorded by plural seismic receivers.

Abstract: A method for processing waveform data for determining a characteristic inside an object includes receiving raw waveform data collected with waveform sensors over a given object; pretraining a first neural network with the raw waveform data so that structural information within the raw waveform data is extracted; receiving a first task to be performed with regard to the object, based on the raw waveform data; fine-tuning a second neural network, based on (1) pretrained parameters from the first neural network, and (2) the first task; and generating an image of the object using the second neural network with refined parameters.

Abstract: A method for preparing a combination adjuvant is based on carboxyl modified aluminum oxyhydroxide nanoparticles. The preparation method uses carboxylated hydroxyl oxide nanoparticles as a carrier, but is not limited to the role of a carrier. The carboxylated hydroxyl oxide nanoparticles are combined with a novel CpG-ODN adjuvant, such that the half-life period of a CpG adjuvant is prolonged. The combination of adjuvants shows a synergistic effect, such that the Th2 type immune stimulation ability is enhanced, and the possibility of Th1 type immunity is also given to the adjuvant.

Abstract: A method for waveform inversion, the method including receiving observed data d, wherein the observed data d is recorded with sensors and is indicative of a subsurface of the earth; calculating estimated data p, based on a model m of the subsurface; calculating, using a trained neural network, a misfit function JML; and calculating an updated model mt+1 of the subsurface, based on an application of the misfit function JML to the observed data d and the estimated data p.

Abstract: A three-dimensional (3D) seismic data set is divided into a plurality of 3D source wavefield subsets, each 3D source wavefield subset is stored in an array element of an array. For each array element, the associated 3D source wavefield is decomposed into a smaller data unit; data boundaries of the smaller data units are randomly shifted; a folding operation and a sample operator is applied to the smaller data units to keep the smaller data units from overlapping; the folded smaller data units are smoothed to generate smoothed data; a quantization operation is performed on the smoothed data to produce quantized data; and the quantized data is compression encoded to generate compressed data. The compressed data associated with each array element is decompressed to generate a 3D seismic output image.

Abstract: A method for calculating a velocity model for a subsurface of the earth. The method includes receiving (200) measured seismic data d; calculating (204) predicted seismic data p; selecting (206) a matching filter w that when applied to one of the measured seismic data d or the predicted seismic data p reproduces the other one of the measured seismic data d or the predicted seismic data p; selecting (208) a misfit function J that calculates (1) a distance between the matching filter w and a Dirac Delta function or (2) a travel time shift associated with the measured seismic data; and calculating (218) a new velocity model using the misfit function J, the measured seismic data d, and the predicted seismic data p. The measured seismic data d includes wavefields generated by a seismic source and the wavefields propagate through the subsurface where they are attenuated and reflected, and the attenuated and reflected wavefields are recorded by plural seismic receivers.

Abstract: The present disclosure discloses a novel biochip substrate, a preparation method and an application thereof. The surface of the novel biochip substrate contains active vinyl sulfone groups. The preparation method involves a one-step reaction of a compound containing vinyl sulfone groups on both ends with a silicon-hydroxyl group on the surface of a silicon-based biochip substrate material under catalytic conditions, to prepare the biochip substrate. The application immobilizes biomacromolecules by conducting Michael addition of amino or sulfydryl group in biomacromolecules and the vinyl sulfone group on the surface of the biochip substrate, realizing biological functionalization thereof. The biochip substrate has high-density active vinyl sulfone groups, which can be used for immobilization of various biomolecules with mild fixation conditions and simple operation.

Abstract: In a method to functionalize high-density chromatography matrix functionalization method, the hydrophilic microsphere having a surface polyhydroxy structure or the hydrophilic microsphere coated with a polyhydroxy polymer is used as chromatography matrix, under anhydrous conditions with catalyst, catalyze surface hydroxyl group of the matrix to react with divinyl sulfone, and achieve functionalization of the hydroxyl group on the surface of the matrix. The chromatography matrix surface functionalization method of the present disclosure has few steps, simple process and high functional density, and the reagents and solvents used are conventional reagents and can be recycled and reused. No byproduct is generated during the reaction with high atom economy and low cost, and the density control can be achieved by adjusting the reaction time and catalyst type.

Abstract: A display panel, a display terminal and a display motherboard are provided. The display panel includes a pixel defining layer, an inorganic barrier layer, an organic light-emitting material layer, and a thin film encapsulation structure. The pixel defining layer is provided with a plurality of openings distributed in an array. The inorganic barrier layer is disposed in a part of the openings at a periphery of the pixel defining layer, and has a plurality of first grooves spaced apart on a side thereof. The organic light-emitting material layer is disposed in the part of the openings and formed on the inorganic barrier layer. The thin film encapsulation structure is disposed on the pixel defining layer, and the thin film encapsulation structure is filled in the first grooves and covers the organic light-emitting material layer.