Abstract: A computer implemented method includes obtaining data for raw image frames captured by a moving camera. The raw image frames are indexed geographically, and a graph is created from the multiple raw image frames. The graph includes image frames as vertices and edges that represent image frames having overlapping image information. The method further includes skipping frames based on the amount of overlap, determining a frame having an interesting feature, using the graph to find additional raw image frames that have the interesting feature, combining multiple raw image frames to form a unique image frame, and transmitting the unique image frame.

Abstract: Data from data sources may be processed at an edge device. The edge device may generate a local processing result, filter the data, and/or prioritize the data. Accordingly, data is transmitted from the edge device to the data platform, where it may be processed further. For example, a local processing result may be processed at the data platform, such that processing is performed without all of the data source data. In examples, at least a part of such data may remain at an edge device. The edge device may maintain a manifest of data stored by the edge device. The data platform may generate an aggregated manifest using manifests from associated edge devices, such that it may be determined where data is stored. As a result, the data platform may redirect requests to an associated edge device when it is determined that requested data is remote from the data platform.

Abstract: A computing device is provided, including a logic subsystem with one or more processors, and memory storing instructions executable by the logic subsystem. These instructions are executed to obtain one or more source images, segment the one or more source images to generate a plurality of segments, determine a priority order for the plurality of segments, and transmit the plurality of segments to a remote computing device in the priority order. The plurality of segments are spatial components generated by spatial decomposition of the one or more source images and/or frequency components that are generated by frequency decomposition of the one or more source images. A remote computing device may receive these components in priority order, and perform certain algorithms on individual components without waiting for the entire image to upload.

Abstract: This disclosure provides a machine learning technique to predict a protein characteristic. A first training set is created that includes, for multiple proteins, a target feature, protein sequences, and other information about the proteins. A first machine learning model is trained and then used to identify which of the features are relevant as determined by feature importance or causal relationships to the target feature. A second training set is created with only the relevant features. Embeddings generated from the protein sequences are also added to the second training set. The second training set is used to train a second machine learning model. The first and second machine learning models may be any type of regressors. Once trained, the second machine learning model is used to predict a value for the target feature for an uncharacterized protein. The model of this disclosure provides 91% accuracy in predicting an ideal digestibility score.

Abstract: Data from data sources may be processed at an edge device. The edge device may generate a local processing result, filter the data, and/or prioritize the data. Accordingly, data is transmitted from the edge device to the data platform, where it may be processed further. For example, a local processing result may be processed at the data platform, such that processing is performed without all of the data source data. In examples, at least a part of such data may remain at an edge device. The edge device may maintain a manifest of data stored by the edge device. The data platform may generate an aggregated manifest using manifests from associated edge devices, such that it may be determined where data is stored. As a result, the data platform may redirect requests to an associated edge device when it is determined that requested data is remote from the data platform.

Abstract: Systems and methods for authoring workflows for processing data from a large-scale dataset include defining a metadata schema for the large-scale dataset, and receiving user input defining a workflow as a plurality of operations to be performed on the data. Each of the operations includes input metadata formatted according to the metadata schema. The input metadata describes input data to be processed by the operation and identifying a location for the input data in the data storage system, programmed instructions for performing an atomic operation on the input data to generate output data; and output metadata formatted according to the metadata schema. The output metadata describes the output data and identifying a location for the output data in the data storage system.

Abstract: A deep learning system is used to predict crop characteristics from inputs that include crop variety features, environmental features, and field management features. The deep learning system includes domain-specific modules for each category of features. Some of the domain-specific modules are implemented as convolutional neural networks (CNN) while others are implemented as fully-connected neural networks. Interactions between different domains are captured with cross attention between respective embeddings. Embeddings from the multiple domain-specific modules are concatenated to create a deep neural network (DNN). The prediction generated by the DNN is a characteristic of the crop such as yield, height, or disease resistance. The DNN can be used to select a crop variety for planting in a field. For a crop that is planted, the DNN may be used to select a field management technique.

Abstract: A computing system measures terrain coverage by: obtaining sample image data representing a multispectral image of a geographic region at a sample resolution; generating, based on the sample image data, an index array of pixels for a subject terrain in which each pixel has an index value that represents a predefined relationship between a first wavelength reflectance and a second wavelength reflectance; providing the index array to a trained calibration model to generate an estimated value based on the index array, the estimated value representing an estimated amount of terrain coverage within the geographic region for the subject terrain; and outputting the estimated value for the subject terrain. The trained calibration model may be trained based on training data representing one or more reference images of one or more training geographic regions containing the subject terrain at a higher resolution than the sample resolution.

Abstract: Techniques for optically detecting a subject chemical species within an atmospheric environment are disclosed. Image data is obtained representing multispectral imagery of a geographic region captured through the atmospheric environment. The image data includes an array of band-specific intensity values for each of a plurality of spectral bands, including a sample spectral band having increased sensitivity to the subject chemical species as compared to a plurality of reference spectral bands. A background reflectance map is generated that includes an array of inter-band intensity values in which each inter-band intensity value represents a filtered combination of band-specific intensity values of albedo-normalized arrays for a grouped subset of the plurality of reference spectral bands. The albedo-normalized array of band-specific intensity values for the sample spectral band is compared to the background reflectance map to obtain an index array of intensity variance values for the subject chemical species.

Abstract: A method for source attribution comprises receiving measurements of a chemical species at a spatially distributed sensor array for a given set of spatially positioned emission sources in a physical environment using a dispersion model. Based on the received measurements, a concentration field is mapped from the emission sources to the sensor array using a forward operator. For each emission source, a likelihood data set is evaluated at least by fitting an emission rate of the chemical species using a regression model based on the mapped concentration field and real-world, runtime measurements from the sensor array. A posterior data set is evaluated based at least on the evaluated likelihood data set and historical data for the physical environment. For each sensor of the sensor array, estimated emission rates and contribution rankings for emission sources are determined and output based on the evaluation of the posterior data set.

Abstract: A method for pollutant sensor placement for pollutants from point sources is described. Data about environmental characteristics for a geographic region are received from a plurality of environmental sensors. The geographic region includes pollutant sources that emit a pollutant. The received data from one or more of the plurality of environmental sensors are transformed into common data having a common spatial and temporal discretization across the geographic region. Predicted emission plumes are generated for the pollutant sources within the geographic region that identify pollutant detection regions for the pollutant when the pollutant is emitted by the pollutant sources using the common data. Sensor locations for a plurality of pollutant sensors are greedily selected across the common spatial and temporal discretization according to a number of predicted emission plumes that are detectable by the plurality of pollutant sensors.

Abstract: A computing device has an energy storage device system with multiple energy storage devices. Various different criteria are used to determine which one or more of the multiple energy storage devices to charge or discharge at any given time to provide power to the computing device. The criteria can include characteristics of the energy storage devices as well as hardware and/or physical characteristics of the computing device, characteristics of the energy storage devices and/or the computing device that change while the computing device operates, and predicted behavior or usage of the computing device. These criteria are evaluated during operation of the computing device, and the appropriate energy storage device(s) from which to draw power or to charge at any given time based on these criteria are determined.

Abstract: Synthetic molecular tags are placed on an item at various points in a supply chain to create a molecular record of movement through the supply chain. Associations between each unique synthetic molecular tag and individual locations in the supply chain are stored in an electronic record which may be maintained in the cloud. The synthetic molecular tags are collected from the item and sequenced to determine movement of the item through the supply chain by reference to the electronic record. The synthetic molecular tags can be used for identifying recalled items based on locations in the supply chain associated with a recall. The synthetic molecular tags may be polynucleotides such as deoxyribose nucleic acid (DNA). The item may be any type of item including food.

Abstract: A computer system that includes a plurality of compute clusters that are located at different geographical locations. Each compute cluster is powered by a local energy source at a geographical location of that compute cluster. Each local energy source has a pattern of energy supply that is variable over time based on an environmental factor. The computer system further includes a server system that executes a global scheduler that distributes virtual machines that perform compute tasks for server-executed software programs to the plurality of compute clusters of the distributed compute platform. To distribute virtual machines for a target server-executed software program, the global scheduler is configured to select a subset of compute clusters that have different complementary patterns of energy supply such that the subset of compute clusters aggregately provide a target compute resource availability for virtual machines for the target server-executed software program.

Abstract: A method for pollutant sensor placement is described. Data about environmental characteristics across a geographic region is received from a plurality of environmental sensors. The geographic region includes one or more pollutant sources that emit a pollutant. The received data is transformed from one or more of the plurality of environmental sensors into common data having a common grid across the geographic region. The geographic region is divided into a plurality of sub-regions based on the common data. Locations within the geographic region are determined for placement of pollutant sensors based on estimated dispersion of the pollutant through the plurality of sub-regions.

Abstract: Data from data sources may be processed at an edge device. The edge device may generate a local processing result, filter the data, and/or prioritize the data. Accordingly, data is transmitted from the edge device to the data platform, where it may be processed further. For example, a local processing result may be processed at the data platform, such that processing is performed without all of the data source data. In examples, at least a part of such data may remain at an edge device. The edge device may maintain a manifest of data stored by the edge device. The data platform may generate an aggregated manifest using manifests from associated edge devices, such that it may be determined where data is stored. As a result, the data platform may redirect requests to an associated edge device when it is determined that requested data is remote from the data platform.

Abstract: A computer implemented method includes obtaining data for raw image frames captured by a moving camera. The raw image frames are indexed geographically, and a graph is created from the multiple raw image frames. The graph includes image frames as vertices and edges that represent image frames having overlapping image information. The method further includes skipping frames based on the amount of overlap, determining a frame having an interesting feature, using the graph to find additional raw image frames that have the interesting feature, combining multiple raw image frames to form a unique image frame, and transmitting the unique image frame.

Abstract: A computing device is provided, including a logic subsystem with one or more processors, and memory storing instructions executable by the logic subsystem. These instructions are executed to obtain one or more source images, segment the one or more source images to generate a plurality of segments, determine a priority order for the plurality of segments, and transmit the plurality of segments to a remote computing device in the priority order. The plurality of segments are spatial components generated by spatial decomposition of the one or more source images and/or frequency components that are generated by frequency decomposition of the one or more source images. A remote computing device may receive these components in priority order, and perform certain algorithms on individual components without waiting for the entire image to upload.

Abstract: A computing device is provided, including a logic subsystem with one or more processors, and memory storing instructions executable by the logic subsystem. These instructions are executed to obtain one or more source images, segment the one or more source images to generate a plurality of segments, determine a priority order for the plurality of segments, and transmit the plurality of segments to a remote computing device in the priority order. The plurality of segments are spatial components generated by spatial decomposition of the one or more source images and/or frequency components that are generated by frequency decomposition of the one or more source images. A remote computing device may receive these components in priority order, and perform certain algorithms on individual components without waiting for the entire image to upload.

Abstract: In the embodiment a determination is made, for one or more applications being executed by the computing system, of an amount of the first or second memory being used by the one or more applications. Based on the determination, a portion of the memory resources of the third memory are configured to function with the first or second memory when it is determined that the amount of the first or second memory being used by the one or more applications is not sufficient for the memory needs of the one or more applications and a portion of the memory resources of the third memory are removed from functioning with the first or second memory when it is determined that the amount of the first or second memory being used by the one or more applications is more than is needed for the memory needs of the one or more applications.