Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for electrical power grid simulation. One of the methods includes obtaining a state-transition matrix model of an electrical power grid and executing a simulation of electric power grid behaviors by executing the state-transition matrix model using a parallel processing device that includes multiple cores.

Abstract: Disclosed implementations relate to automatically generating and providing guidance for navigating HCIs to carry out semantically equivalent/similar computing tasks across different computer applications. In various implementations, a domain of a first computer application that is operable using a first HCI may be used to select a domain model that translates between an action space of the first computer application and another space. Based on the selected domain model, a domain-agnostic action embedding—representing actions performed previously using a second HCI of a second computer application to perform a semantic task—may be processed to generate probability distribution(s) over actions in the action space of the first computer application. Based on the probability distribution(s), actions may be identified that are performable using the first computer application—these actions may be used to generate guidance for navigating the first HCI to perform the semantic task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image segmentation and chemical analysis using machine learning. In some implementations, a system obtains a hyperspectral image that includes a representation of an object. The system segments the hyperspectral image to identify regions of a particular type on the object. The system generates a set of feature values derived from image data for different wavelength bands that is located in the hyperspectral image in the identified regions of the particular type. The system generates a prediction of a level of one or more chemicals in the object based on an output produced by a machine learning model in response to the set of feature values being provided as input to the machine learning model. The system provides data indicating the prediction of the level of the one or more chemicals in the object.

Abstract: Techniques for selecting a spectroscopic light source include obtaining a light source dataset and a spectroscopic dataset, initializing a genetic algorithm, selecting a first individual solution and a second individual solution from an initial generation of solutions, generating a new individual solution from the first and second individual solutions by combining their respective chromosome encodings, evaluating a specificity of the new individual solution to a target material, adding the new individual solution to a new generation of solutions, populating the new generation of solutions with a plurality of additional individual solutions, generating one or more descendent generations of solutions by iterating the genetic algorithm, selecting one or more implementation individual solutions exhibiting a threshold specificity to the target material, and outputting the one or more implementation individual solutions.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a machine-learning model for predicting event tags. The system obtains asset data for an electric power distribution system in a geographic area. The asset data includes: for each of a plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset. The system further obtains sensor data for the electric power distribution system. The sensor data includes measurement data from a plurality of electric sensors. The system generates, by processing the asset data and the sensor data, partition data that includes, for each of the plurality of electrical assets, an assignment that assigns the electrical asset to one of a set of feeder networks.

Abstract: Disclosed herein are systems and methods for objectively characterizing machine-learning models including receiving first training data formatted to be used in the training of a machine-learning model; receiving one or more challenge queries formatted to be run on the machine-learning model; generating, for the first training data, a plurality of associated training vectors that embed at least some of the first training data into a vector space; generating, for each of the one or more challenge queries, a plurality of associated challenge vectors that embed at least some of the challenge queries into the vector space; and determining, for each challenge query, a corresponding quality metric for the machine-learning model by determining a neighborhood density for each of the challenge queries in the vector space.

Abstract: A method includes providing, for presentation by a display, a user interface including graphics depicting one or more fields for receiving input for simulations of electrical grid scenarios. The method includes receiving input for a scenario including a proposed modification to the electrical grid and performing a simulation by modeling the input in a virtual model of an electrical grid. The method includes modifying the user interface to include graphics depicting: visualizations of results of the simulation for the scenario; and a menu of options for modifying the input. The method includes receiving a selection from the menu of options for modifying the input; performing a modified simulation by modeling the modified input in the virtual model of the electrical grid; and modifying the user interface to include graphics depicting visualizations of the results of the simulation compared to the results of the modified simulation.

Abstract: Platforms, systems, and methods for rapid fermenter sampling. According to one aspect, there is provided A rapid sampling system for obtaining samples from a fermentation system, comprising: a sample inlet fluidly connected to the fermentation system; a pump fluidly connected to the sample inlet and configured to draw a sample from the fermentation system; a first valve fluidly connected to an outlet of the pump; a second valve fluidly connected to a liquid nitrogen chamber; a multi-well filter plate, wherein an individual well of the multi-well filter plate is configured to collect and filter the sample; a motorized base operatively connected to the multi-well filter plate configured to adjust a position of the multi-well filter plate; and a control unit including one or more processors and one or more memories operatively connected to the pump, the first valve, the second valve, and the motorized base.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for determining whether a distributed energy resource is connected at a location. Electrical load data is obtained for a location over a time period. The electrical load data is analyzed to determine one or more signals from the electrical load data. The signals are compared to one or more load profiles for the location. Each load profile can indicate one or more baseline electrical patterns for the location. A likelihood that at least one distributed energy resource is in use at the location is determined based on the comparison. In response to determining that the likelihood is more than a threshold, one or more actions are performed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for operating sources of electricity in an electrical grid having a forecasting error rate are described. In some implementations, a method includes selecting a forecast horizon based on the forecasting error rate; performing an optimization process for dispatch planning of the electrical grid for the selected forecast horizon; automatically operating one or more power sources of the electrical grid in accordance with the dispatch planning for a first time increment; and performing an optimization process for dispatch planning for subsequent time increments within the selected horizon after the first time increment has elapsed.

Abstract: This disclosure describes a system and method for enabling an inverter to temporarily sustain fault current. One implementation is a system that includes an inverter having a plurality of transistors. A reservoir having an outlet channel is configured to contain a compressed gas. The outlet channel is arranged to direct the compressed gas towards a heatsink in thermal communication with one or more of the plurality of transistors. A control valve can be positioned between the reservoir and the outlet channel and a controller can be configured to detect an overcurrent event in the inverter and, in response, open the control valve. A transformer is electrically connected to an output of the inverter and configured to step down voltage from the inverter to a circuit being supplied by the inverter.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for filling gaps in electric grid models are enclosed. A method includes obtaining vector data representing first portions of paths of electric grid wires over a geographic region; converting the vector data to first raster image data that depicts an overhead view of the electric grid wires including a first set of line segments representing the first portions of the paths; processing the first raster image data using a gap filling model; obtaining, as output from the gap filling model, second raster image data including a second set of line segments corresponding to gaps included in the input raster image data and representing second portions of paths of the electric grid wires; and converting the second raster image data to vector data representing the first portions and the second portions of paths of the electric grid wires.

Abstract: Image data is obtained that indicates an extent to which one or more objects reflect, scatter, or absorb light at each of multiple wavelength bands, where the image data was collected while a conveyor belt was moving the object(s). The image data is preprocessed by performing an analysis across frequencies and/or performing an analysis across a representation of a spatial dimension. A set of feature values is generated using the image preprocessed image data. A machine-learning model generates an output using to the feature values. A prediction of an identity of a chemical in the one or more objects or a level of one or more chemicals in the object(s) is generated using the output. Data is output indicating the prediction of the identity of the chemical in the object(s) or the level of the one or more chemicals in at least one of the one or more objects.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for predicting connections in electric grid models are disclosed. A method includes obtaining geospatial data representing a geographic area that includes an electrical distribution system; and generating, from the geospatial data, asset data that represents characteristics of electrical distribution system assets. The asset data includes: load data representing electrical loads of the electrical distribution system; and node data representing nodes of the electrical distribution system. The method includes processing the asset data using a connection model that is configured to predict electrical connections between assets of the electrical distribution system; and obtaining, from the connection model; output data indicating predicted electrical connections between assets of the electrical distribution system. The geospatial data includes at least one of overhead imagery or street level imagery of the geographic area.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for mapping an electrical grid are disclosed. A method includes sampling multiple locations within a geographic region, executing a detection process for each location, the detection process including applying the set of images for the location as input to a machine learning (ML) model that is trained to identify electrical grid assets depicted within images taken from a combination of different perspectives and obtaining an output from the machine learning model that indicates whether a same electrical grid asset is identified in each of the images of the location. In response to an ML output that indicates a positive identification of the same electrical grid asset being depicted in a particular set of images of a particular location, the method further includes: selecting a number of sublocations within the region, and executing the detection process for each sublocation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a representation of an electric power grid. One of the methods includes obtaining respective datasets, identifying one or more predictive models for each of the respective datasets that are each configured to processes a category of data to generate an output that specifies a partial representation of the electric power grid; and aggregating the respective outputs in accordance with a set of predetermined rules to generate a final representation of the electric power grid.

Abstract: An inverter coupled to an electrical power grid characterizes the electrical power grid. The inverter outputs a plurality of electrical signals of different frequencies to the electrical power grid, measures responses of the electrical power grid to the plurality of electrical signals to obtain measurement data, and processes the measurement data to generate prediction data that characterizes one or more fault conditions of the electrical power grid. The inverter adjusts an operational setting of the inverter based on the prediction data. The operational setting affects a response of the electrical power grid to a fault condition.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatic generation of a supply chain simulation. The methods, systems, and apparatus include actions of obtaining supply chain data of a supply chain, generating a supply chain network graph that represents relationships between locations indicated by the supply chain data, determining classifications of the locations indicated by the supply chain data, determining agent rule models based on the supply chain data, and generating a supply chain simulation based on the supply chain network graph, the classifications of the locations, and the agent rule models.

Abstract: Systems and methods for managing chemical recycling processes include accessing characterization data of a feedstock, the characterization data comprising one or more spectra collected according to one or more spectroscopic methods. The methods include predicting, using the characterization data, a set of constituent materials included in the feedstock. The methods include predicting a material composition of the feedstock using the predicted set of constituent materials. The methods include identifying, at least in part using the predicted material composition of the feedstock, one or more target products. The methods include generating a set of chemical reaction schemas enabling a conversion of at least part of the feedstock into the one or more target products. The methods also include storing identifications of the material composition of the feedstock, the one or more target products, and the set of chemical reaction schemas in a data store.

Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus for mitigating wildfire ignition, the method including: obtaining first data identifying utility lines in a geographical region, obtaining second data characterizing operational and environmental factors related to the utility lines in the geographical region, determining a probability score that characterizes the likelihood of wildfire ignition caused by the utility lines in the geographical region, generating, based on the probability score, a cost function associating a wildfire-based cost to the current carried by the utility lines, and generating, using the cost function and a mixed-integer program solver, an output for the utility lines in the geographical region, where the output specifies an adjusted value of the current carried by the utility lines.