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: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying wildfire in satellite imagery. In some implementations, a server obtains a satellite image of a geographic region and a date corresponding to when the satellite image was generated. The server determines a number of pixels in the satellite image that are indicated as on fire. The server obtains satellite imagery of the geographic region from before the date. The server generates a statistical distribution from the satellite imagery. The server determines a likelihood that the satellite image illustrates fire based on a comparison of the determined number of pixels in the satellite image that are indicated as on fire to the generated statistical distribution. The server can compare the determined likelihood to a threshold. In response to comparing the determined likelihood to the threshold, the server provides an indication that the satellite image illustrates fire.

Abstract: Systems and methods for detecting a mechanical disturbance are disclosed. One of the method may comprise the operation steps including: transmitting, by a transmitter, a pulse at a preset frequency along a first cable; receiving, by a receiver, a plurality of signals, wherein each of the plurality of signals travels along the first cable and a second cable connected to the receiver for a corresponding span; calculating one or more differential phases, wherein each differential phase is calculated based on respective phases and the corresponding spans of two of the plurality of signals; and determining a localization of the mechanical disturbance based on the one or more differential phases.

Abstract: The technology relates to free-space optical communication systems that correct for errors in tracking and pointing accuracy to maintain connection integrity. Such systems can both proactively and reactively correct for errors in tracking performance and pointing accuracy of terminals within the system. An aspect includes receiving information indicative of at least one external disturbance associated with a communication device. A determination is made for a proactive estimation indicative of a first error associated with an effect of the at least one external disturbance at a current timestep. A determination is made for a reactive estimation indicative of a second error associated with the effect of the at least one external disturbance at a previous timestep. A final control signal is determined based on the proactive estimation and the reactive estimation. A controller is able to actuate an optical assembly of the communication device based on the determined final control signal.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, for machine learning classification based on separate processing of multiple views. In some implementations, a system obtains image data for multiple images showing different views of an object. A machine learning model is used to generate a separate output based on each the multiple images individually. The outputs for the respective images are combined to generate a combined output. A predicted characteristic of the object is determined based on the combined output. An indication of the predicted characteristic of the object is provided.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for improved image segmentation using hyperspectral imaging. In some implementations, a system obtains image data of a hyperspectral image, the image data comprising image data for each of multiple wavelength bands. The system accesses stored segmentation profile data for a particular object type that indicates a predetermined subset of the wavelength bands designated for segmenting different region types for images of an object of the particular object type. The system segments the image data into multiple regions using the predetermined subset of the wavelength bands specified in the stored segmentation profile data to segment the different region types. The system provides output data indicating the multiple regions and the respective region types of the multiple regions.

Abstract: Methods, systems, and apparatus for generating a recipe for a concrete mixture, comprising: obtaining an optical characterization of a set of particles; determining, based on the optical characterization, physical characteristics of the set of particles; generating a multispherical approximation of the set of particles; selecting, based on the physical characteristics of the set of particles and from a database of performance rules, performance rules applicable to the set of particles; predicting performance of a proposed recipe for a concrete mixture formed from the set of particles by: determining a wet flowability rating of the proposed recipe based on the selected performance rules; and determining a dry packing rating of the proposed recipe based on the multispherical approximation; iteratively altering the proposed recipe and predicting performance of the altered proposed recipe until the predicted performance satisfies performance criteria to obtain a final recipe; and outputting the final recipe.

Abstract: Aspects of the disclosure provide a method of adjusting a plurality of phase shifters of an OPA. The method may include identifying, by one or more processors, one or more first subsets of phase shifters of the plurality of phase shifters based on an orthogonal set of functions; performing, by the one or more processors, one or more first dithers on the one or more first subsets of phase shifters of the plurality of phase shifters using one or more first frequencies of a predetermined set of frequencies; determining, by the one or more processors, one or more first corrections based on a first power output of the OPA resulting from the one or more first dithers; and adjusting, by the one or more processors, the one or more first subsets using the one or more first corrections, the adjustment resulting in a first set of corrected phase shifter values.

Abstract: An energy harvesting tape comprising a plurality of flexible layers. The plurality of flexible layers includes a solar cell layer configured to capture solar energy, a thermoelectric layer configured to capture thermal energy, one or more piezoelectric layers configured to capture mechanical energy; and an electrode layer configured to capture radiofrequency energy and to transmit a radiofrequency signal. The energy harvesting tape also includes one or more processing units on at least one of the plurality of flexible layers. The one or more processing units are configured to use the captured energy from the plurality of flexible layers to transmit the radiofrequency signal. The energy harvesting tape has a length, a width, and a thickness, where the length is greater than the width, and the width is greater than the thickness.

Abstract: This disclosure describes a system and method for generating a subsurface model representing lithological characteristics and attributes of the subsurface of a celestial body or planet. By automatically ingesting data from many sources, a machine learning system can infer information about the characteristics of regions of the subsurface and build a model representing the subsurface rock properties. In some cases, this can provide information about a region using inferred data, where no direct measurements have been taken. Remote sensing data, such as aerial or satellite imagery, gravimetric data, magnetic field data, electromagnetic data, and other information can be readily collected or is already available at scale.

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: A free-space optical communication system includes an optical phased array (OPA) photonic integrated chip, a transceiver photonic integrated chip, and one or more processors. The OPA chip includes a plurality of array elements and a plurality of phase shifters. The transceiver chip includes one or more transmitter components and one or more receiver components. The one or more processors are configured to transmit a first signal via the OPA chip and the transceiver chip, and receive a second signal via the OPA chip and the transceiver chip.

Abstract: An intermediate data set can be generated based on an image of a set of objects, where each of the set of objects includes a plastic. A predicted chemometric property can be generated by inputting the intermediate data set to a machine-learning model. The chemometric property can be of a physical output pyrolysis oil produced by performing a pyrolysis processing of the set of objects using a pyrolysis reactor. A result associated with the set of objects can be generated, where the result is based on or includes the predicted chemometric property.

Abstract: A tracking tag of a tracking system configured to receive, by one or more processors of the tracking tag, a first measurement collected by one or more sensors of the tracking tag; determine, by the one or more processors, a degree of similarity between the first measurement and a critical value; compare, by the one or more processors, the degree of similarity between the first measurement and the critical value to a first threshold value; modify, by the one or more processors, an initial time interval based on the comparison of the degree of similarity between the first measurement and the critical value to the first threshold to determine a modified time interval; and transmit, by the one or more processors, one or more beacon signals according to the modified time interval.

Abstract: According to some embodiments of the present disclosure, an intelligent tracking system is disclosed. The intelligent tracking system includes one or more passive tracking devices, an exciter, and a tracker. Each passive tracking device includes one or more transceivers and is energized by an electromagnetic frequency. In response to being energized each passive tracking device transmits a short message. The exciter emits the electromagnetic frequency. The tracker receives short messages from the one or more passive tracking devices and confirms the presence of the one or more passive tracking devices in a vicinity of the tracker based on the received messages.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for identification and re-identification of fish. In some implementations, first media representative of aquatic cargo is received. Second media based on the first media is generated, wherein a resolution of the second media is higher than a resolution of the first media. A cropped representation of the second media is generated. The cropped representation is provided to the machine learning model. In response to providing the cropped representation to the machine learning model, an embedding representing the cropped representation is generated using the machine learning model. The embedding is mapped to a high dimensional space. Data identifying the aquatic cargo is provided to a database, wherein the data identifying the aquatic cargo comprises an identifier of the aquatic cargo, the embedding, and a mapped region of the high dimensional space.

Abstract: The disclosure provides a method for adjusting an optical link alignment of a first communication device with a remote device. The method includes transmitting or receiving an optical signal; receiving one or more measurements of at least one environmental factor at the first communication device or the remote device; and receiving or detecting an apparent amount of alignment of the optical signal. Then, by one or more processors of the first communication device, determining an estimated error attributable to optical cross coupling and an actual amount of alignment of the optical signal based on the apparent amount of alignment and the estimated error. Next, adjusting the first communication device based on the actual amount of alignment to correct for optical cross coupling.

Abstract: A method of operating a communication network includes training a neural network and implementing the neural network to determine link availability. Training the neural network includes receiving first images and signal visibility data for first locations for one or more first nodes in the communication network, generating training data based on the first images and the signal visibility data, and training the neural network using the training data to output an attenuation category related to attenuation rate of a link based on a training image and a timestamp for the training image. Implementing the neural network includes receiving second images for second locations for one or more second nodes in the communication network, determining link availability based on the second images and outputs from the neural network, and operating the communication network based on the link availability.

Abstract: Photonic devices, photonic integrated circuits, optical elements, and techniques of making and using the same are described. A photonic device includes an input region adapted to receive an optical signal including a multiplexed channel characterized by a distinct wavelength, a dispersive region optically coupled with the input region to receive the optical signal, the dispersive region including a plurality of sub-regions defined by an inhomogeneous arrangement of a first material and a second material, and a plurality of output regions optically coupled with the input region via the dispersive region. The plurality of sub-regions can include an input channel section, one or more coupler sections, and one or more branching sections. The plurality of sub-regions together can configure the photonic device to demultiplex the optical signal and to isolate the multiplexed channel at a first output region of the plurality of output regions.

Abstract: A multilayer photonic device is described, including an input region configured to receive an input signal, a multilayer stack optically coupled with the input region to receive the input signal, and an output region optically coupled with the multilayer stack to output an output signal. The multilayer stack can include a first metastructured dispersive region disposed in a first patterned layer of the multilayer stack and a second metastructured dispersive region disposed in a second patterned layer of the multilayer stack and optically coupled with the first metastructured dispersive region. The first metastructured dispersive region and the second metastructured dispersive region can together structure the multilayer stack to generate the output signal in response to the input signal.