Applied Materials, Inc.

X Development LLC

Allen Richard Zhao

Diana Xiaobing Ma

Yan Ye

Hongxu Ma

Vadim Tschernezki

Jie Jacquot

Artem Goncharuk

Peter K Loewenhardt

Kevin Forsythe Smith

Hiroji Hanawa

Peter Chang-Lin Hsieh

Xiancan Deng

Derek Werdenberg

Kenton Lee Prindle

Mehul B Naik

Gerald Z Yin

Cyrus Behroozi

Chun Yan

Jie Yuan

Dian Sugiarto

Philip M Salzman

Pavel Ionov

Tim Weidman

Gerald Zheyao Yin

Thomas Peter Hunt

Neil David Treat

Karen R Davis

Lance Co Ting Keh

Diana Xiabing Ma

Ronald Votel

Hong Shih

Phillip Yee

Benoit M Schillings

Li Xu

Joseph Hollis Sargent

Phil M Salzman

Danny Chien Lu

Chang-Lin Hsieh

Gearoid Murphy

Timothy R Webb

Shruti Badhwar

Alexander Holiday

Daisuke Tajima

Alex S Miller

Jerome Nowak

Philip M Saizman

Jonathan Gray Wilfong

Diosdado Banatao

Methods and systems for using multiple hyperspectral cameras sensitive to different wavelengths to predict characteristics of objects for further processing, including recycling, are described. The multiple hyperspectral images can be used to predict higher resolution spectra by using a trained machine learning model. The higher resolution spectra may be more easily analyzed to sort plastics into a recyclability category. The hyperspectral images may also be used to identify and analyze dark or black plastics, which are challenging for SWIR, MWIR, and other wavelengths. The machine learning model may also predict the base polymers and contaminants of plastic objects for recycling. The hyperspectral images may be used to predict recyclability and other characteristics using a trained machine learning model.

Sensor fusion approach for plastics identification

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.

Sample segmentation

A carbon dioxide (CO) sequestration sensor system includes an underground sub-assembly including one or more sensors configured to detect at least one attribute associated with COsequestration below a terranean surface; and an above-ground sub-assembly positionable on the terranean surface proximate the underground sub-assembly and including at least one controller communicably coupled to the one or more sensors.

Subterranean parameter sensing systems and methods

This disclosure describes a system and method for generating images and location data of a subsurface object using existing infrastructure as a source. Many infrastructure objects (e.g., pipes, cables, conduits, wells, foundation structures) are constructed of rigid materials and have a known shape and location. Additionally these infrastructure objects can have exposed portions that are above or near the surface and readily accessible. A signal generator can be affixed to the exposed portion of the infrastructure object, which induces acoustic energy, or vibrations in the object. The object with affixed signal generator can then be used as a source in performing a subsurface imaging of subsurface objects, which are not exposed.

Synthetic subterranean source

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.

Machine learning classification based on separate processing of multiple views

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. Lithological attributes and characteristics present in available geoscience data can be correlated with related remote sensing data using a machine learning model, which can then infer lithological attributes and characteristics for regions where remote sensing data is available, but geoscience data is not.

Subsurface lithological model with machine learning

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.

Segmentation to improve chemical analysis

This disclosure describes a system and method for generating images by performing TEM surveys using pre-existing infrastructure such as transmission lines, or power lines, and naturally occurring transients such as lightning strikes or load switching. A relatively inexpensive sensor array can be installed on overhead power lines (e.g., electrical transmission or sub-transmission lines) which can detect transients in the overhead power lines. Transients in the overhead power lines can cause the power lines to emit pulses of electromagnetic (EM) radiation, which propagate into the earth's subsurface. This sudden change in electromagnetic field in the subsurface can induce eddy currents, which in turn emit return EM radiation that can propagate back to the overhead power line and induce secondary voltage and current transients. The magnitude of these secondary transients, and their time delay from the original transient are influenced by the properties of the subsurface in which the eddy currents formed.

Electromagnetic surveys with power transmission lines

Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

Data band selection using machine learning

A system and method for automated lens adjustment for hyperspectral imaging is described. The system includes an image sensor and an electrically-controllable element arranged to set a spectral band for image capture by (i) selectively providing light for a selected spectral band or (ii) selectively filtering light to a selected spectral band. The system includes a tunable lens that is adjustable to change a focal length of the lens; and one or more data storage devices storing data that indicates different focus adjustment parameters corresponding to different spectral bands. The system includes a control system configured to perform operations including: selecting a spectral band; controlling the electrically-controllable element to set the spectral band for image capture; retrieving the focus adjustment parameter that corresponds to the spectral band; adjusting the lens based on the retrieved focus adjustment parameter; and capturing an image of the subject while the lens remains adjusted.

Automated lens adjustment for hyperspectral imaging

Growing community of inventors

Mountain View, CA, United States of America

Allen Richard Zhao