California Institute of Technology

Toyota Research Institute, Inc.

University of California

Santosh K Suram

John M Gregoire

Lan Zhou

Muratahan Aykol

Aniketa A Shinde

Jian Jin

Chengxiang Xiang

Patrick Kenichi Herring

Slobodan Mitrovic

Dan W Guevarra

Joel A Haber

Martin R Marcin

Paul F Newhouse

Kevin S Kan

Linda Hung

Brian Rohr

Helge Stein

An oxygen evolution reaction catalyst is a ternary metal oxide that includes Mn and is represented by MnSbOin the rutile crystal phase and MMnOwhere M is selected from the group consisting of Ca, Ni, Sr, Zn, Mg, Ni, Ba, Co and where u/(u+v) is greater than 33%.

Oxygen evolution reaction catalysis

One aspect of the disclosure relates to systems and methods for determining probabilities of successful synthesis of materials in the real world at one or more points in time. The probabilities of successful synthesis of materials in the real world at one or more points in time can be determined by representing the materials and their pre-defined relationships respectively as nodes and edges in a network form, and computation of the parameters of the nodes in the network as input to a classification model for successful synthesis. The classification model being configured to determine probabilities of successful synthesis of materials in the real world at one or more points in time.

Methods for predicting likelihood of successful experimental synthesis of computer-generated materials by combining network analysis and machine learning

A synthesis machine for preparation of a targeted inorganic material for recommended synthesis by a computer program that determines optimal solid-state methods for synthesis of an inorganic material. The computational method involves inputting a target inorganic material, querying structural data and thermodynamic data for the target inorganic material, enumerating possible synthetic reactions to construct a synthetic reaction database with a viable subset of the possible synthetic methods. The routine generates a nucleation metric and competition metric that are combined to provide recommended synthetic methods. The output for each of the recommended syntheses are input into a robotic synthesis machine where the delivery of reactants, reaction conditions, and analysis of extent of reaction, and product quality is controlled by a processor.

Autonomous inorganic material synthesis machine

A composition of matter includes an n-type semiconductor. At least a portion of the semiconductor has the crystal structure of the chemical compound represented by FeWO. The portion of the semiconductor having the crystal structure of FeWOincludes iron and tungsten. A photoanode can have a light-absorbing layer that includes or consists of the semiconductor. A solar fuels generator can include the photoanode.

Semiconductor suitable for use in photoanode

Methods and systems described herein concern machine-learning-assisted materials discovery. One embodiment selects a candidate sample set including a plurality of compositions and performs the following operations iteratively: (1) selects an acquisition sample set, (2) performs a dark electrocatalyst experiment or a photo-electrocatalyst experiment on the compositions in the acquisition sample set to determine one or more properties, (3) trains a machine learning model using the one or more properties, and (4) predicts, based at least in part on one or more outputs of the machine learning model, the one or more properties for one or more compositions in a test sample set including compositions on which an experiment has not yet been performed. When one or more predetermined termination criteria have been satisfied, the embodiment also identifies one or more compositions in the candidate sample set for which the one or more properties satisfy predetermined performance criteria.

Methods and systems for machine-learning-assisted discovery of dark electrocatalysts and photo-electrocatalysts

Various samples are generated on a substrate. The samples each includes or consists of one or more analytes. In some instances, the samples are generated through the use of gels or through vapor deposition techniques. The samples are used in an instrument for screening large numbers of analytes by locating the samples between a working electrode and a counter electrode assembly. The instrument also includes one or more light sources for illuminating each of the samples. The instrument is configured to measure the photocurrent formed through a sample as a result of the illumination of the sample.

Generation and analysis of chemical compound libraries

Growing community of inventors

Pasadena, CA, United States of America

Santosh K Suram