Evident Technologies, Inc.

Exxonmobil Upstream Research Company

Samsung Electronics Co., Ltd.

Raytheon Company

Leland Stanford Junior University

Exxonmobil Research and Engineering Company

Exxonmobil Technology and Engineering Company

Wei D Liu

Kuang-Hung Liu

Huseyin Denli

Cody J Macdonald

Daniel P Landry

Adam Z Peng

Michael LoCascio

Niranjan A Subrahmanya

Michael Locascio

Diego A Hernandez

Zuoyan Peng

Michael H Kovalski

Yi Cui

Alexander A Betin

Kalin Spariosu

Minsang Song

Jennifer Gillies

David Socha

Thomas A Badgwell

Victoria M Som De Cerff

D Braden Fitz-Gerald

A method and apparatus for automated seismic interpretation (ASI), including: obtaining trained models comprising a geologic scenario from a model repository, wherein the trained models comprise executable code; obtaining test data comprising geophysical data for a subsurface region; and performing an inference on the test data with the trained models to generate a feature probability map representative of subsurface features. A method and apparatus for machine learning, including: an ASI model; a training dataset comprising seismic images and a plurality of data portions; a plurality of memory locations, each comprising a replication of the ASI model and a different data portion of the training dataset; a plurality of data augmentation modules, each identified with one of the plurality of memory locations; a training module configured to receive output from the plurality of data augmentation modules; and a model repository configured to receive updated models from the training module.

Automated seismic interpretation systems and methods for continual learning and inference of geological features

A method and apparatus for machine learning for use with automated seismic interpretation include: obtaining input data; extracting patches from a pre-extraction dataset based on the input data; transforming data of a pre-transformation dataset based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and generating augmented data from the extracted patches and the transformed data. A method and apparatus for machine learning for use with automated seismic interpretation include: a data input module configured to obtain input data; a patch extraction module configured to extract patches from a pre-extraction dataset that is based on the input data; a data transformation module configured to transform data from a pre-transformation dataset that is based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and a data augmentation module configured to augment data from the extracted patches and the transformed data.

Data augmentation for seismic interpretation systems and methods

A method and apparatus for seismic interpretation including machine learning (ML). A method of training a ML system for seismic interpretation includes: preparing a collection of seismic images as training data; training an interpreter ML model to learn to interpret the training data, wherein: the interpreter ML model comprises a geologic objective function, and the learning is regularized by one or more geologic priors; and training a discriminator ML model to learn the one or more geologic priors from the training data. A method of hydrocarbon management includes: training the ML system for seismic interpretation; obtaining test data comprising a second collection of seismic images; applying the trained ML system to the test data to generate output; and managing hydrocarbons based on the output. A method includes performing an inference on test data with the interpreter and discriminator ML models to generate a feature probability map representative of subsurface features.

Training machine learning systems for seismic interpretation

A method to automatically interpret a subsurface feature within geophysical data, the method including: storing, in a computer memory, geophysical data obtained from a survey of a subsurface region; and extracting, with a computer, a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks, which are trained to relate the geophysical data to at least one subsurface feature, wherein the extracting includes fusing together outputs of the one or more fully convolutional neural networks.

Automated seismic interpretation using fully convolutional neural networks

Systems and methods are provided for using a Deep Reinforcement Learning (DRL) agent to provide adaptive tuning of process controllers, such as Proportional-Integral-Derivative (PID) controllers. The agent can monitor process controller performance, and if unsatisfactory, can attempt to improve it by making incremental changes to the tuning parameters for the process controller. The effect of a tuning change can then be observed by the agent and used to update the agent's process controller tuning policy. It has been unexpectedly discovered that providing adaptive tuning based on incremental changes in tuning parameters, as opposed to making changes independent of current values of the tuning parameters, can provide enhanced or improved control over a controlled variable of a process.

Adaptive PID controller tuning via deep reinforcement learning

A stretchable battery includes: a pouch; a metal barrier disposed in the pouch; and an electrode assembly disposed in the pouch and on the metal barrier, wherein the pouch and the electrode assembly each have a wavy shape including a plurality of peaks and valleys.

Stretchable battery and method of manufacturing the same

A lighting system includes at least one light emitting diode and a coating of matrix material having at least one glass-coated quantum dot in a base material. The at least one glass-coated quantum dot may be selected from at least one of a group II-VI materials, III-V materials, IV-VI materials, I-III-VI materials and combinations of such materials. The matrix material may be silicone, and the lighting system may include a light bulb replacement fixture including a threaded screw electrically connected to the light emitting diode.

Lighting system including LED with glass-coated quantum-dots

A laser gain medium. The novel laser gain medium includes a host material, a plurality of quantum dots dispersed throughout the host material, and a plurality of laser active ions surrounding each of the quantum dots. The laser active ions are disposed in close proximity to the quantum dots such that energy absorbed by the quantum dots is non-radiatively transferred to the ions via a Forster resonant energy transfer, thereby exciting the ions to produce laser output. In an illustrative embodiment, each quantum dot is surrounded by an external shell doped with the laser active ions.

Laser based on quantum dot activated media with forster resonant energy transfer excitation

A water-stable semiconductor nanocrystal complex and methods of making the same are provided. The water-stable semiconductor nanocrystal complex includes a semiconductor nanocrystal composition, a surfactant layer, and an outer layer. The outer layer and/or the surfactant layer can be cross-linked.

Water-stable semiconductor nanocrystal complexes and methods of making same

A semiconductor nanocrystal complex including a metal layer formed on the outer surface of a semiconductor nanocrystal core after synthesis of the semiconductor nanocrystal core and a method for preparing a nanocrystal complex comprising forming a metal layer on a semiconductor nanocrystal core after synthesis of the semiconductor nanocrystal core. The metal layer may passivate the surface of the semiconductor nanocrystal core and protect the semiconductor nanocrystal core from the effects of oxidation. Also provided is a semiconductor nanocrystal complex with a shell grown onto the metal layer formed on the semiconductor nanocrystal core. In this embodiment, the metal layer may prevent lattice mismatch between the semiconductor shell and the semiconductor nanocrystal core.

Semiconductor nanocrystal complexes comprising a metal coating and methods of making same

A semiconductor nanocrystal complex that is stable and has high luminescent quantum yield. The semiconductor nanocrystal complex has a semiconductor nanocrystal core of a III-V semiconductor nanocrystal material. A method of making a semiconductor nanocrystal complex is also provided. The method includes synthesizing a semiconductor nanocrystal core of a III-V semiconductor nanocrystal material, and forming a metal layer on the semiconductor nanocrystal core after synthesis of the semiconductor nanocrystal core.

III-V semiconductor nanocrystal complexes and methods of making same

A method of detecting target biological molecules in a target sample is provided. The method includes using spectral, temporal, and polarization characteristics of emitted light from water-stable semiconductor nanocrystal complexes to detect the presence of target biological molecules in a target sample.

Fluorescent lifetime biological detection and imaging using water-stable semiconductor nanocrystals

A method for preparing water-stable semiconductor nanocrystal complexes that can be stably coupled to tertiary molecules using a self-assembled coating of diblock polymers. The diblock polymers have hydrophilic ends containing hydrophilic functional groups and hydrophobic ends containing hydrophobic functional groups. The diblock polymers are assembled around a semiconductor nanocrystal having a lyophilic surface outer layer. The diblock polymers are further crosslinked via bridging molecules that link adjacent diblock polymers through the hydrophilic functional groups of the hydrophilic ends of the diblock polymers to form a semiconductor nanocrystal complex. The functional groups present on the outer surface of the amphiphilic diblock polymer may serve as attachment sites for coupling tertiary molecules to the semiconductor nanocrystal complex.

Growing community of inventors

Schenectady, NY, United States of America

Wei D Liu