DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Identification and localization of rotational spectra using recurrent neural networks

Abstract

A method of identifying molecular parameters in a complex mixture may include receiving a set of combined transition frequencies and analyzing the set of combined transition frequencies using a first trained artificial neural network to generate a plurality of separated transition frequency sets. Each of the plurality of separated frequency sets may be analyzed using a second trained artificial neural network to generate a respective set of estimated spectral parameters. The method may include identifying a set of molecular parameters corresponding to the set of separated transition frequencies.

Inventors:
; ;
Issue Date:
Research Org.:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1987181
Patent Number(s):
11594304
Application Number:
16/146,970
Assignee:
UChicago Argonne, LLC (Chicago, IL)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G16 - INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS G16C - COMPUTATIONAL CHEMISTRY
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Patent
Resource Relation:
Patent File Date: 09/28/2018
Country of Publication:
United States
Language:
English

Citation Formats

Prozuments, Kirills, Zaleski, Daniel P., and Balaprakash, Prasanna. Identification and localization of rotational spectra using recurrent neural networks. United States: N. p., 2023. Web.
Prozuments, Kirills, Zaleski, Daniel P., & Balaprakash, Prasanna. Identification and localization of rotational spectra using recurrent neural networks. United States.
Prozuments, Kirills, Zaleski, Daniel P., and Balaprakash, Prasanna. Tue . "Identification and localization of rotational spectra using recurrent neural networks". United States. https://www.osti.gov/servlets/purl/1987181.
@article{osti_1987181,
title = {Identification and localization of rotational spectra using recurrent neural networks},
author = {Prozuments, Kirills and Zaleski, Daniel P. and Balaprakash, Prasanna},
abstractNote = {A method of identifying molecular parameters in a complex mixture may include receiving a set of combined transition frequencies and analyzing the set of combined transition frequencies using a first trained artificial neural network to generate a plurality of separated transition frequency sets. Each of the plurality of separated frequency sets may be analyzed using a second trained artificial neural network to generate a respective set of estimated spectral parameters. The method may include identifying a set of molecular parameters corresponding to the set of separated transition frequencies.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {2}
}

Works referenced in this record:

Adaptive filtering neural network classifier
patent, June 1998


Automated assignment of rotational spectra using artificial neural networks
journal, September 2018


Artificial intelligence characterizes rotational spectroscopy
journal, September 2018


Spectral bio-imaging methods for cell classification
patent, November 1999


Microwave spectrometers
patent, August 1996