skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Modeling Time Series Data with Ordinary Differential Equations and Neural Networks

Abstract

This suite of code learns neural network models to emulate the dynamics of time series data. To do so, it learns a set of "neural shape functions" that provide a common vocabulary for expressing the various dynamics operators. The code is implemented in Python and TensorFlow.

Developers:
 [1];  [2]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  2. UC Merced
Release Date:
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
Python
Version:
0.0.1
Licenses:
MIT License
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)

Primary Award/Contract Number:
AC52-07NA27344
Code ID:
31120
Site Accession Number:
989386
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Country of Origin:
United States

Citation Formats

Desautels, Thomas, Reeves, Majerle, and USDOE National Nuclear Security Administration. Modeling Time Series Data with Ordinary Differential Equations and Neural Networks. Computer software. https://www.osti.gov//servlets/purl/1570343. Vers. 0.0.1. USDOE National Nuclear Security Administration (NNSA). 9 Aug. 2019. Web. doi:10.11578/dc.20191011.2.
Desautels, Thomas, Reeves, Majerle, & USDOE National Nuclear Security Administration. (2019, August 9). Modeling Time Series Data with Ordinary Differential Equations and Neural Networks (Version 0.0.1) [Computer software]. https://www.osti.gov//servlets/purl/1570343. doi:10.11578/dc.20191011.2.
Desautels, Thomas, Reeves, Majerle, and USDOE National Nuclear Security Administration. Modeling Time Series Data with Ordinary Differential Equations and Neural Networks. Computer software. Version 0.0.1. August 9, 2019. https://www.osti.gov//servlets/purl/1570343. doi:10.11578/dc.20191011.2.
@misc{osti_1570343,
title = {Modeling Time Series Data with Ordinary Differential Equations and Neural Networks, Version 0.0.1},
author = {Desautels, Thomas and Reeves, Majerle and USDOE National Nuclear Security Administration},
abstractNote = {This suite of code learns neural network models to emulate the dynamics of time series data. To do so, it learns a set of "neural shape functions" that provide a common vocabulary for expressing the various dynamics operators. The code is implemented in Python and TensorFlow.},
url = {https://www.osti.gov//servlets/purl/1570343},
doi = {10.11578/dc.20191011.2},
year = {2019},
month = {8},
note =
}

Software:
Publicly Accessible Repository
https://github.com/tadesautels/PSINN

Save / Share: