June 12, 2020 Software Open Access

Olivier Pannekoucke

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3891101</identifier>
  <creators>
    <creator>
      <creatorName>Olivier Pannekoucke</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-3249-2818</nameIdentifier>
      <affiliation>INPT-ENM, UMR CNRS CNRM 3589, CERFACS</affiliation>
    </creator>
  </creators>
  <titles>
    <title>opannekoucke/pdenetgen: pde-netgen-GMD</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <dates>
    <date dateType="Issued">2020-06-12</date>
  </dates>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3891101</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/opannekoucke/pdenetgen/tree/1.0.1</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3891100</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0.1</version>
  <rightsList>
    <rights rightsURI="http://www.cecill.info/licences/Licence_CeCILL-B_V1-en.html">CeCILL-B Free Software License Agreement</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Bridging physics and deep learning is a topical challenge. While deep learning frameworks open avenues in physical science, the design of physically-consistent deep neural network architectures is an open issue. In the spirit of physics-informed NNs, PDE-NetGen package provides new means to automatically translate physical equations, given as PDEs, into neural network architectures. PDE-NetGen combines symbolic calculus and a neural network generator. The later exploits NN-based implementations of PDE solvers using Keras. With some knowledge of a problem, PDE-NetGen is a plug-and-play tool to generate physics-informed NN architectures. They provide computationally-efficient yet compact representations to address a variety of issues, including among others adjoint derivation, model calibration, forecasting, data assimilation as well as uncertainty quantification.&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Olivier Pannekoucke and Ronan Fablet. &amp;quot;&lt;a href="https://doi.org/10.5194/gmd-2020-35"&gt;PDE-NetGen 1.0: from symbolic PDE representations of physical processes to trainable neural network representations&lt;/a&gt;&amp;quot;, Geoscientific Model Development (2020) https://doi.org/10.5194/gmd-2020-35&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;&lt;strong&gt;Description of the version&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;Version of the package based on tensorflow.keras, where neural network can be generated by using &lt;code&gt;TrainableScalar&lt;/code&gt; or exogenous network.&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Examples&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;As an illustration, the workflow is first presented for the 2D diffusion equation, then applied to the data-driven and physics-informed identification of uncertainty dynamics for the Burgers equation.&lt;/p&gt;</description>
  </descriptions>
</resource>