January 31, 2024 Dataset Open Access

Fiedler, Lenz; Cangi, Attila

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">10.14278/rodare.2724</identifier>
  <creators>
    <creator>
      <creatorName>Fiedler, Lenz</creatorName>
      <givenName>Lenz</givenName>
      <familyName>Fiedler</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-8311-0613</nameIdentifier>
      <affiliation>CASUS / HZDR</affiliation>
    </creator>
    <creator>
      <creatorName>Cangi, Attila</creatorName>
      <givenName>Attila</givenName>
      <familyName>Cangi</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-9162-262X</nameIdentifier>
      <affiliation>CASUS / HZDR</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Retrained Models and Scripts for Aluminum at 298K and 933K</title>
  </titles>
  <publisher>Rodare</publisher>
  <publicationYear>2024</publicationYear>
  <dates>
    <date dateType="Issued">2024-01-31</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://rodare.hzdr.de/record/2724</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsIdenticalTo">https://www.hzdr.de/publications/Publ-38719</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.14278/rodare.2723</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/rodare</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;&lt;strong&gt;Retrained Models and Scripts for Aluminum at 298K and 933K&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;&lt;em&gt;Authors&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;- Fiedler, Lenz (HZDR/CASUS)&lt;br&gt;
- Cangi, Attila (HZDR/CASUS)&lt;/p&gt;

&lt;p&gt;Affiliations:&lt;/p&gt;

&lt;p&gt;HZDR - Helmholtz-Zentrum Dresden-Rossendorf&lt;br&gt;
CASUS - Center for Advanced Systems Understanding&lt;/p&gt;

&lt;p&gt;&lt;em&gt;Data set description&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;This data sets contains models, scripts and inference results for aluminum at room temperature and the melting point. Training data, hyperparameters and general methodology follow Ref. [1]. The models here are retrained versions of the ones discussed in this publication, and therefore retrained versions of the models contained in Ref. [2]. As such, data from Ref. [2] has been used. Only a subset of models contained in Ref. [1] have been retrained, namely the room temperature model, one liquid and one solid melting point model with four training snapshot each, and the final melting point hybrid model (six training snapshots per phase). Furthermore, for both the hybrid melting temperature model and the room temperature model, multiple models with different initializations were trained.&lt;/p&gt;

&lt;p&gt;All models were trained with the MALA code [3] version 1.2.1. They show better accuracy than their original counterparts, as they were trained using the inter-snapshot shuffling algorithm first discussed for the MALA code in Ref. [4].&lt;/p&gt;

&lt;p&gt;[1] - &amp;quot;Accelerating finite-temperature Kohn-Sham density functional theory with deep neural networks&amp;quot;, Physical Review B, doi.org/10.1103/PhysRevB.104.035120&lt;br&gt;
[2] - &amp;quot;RODARE&amp;quot;, doi.org/10.14278/rodare.2485 (v1.0.0)&lt;br&gt;
[3] - &amp;quot;MALA&amp;quot;, Zenodo, doi.org/10.5281/zenodo.5557254&lt;br&gt;
[4] - &amp;quot;Machine learning the electronic structure of matter across temperatures&amp;quot;, Physical Review B, doi.org/10.1103/PhysRevB.108.125146&lt;/p&gt;

&lt;p&gt;&lt;em&gt;Contents&lt;/em&gt;&lt;/p&gt;

&lt;p&gt;- The models themselves, labeled as either Al298K or Al933K, given as one .zip file per model&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;- For 933K, additionally &amp;quot;liquid&amp;quot;, &amp;quot;solid&amp;quot; and &amp;quot;hybrid&amp;quot; denotes the training data set&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;- For ensembles, a running index denotes the number in the ensemble&lt;br&gt;
- Inference results, given as a single .zip file&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;- For all models, band energy and total free energy results are given in the .csv format&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;&amp;nbsp;&amp;nbsp; &amp;nbsp;- The columns in these files correspond to &amp;quot;Calculated via DFT LDOS&amp;quot;, &amp;quot;Calculated via ML-DFT LDOS&amp;quot;, &amp;quot;Calculated via Kohn-Sham system&amp;quot;, respectively&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;- For some models, additionally the predicted electronic density and density of states on select snapshots is given&lt;br&gt;
- Shuffling, training and testing scripts, given as a single .zip file&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;- Scripts are ready-to-use with suitable MALA installation, however, correct data paths have to be filled in&lt;br&gt;
&amp;nbsp;&amp;nbsp; &amp;nbsp;&lt;br&gt;
&amp;nbsp;&amp;nbsp;&amp;nbsp;&lt;/p&gt;</description>
  </descriptions>
</resource>