Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
PiNN: Equivariant Neural Network Suite for Modeling Electrochemical Systems
Uppsala University, Disciplinary Domain of Science and Technology, Chemistry, Department of Chemistry - Ångström, Structural Chemistry.ORCID iD: 0000-0003-3931-6291
Uppsala University, Disciplinary Domain of Science and Technology, Chemistry, Department of Chemistry - Ångström, Structural Chemistry.
Uppsala University, Disciplinary Domain of Science and Technology, Chemistry, Department of Chemistry - Ångström, Structural Chemistry. Uppsala Univ, Wallenberg Initiat Mat Sci Sustainabil, S-75121 Uppsala, Sweden..
Uppsala University, Disciplinary Domain of Science and Technology, Chemistry, Department of Chemistry - Ångström, Structural Chemistry.
Show others and affiliations
2025 (English)In: Journal of Chemical Theory and Computation, ISSN 1549-9618, E-ISSN 1549-9626, Vol. 21, no 3, p. 1382-1395Article in journal (Refereed) Published
Abstract [en]

Electrochemical energy storage and conversion play increasingly important roles in electrification and sustainable development across the globe. A key challenge therein is to understand, control, and design electrochemical energy materials with atomistic precision. This requires inputs from molecular modeling powered by machine learning (ML) techniques. In this work, we have upgraded our pairwise interaction neural network Python package PiNN via introducing equivariant features to the PiNet2 architecture for fitting potential energy surfaces along with PiNet2-dipole for dipole and charge predictions as well as PiNet2-chi for generating atom-condensed charge response kernels. By benchmarking publicly accessible data sets of small molecules, crystalline materials, and liquid electrolytes, we found that the equivariant PiNet2 shows significant improvements over the original PiNet architecture and provides a state-of-the-art overall performance. Furthermore, leveraging on plug-ins such as PiNNAcLe for an adaptive learn-on-the-fly workflow in generating ML potentials and PiNNwall for modeling heterogeneous electrodes under external bias, we expect PiNN to serve as a versatile and high-performing ML-accelerated platform for molecular modeling of electrochemical systems.

Place, publisher, year, edition, pages
American Chemical Society (ACS), 2025. Vol. 21, no 3, p. 1382-1395
National Category
Materials Chemistry Computer Sciences Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:uu:diva-554781DOI: 10.1021/acs.jctc.4c01570ISI: 001409940900001PubMedID: 39883580Scopus ID: 2-s2.0-85216813378OAI: oai:DiVA.org:uu-554781DiVA, id: diva2:1952865
Funder
EU, Horizon 2020, 949012EU, European Research CouncilKnut and Alice Wallenberg Foundation, 2022-06725Swedish Research CouncilAvailable from: 2025-04-16 Created: 2025-04-16 Last updated: 2025-04-16Bibliographically approved

Open Access in DiVA

fulltext(5991 kB)26 downloads
File information
File name FULLTEXT01.pdfFile size 5991 kBChecksum SHA-512
45f7988e483e7483a6125172c74e375652b8cbb0ca17c8cb6e060b83061844c5f9801277b07ce52b8bdb605c6418e135da47c062dcfa387cd592f0d0bb450e5f
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Search in DiVA

By author/editor
Li, JichenKnijff, LisanneZhang, Zhan-YunAndersson, LinnéaZhang, Chao
By organisation
Structural Chemistry
In the same journal
Journal of Chemical Theory and Computation
Materials ChemistryComputer SciencesBioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar
Total: 28 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 45 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf