Fully Integrating Atomistic Modeling with Machine Learning

Información del proyecto

FIAMMA

Identificador del acuerdo de subvención: 101001890

DOI

10.3030/101001890

Fecha de la firma de la CE 18 Diciembre 2020

Fecha de inicio 1 Enero 2022

Fecha de finalización 31 Diciembre 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 998 015,00

Aportación de la UE

€ 1 998 015,00

Coordinado por

ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE
Switzerland

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Peer reviewed articles (30)

Fast evaluation of spherical harmonics with sphericart

Autores: F. Bigi, G. Fraux, N. J. Browning, and M. Ceriotti
Publicado en: Journal of Chemical Physics, Edición 159, 2023, Página(s) 064802, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0156307

Representing spherical tensors with scalar-based machine-learning models

Autores: M. Domina, F. Bigi, P. Pegolo, M. Ceriotti
Publicado en: The Journal of Chemical Physics, Edición 163, 2025, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0284802

A prediction rigidity formalism for low-cost uncertainties in trained neural networks

Autores: Filippo Bigi, Sanggyu Chong, Michele Ceriotti, Federico Grasselli
Publicado en: Machine Learning: Science and Technology, Edición 5, 2024, Página(s) 045018, ISSN 2632-2153
Editor: IOP
DOI: 10.1088/2632-2153/ad805f

Prediction rigidities for data-driven chemistry

Autores: Sanggyu Chong, Filippo Bigi, Federico Grasselli, Philip Loche, Matthias Kellner, Michele Ceriotti
Publicado en: Faraday Discussions, Edición 256, 2026, Página(s) 322-344, ISSN 1359-6640
Editor: Royal Society of Chemistry
DOI: 10.1039/d4fd00101j

Physics-Inspired Equivariant Descriptors of Nonbonded Interactions

Autores: Kevin K. Huguenin-Dumittan, Philip Loche, Ni Haoran, Michele Ceriotti
Publicado en: The Journal of Physical Chemistry Letters, Edición 14, 2023, Página(s) 9612-9618, ISSN 1948-7185
Editor: American Chemical Society
DOI: 10.1021/acs.jpclett.3c02375

Completeness of atomic structure representations

Autores: Jigyasa Nigam, Sergey N. Pozdnyakov, Kevin K. Huguenin-Dumittan, Michele Ceriotti
Publicado en: APL Machine Learning, Edición 2, 2024, ISSN 2770-9019
Editor: AIP Publishing LLC
DOI: 10.1063/5.0160740

Mechanism of Charge Transport in Lithium Thiophosphate

Autores: Lorenzo Gigli, Davide Tisi, Federico Grasselli, Michele Ceriotti
Publicado en: Chemistry of Materials, Edición 36, 2024, Página(s) 1482-1496, ISSN 0897-4756
Editor: American Chemical Society
DOI: 10.1021/acs.chemmater.3c02726

Unified theory of atom-centered representations and message-passing machine-learning schemes.

Autores: Jigyasa Nigam; Sergey Pozdnyakov; Guillaume Fraux; Michele Ceriotti
Publicado en: Journal of Chemical Physics, 2022, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.48550/arxiv.2202.01566

Exploring the Design Space of Machine Learning Models for Quantum Chemistry with a Fully Differentiable Framework

Autores: Divya Suman, Jigyasa Nigam, Sandra Saade, Paolo Pegolo, Hanna Türk, Xing Zhang, Garnet Kin-Lic Chan, Michele Ceriotti
Publicado en: Journal of Chemical Theory and Computation, Edición 21, 2025, Página(s) 6505-6516, ISSN 1549-9618
Editor: American Chemical Society
DOI: 10.1021/acs.jctc.5c00522

Resolving the body-order paradox of machine learning interatomic potentials

Autores: Sanggyu Chong, Tong Jiang, Michelangelo Domina, Filippo Bigi, Federico Grasselli, Joonho Lee, Michele Ceriotti
Publicado en: The Journal of Chemical Physics, Edición 164, 2026, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0303302

Predicting hot-electron free energies from ground-state data

Autores: Chiheb Ben Mahmoud, F. Grasselli, and M. Ceriotti
Publicado en: Physical Review B, 2022, ISSN 2469-9950
Editor: American Physical Society
DOI: 10.1103/physrevb.106.l121116

<tt>metatensor</tt> and <tt>metatomic</tt> : Foundational libraries for interoperable atomistic machine learning

Autores: Filippo Bigi, Joseph W. Abbott, Philip Loche, Arslan Mazitov, Davide Tisi, Marcel F. Langer, Alexander Goscinski, Paolo Pegolo, Sanggyu Chong, Rohit Goswami, Pol Febrer, Sofiia Chorna, Matthias Kellner, Michele Ceriotti, Guillaume Fraux
Publicado en: The Journal of Chemical Physics, Edición 164, 2026, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0304911

Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties

Autores: Jigyasa Nigam; Michael J. Willatt; Michele Ceriotti
Publicado en: Chemical Physics, Edición 1, 2022, Página(s) 156(1), 014115 (2022), ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0072784

Comparing the Latent Features of Universal Machine‐Learning Interatomic Potentials

Autores: Sofiia Chorna, Davide Tisi, Cesare Malosso, Wei Bin How, Michele Ceriotti, Sanggyu Chong
Publicado en: Advanced Intelligent Systems, Edición 8, 2026, ISSN 2640-4567
Editor: Wiley
DOI: 10.1002/aisy.202501497

Pushing the limits of unconstrained machine-learned interatomic potentials

Autores: Filippo Bigi, Paolo Pegolo, Arslan Mazitov, Jonathan Schmidt, Michele Ceriotti
Publicado en: Machine Learning: Science and Technology, Edición 7, 2026, Página(s) 035051, ISSN 2632-2153
Editor: IOP Publishing
DOI: 10.1088/2632-2153/ae6417

A foundation model for atomistic materials chemistry

Autores: Ilyes Batatia, Philipp Benner, Yuan Chiang, Alin M. Elena, Dávid P. Kovács, Janosh Riebesell, Xavier R. Advincula, Mark Asta, Matthew Avaylon, William J. Baldwin, Fabian Berger, Noam Bernstein, Arghya Bhowmik, Filippo Bigi, Samuel M. Blau, Vlad Cărare, Michele Ceriotti, Sanggyu Chong, James P. Darby, Sandip De, Flaviano Della Pia, Volker L. Deringer, Rokas Elijošius, Zakariya El-Machachi, Edvi
Publicado en: The Journal of Chemical Physics, Edición 163, 2025, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0297006

A universal machine learning model for the electronic density of states

Autores: Wei Bin How, Pol Febrer, Sanggyu Chong, Arslan Mazitov, Filippo Bigi, Matthias Kellner, Sergey Pozdnyakov, Michele Ceriotti
Publicado en: Digital Discovery, Edición 5, 2026, Página(s) 1635-1649, ISSN 2635-098X
Editor: Royal Society of Chemistry (RSC)
DOI: 10.1039/d5dd00557d

Fast and flexible long-range models for atomistic machine learning

Autores: Philip Loche, Kevin K. Huguenin-Dumittan, Melika Honarmand, Qianjun Xu, Egor Rumiantsev, Wei Bin How, Marcel F. Langer, Michele Ceriotti
Publicado en: The Journal of Chemical Physics, Edición 162, 2025, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0251713

Probing the effects of broken symmetries in machine learning

Autores: Marcel F Langer, Sergey N Pozdnyakov, Michele Ceriotti
Publicado en: Machine Learning: Science and Technology, Edición 5, 2024, Página(s) 04LT01, ISSN 2632-2153
Editor: IOP
DOI: 10.1088/2632-2153/ad86a0

Robustness of Local Predictions in Atomistic Machine Learning Models

Autores: Sanggyu Chong, Federico Grasselli, Chiheb Ben Mahmoud, Joe D. Morrow, Volker L. Deringer, Michele Ceriotti
Publicado en: Journal of Chemical Theory and Computation, Edición 19, 2023, Página(s) 8020-8031, ISSN 1549-9618
Editor: American Chemical Society
DOI: 10.1021/acs.jctc.3c00704

PET-MAD as a lightweight universal interatomic potential for advanced materials modeling

Autores: Arslan Mazitov, Filippo Bigi, Matthias Kellner, Paolo Pegolo, Davide Tisi, Guillaume Fraux, Sergey Pozdnyakov, Philip Loche, Michele Ceriotti
Publicado en: Nature Communications, Edición 16, 2025, ISSN 2041-1723
Editor: Nature Publishing Group
DOI: 10.1038/s41467-025-65662-7

Local invertibility and sensitivity of atomic structure-feature mappings

Autores: Sergey Pozdnyakov; Liwei Zhang; Christoph Ortner; Gábor Csányi; Michele Ceriotti
Publicado en: Open Research Europe, Edición 1, 2021, ISSN 2732-5121
Editor: Excellent Science
DOI: 10.12688/openreseurope.14156.1

Electronic Excited States from Physically Constrained Machine Learning

Autores: Edoardo Cignoni, Divya Suman, Jigyasa Nigam, Lorenzo Cupellini, Benedetta Mennucci, Michele Ceriotti
Publicado en: ACS Central Science, Edición 10, 2024, Página(s) 637-648, ISSN 2374-7943
Editor: American Chemical Society
DOI: 10.1021/acscentsci.3c01480

scikit-matter : A Suite of Generalisable Machine Learning Methods Born out of Chemistry and Materials Science

Autores: Alexander Goscinski, Victor Paul Principe, Guillaume Fraux, Sergei Kliavinek, Benjamin Aaron Helfrecht, Philip Loche, Michele Ceriotti, Rose Kathleen Cersonsky
Publicado en: Open Research Europe, Edición 3, 2024, Página(s) 81, ISSN 2732-5121
Editor: London, UK: F1000 Research Limited
DOI: 10.12688/openreseurope.15789.2

Electronic-Structure Properties from Atom-Centered Predictions of the Electron Density

Autores: Andrea Grisafi; Alan M. Lewis; Mariana Rossi; Michele Ceriotti
Publicado en: Journal of Chemical Theory and Computation, Edición 19, 2023, Página(s) 4451, ISSN 1549-9618
Editor: American Chemical Society
DOI: 10.1021/acs.jctc.2c00850

A Deep Learning Model for Chemical Shieldings in Molecular Organic Solids Including Anisotropy

Autores: Matthias Kellner, Jacob B. Holmes, Ruben Rodriguez-Madrid, Florian Viscosi, Yuxuan Zhang, Lyndon Emsley, Michele Ceriotti
Publicado en: The Journal of Physical Chemistry Letters, Edición 16, 2025, Página(s) 8714-8722, ISSN 1948-7185
Editor: American Chemical Society
DOI: 10.1021/acs.jpclett.5c01819

Adaptive energy reference for machine-learning models of the electronic density of states

Autores: Wei Bin How, Sanggyu Chong, Federico Grasselli, Kevin K. Huguenin-Dumittan, Michele Ceriotti
Publicado en: Physical Review Materials, Edición 9, 2025, ISSN 2475-9953
Editor: APS
DOI: 10.1103/physrevmaterials.9.013802

i-PI 3.0: A flexible and efficient framework for advanced atomistic simulations

Autores: Yair Litman, Venkat Kapil, Yotam M. Y. Feldman, Davide Tisi, Tomislav Begušić, Karen Fidanyan, Guillaume Fraux, Jacob Higer, Matthias Kellner, Tao E. Li, Eszter S. Pós, Elia Stocco, George Trenins, Barak Hirshberg, Mariana Rossi, Michele Ceriotti
Publicado en: The Journal of Chemical Physics, Edición 161, 2024, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0215869

"Thermal conductivity of <mml:math xmlns:mml=""http://www.w3.org/1998/Math/MathML""><mml:mrow><mml:msub><mml:mi>Li</mml:mi><mml:mn>3</mml:mn></mml:msub><mml:msub><mml:mi>PS</mml:mi><mml:mn>4</mml:mn></mml:msub></mml:mrow></mml:math> solid electrolytes with <i>ab initio</i> accuracy"

Autores: Davide Tisi, Federico Grasselli, Lorenzo Gigli, Michele Ceriotti
Publicado en: Physical Review Materials, Edición 8, 2024, ISSN 2475-9953
Editor: ACS
DOI: 10.1103/physrevmaterials.8.065403

Ranking the synthesizability of hypothetical zeolites with the sorting hat

Autores: B. A. Helfrecht, G. Pireddu, R. Semino, S. M. Auerbach, and M. Ceriotti
Publicado en: Digital Discovery, Edición 1, 2022, Página(s) 779, ISSN 2635-098X
Editor: Royal Society of Chemistry
DOI: 10.1039/d2dd00056c

Non-peer reviewed articles (2)

A smooth basis for atomistic machine learning

Autores: F. Bigi, K. K. Huguenin-Dumittan, M. Ceriotti, and D. E. Manolopoulos, J. Chem
Publicado en: Journal Of Chemical Physics, 2022, ISSN 0021-9606
Editor: American Institute of Physics
DOI: 10.1063/5.0124363

A data-driven interpretation of the stability of organic molecular crystals

Autores: R. K. Cersonsky, M. Pakhnova, E. A. Engel, and M. Ceriotti
Publicado en: Chemical Science, 2023, ISSN 2041-6520
Editor: Royal Society of Chemistry
DOI: 10.1039/d2sc06198h