Michele Ceriotti

Edit profile

michele.ceriotti@epfl.ch +41 21 693 29 39 http://cosmo.epfl.ch/

Google Scholar ID

+41 21 693 29 39
EPFL > STI > STI-SMX > SMX-ENS

+41 21 693 29 39
EPFL > VPA-AVP-DLE > AVP-DLE-EDOC > EDMX-ENS

EPFL STI IMX COSMO
MXG 337 (Bâtiment MXG)
Station 12
1015 Lausanne

+41 21 693 29 39
Office: MXG 337
EPFL > STI > IMX > COSMO

Web site: Web site: https://cosmo.epfl.ch/

+41 21 693 29 39
EPFL > STI > IMX > IMX-GE

+41 21 693 29 39
EPFL > STI > STI-DEC > STI-DIR

+41 21 693 29 39
EPFL > VPA-AVP-DLE > AVP-DLE-EDOC > EDPY-ENS

vCard
Administrative data

Fields of expertise

Atomistic computer simulations, statistical mechanics, machine learning, molecular dynamics, nuclear quantum effects, molecular materials, nucleation.

Biography

Michele Ceriotti received his Ph.D. in Physics from ETH Zürich. He spent three years in Oxford as a Junior Research Fellow at Merton College. Since 2013 he leads the laboratory for Computational Science and Modeling, in the institute of Materials at EPFL, that focuses on method development for atomistic materials modeling based on statistical mechanics and machine learning. He is one of the core developers of several open-source software packages, including http://ipi-code.org and http://chemiscope.org, and proudly serves the atomistic modeling community as an associate editor of the Journal of Chemical Physics, as a moderator of the physics.chem-ph section of the arXiv, and as an editorial board member of Physical Review Materials.

Publications

Infoscience publications

2025

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

D. Suman; J. Nigam; S. Saade; P. Pegolo; H. Türk et al.

Journal of Chemical Theory and Computation. 2025. DOI : 10.1021/acs.jctc.5c00522.

Michele Ceriotti

Fields of expertise

Biography

Publications

Infoscience publications

2025

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

Fast and flexible long-range models for atomistic machine learning

PLUMED Tutorials: A collaborative, community-driven learning ecosystem

Mathematical Analysis and Optimization of Features for Atomistic Machine Learning

Advancing understanding and practical performance of machine learning interatomic potentials

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

2024

Probing the effects of broken symmetries in machine learning

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

Uncertainty quantification by direct propagation of shallow ensembles

Prediction rigidities for data-driven chemistry

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

Wigner kernels: Body-ordered equivariant machine learning without a basis

Modeling the ferroelectric phase transition in barium titanate with DFT accuracy and converged sampling

Thermal conductivity of Li 3 PS 4 solid electrolytes with ab initio accuracy

Surface segregation in high-entropy alloys from alchemical machine learning

Electronic Excited States from Physically Constrained Machine Learning

Completeness of Atomic Structure Representations

Mechanism of Charge Transport in Lithium Thiophosphate

Efficient and insightful descriptors for representing molecular and material space

Integrating symmetry and physical constraints into atomic-scale machine learning

Teaching & PhD

Teaching

PhD Students

Past EPFL PhD Students

Courses

Introduction to atomic-scale modeling

Statistical mechanics

Statistical methods in atomistic computer simulations

Lecture series on scientific machine learning

All postal addresses and positions