Publications related to Physics-Inspired Equivariant Descriptors of Nonbonded Interactions

Efficient and insightful descriptors for representing molecular and material space

Data-driven approaches have been applied to reduce the cost of accurate computational studies on materials, by using only a small number of expensive reference electronic structure calculations for a representative subset of the materials space, and using ...

EPFL2024

Encoding quantum-chemical knowledge into machine-learning models of complex molecular properties

Ksenia Briling

Statistical (machine-learning, ML) models are more and more often used in computational chemistry as a substitute to more expensive ab initio and parametrizable methods. While the ML algorithms are capable of learning physical laws implicitly from data, ad ...

EPFL2024

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

Michele Ceriotti, Edgar Albert Engel, Maria Pakhnova

Due to the subtle balance of intermolecular interactions that govern structure-property relations, predicting the stability of crystal structures formed from molecular building blocks is a highly non-trivial scientific problem. A particularly active and fr ...

ROYAL SOC CHEMISTRY2023

Universal machine learning for the response of atomistic systems to external fields

Yaolong Zhang

Machine learned interatomic interaction potentials have enabled efficient and accurate molecular simulations of closed systems. However, external fields, which can greatly change the chemical structure and/or reactivity, have been seldom included in curren ...

Nature Portfolio2023

Effects of surface rigidity and metallicity on dielectric properties and ion interactions at aqueous hydrophobic interfaces

Philip Robin Loche

Using classical molecular dynamics simulations, we investigate the dielectric properties at interfaces of water with graphene, graphite, hexane, and water vapor. For graphite, we compare metallic and nonmetallic versions. At the vapor-liquid water and hexa ...

AIP Publishing2022

Beyond potentials: Integrated machine learning models for materials

Michele Ceriotti

Over the past decade, interatomic potentials based on machine learning (ML) techniques have become an indispensable tool in the atomic-scale modeling of materials. Trained on energies and forces obtained from electronic-structure calculations, they inherit ...

SPRINGER HEIDELBERG2022

Modeling non-covalent interactions in condensed phase

Veronika Juraskova

The modeling of non-covalent interactions, solvation effects, and chemical reactions in complex molecular environment is a challenging task. Current state-of-the-art approaches often rely on static computations using implicit solvent models and harmonic ap ...

EPFL2022

Assessing the persistence of chalcogen bonds in solution with neural network potentials

Rubén Laplaza Solanas, Anne-Clémence Corminboeuf, Frédéric Célerse, Veronika Juraskova

Non-covalent bonding patterns are commonly harvested as a design principle in the field of catalysis, supramolecular chemistry, and functional materials to name a few. Yet, their computational description generally neglects finite temperature and environme ...

2022

Predicting hot-electron free energies from ground-state data

Michele Ceriotti, Federico Grasselli, Chiheb Ben Mahmoud

Machine-learning potentials are usually trained on the ground-state, Born-Oppenheimer energy surface, which depends exclusively on the atomic positions and not on the simulation temperature. This disregards the effect of thermally excited electrons, that i ...

AMER PHYSICAL SOC2022

A general and efficient framework for atomistic machine learning

Félix Benedito Clément Musil

Over the last two decades, many technological and scientific discoveries, ranging from the development of materials for energy conversion and storage through the design of new drugs, have been accelerated by the use of preliminary in silico experiments, to ...

EPFL2021