Publications by Andrea Anelli | EPFL Graph Search

Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems

In committee of experts strategies, small datasets are extracted from a larger one and utilised for the training of multiple models. These models' predictions are then carefully weighted so as to obtain estimates which are dominated by the model(s) that ar ...

Royal Soc Chemistry2023

Characterising Structure and Stability of Materials using Machine Learning

Andrea Anelli

The search of novel materials using in-silico high-throughput screening is emerging as a fundamental step in the pipeline of materials discovery, but its low yields in terms of synthesisable structures limit its effectiveness. In order to isolate configura ...

EPFL2020

Learning the electronic density of states in condensed matter

Michele Ceriotti, Andrea Anelli, Chiheb Ben Mahmoud

The electronic density of states (DOS) quantifies the distribution of the energy levels that can be occupied by electrons in a quasiparticle picture and is central to modern electronic structure theory. It also underpins the computation and interpretation ...

AMER PHYSICAL SOC2020

A Bayesian approach to NMR crystal structure determination

David Lyndon Emsley, Michele Ceriotti, Albert Hofstetter, Edgar Albert Engel, Federico Maria Paruzzo, Andrea Anelli

Nuclear Magnetic Resonance (NMR) spectroscopy is particularly well suited to determine the structure of molecules and materials in powdered form. Structure determination usually proceeds by finding the best match between experimentally observed NMR chemica ...

2019

Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials

Michele Ceriotti, Giulio Imbalzano, Andrea Anelli, Daniele Giofré, Sinja Klees

2018

Mapping uncharted territory in ice from zeolite networks to ice structures

Michele Ceriotti, Edgar Albert Engel, Andrea Anelli

Nature Research2018

Generalized convex hull construction for materials discovery

Michele Ceriotti, Edgar Albert Engel, Andrea Anelli

Searching for novel materials involves identifying potential candidates and selecting those that have desirable properties and facile synthesis. It is relatively easy to generate large numbers of potential candidates, for instance, by computational searche ...

2018