Dissertation · 2026 · Open access

From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning

Filippo Bigi

Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Published 1 January 2026 · DOI 10.5075/epfl-thesis-11840

Open full textCite this paper

In brief

“From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning” is a 2026 dissertation by Filippo Bigi, published in Infoscience (Ecole Polytechnique Fédérale de Lausanne). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at Infoscience (Ecole Polytechnique Fédérale de Lausanne).

Citations
0
Authors
1

Abstract

Atomic-scale simulations provide a computational method to probe the properties of molecules and materials. Their predictive power is highest when the interactions between atoms are obtained from electronic-structure theory, but the cost of these calculations limits the accessible system sizes, time scales, and statistical accuracy. Machine learning offers a way to overcome these limitations: expensive quantum-mechanical calculations can be replaced by much faster regression models trained on reference data. The central difficulty is not only to make these models accurate, but to make them useful in scientific simulations. This thesis develops machine-learning methods for atomic-scale modeling along two connected directions. The first is the construction of physically faithful representations and architectures for predicting structure-property maps. Particular emphasis is placed on the role of physical priors such as locality, smoothness, symmetry, and body-order character, and how they can be incorporated into descriptors, kernels, and neural networks. This includes smooth bases for atom-centered representations, body-ordered equivariant kernels, and architectures that use physical preconditioning without imposing restrictive truncations. The opposite limit is also examined, in which some symmetries or conservation laws are relaxed, showing when this leads to improved accuracy and efficiency, and when it instead results in qualitative failures of simulations. The resulting unconstrained models are especially valuable for developing universal interatomic potentials that aim to cover large regions of chemical and configurational space. These models make it possible to perform advanced simulations out of the box, but they also expose the need for careful validation and uncertainty quantification. To address this issue, the thesis introduces prediction-rigidity methods that provide low-cost uncertainty estimates for trained neural networks and can be propagated to downstream properties and simulation workflows. The second direction is molecular dynamics beyond conventional time integration. Machine-learned potentials accelerate force evaluation, but they still inherit the very small time steps required by the numerical integration of atomistic motion. This thesis investigates models that predict long strides of molecular dynamics directly, thereby replacing many numerical integration steps by a single learned map. These direct predictors can reproduce equilibrium and time-dependent properties over much longer effective time scales, but they also introduce failure modes that are specific to trajectory prediction. The geometric structure of Hamiltonian mechanics can be restored by learning symplectic and time-reversible maps, which is equivalent to learning the classical action that generates the dynamics. Together, these results outline a pragmatic view of atomistic machine learning. Accuracy on benchmark data is only one part of the problem. Useful models must encode the right physical structure when needed and relax it when…

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Bigi, F. (2026). From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-11840

MLA 9

Bigi, Filippo. “From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning.” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2026. https://doi.org/10.5075/epfl-thesis-11840.

Chicago

Bigi, Filippo. 2026. “From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning.” Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-11840.

Harvard

Bigi, F. (2026) ‘From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning’, Infoscience (Ecole Polytechnique Fédérale de Lausanne). doi:10.5075/epfl-thesis-11840.

IEEE

F. Bigi, “From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning,” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2026, doi: 10.5075/epfl-thesis-11840.

BibTeX

@phdthesis{bigi2026from,
  title     = {{From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning}},
  author    = {Bigi, Filippo},
  year      = {2026},
  doi       = {10.5075/epfl-thesis-11840},
  url       = {https://doi.org/10.5075/epfl-thesis-11840}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • atomistic machine learning
  • interatomic potentials
  • structure-property prediction
  • physical priors
  • uncertainty quantification
  • symplectic maps
  • Hamiltonian mechanics

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Bigi, F. (2026). From Property Prediction to Long-Stride Dynamics: Accelerating Atomistic Simulation with Machine Learning. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-11840

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Infoscience (Ecole Polytechnique Fédérale de Lausanne): sign in and open the full text from this page.

Who wrote this paper?

Filippo Bigi.

What is the DOI of this paper?

10.5075/epfl-thesis-11840, permanently at https://doi.org/10.5075/epfl-thesis-11840. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.