Uncertainty in the era of machine learning for atomistic modeling
Federico Grasselli (Università Degli Studi di Modena e Reggio Emilia, IMAMOTER - C.N.R. Sensors and Nanomaterials Laboratory)
Sanggyu Chong (Institute of Materials)
Venkat Kapil (London Centre for Nanotechnology, University College London, University of Cambridge)
Silvia Bonfanti (National Center for Nuclear Research, University of Milan)
Kevin Rossi (TU Delft - Mechanical Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The widespread adoption of machine learning surrogate models has significantly improved the scale and complexity of systems and processes that can be explored accurately and efficiently using atomistic modeling. However, the inherently data-driven nature of machine learning models introduces uncertainties that must be quantified, understood, and effectively managed to ensure reliable predictions and conclusions. Building upon these premises, in this perspective, we first overview state-of-the-art uncertainty estimation methods, from Bayesian frameworks to ensembling techniques, and discuss their application in atomistic modeling. We then examine the interplay between model accuracy, uncertainty, training dataset composition, data acquisition strategies, model transferability, and robustness. In doing so, we synthesize insights from the existing literature and highlight areas of ongoing debate.
help_outline