<div class="csl-bib-body">
<div class="csl-entry">Wieser, S. (2026, September 23). <i>Transition-Point Sampling via Stochastic Saddle Point Dynamics for Training Machine-Learned Interatomic Potentials</i> [Conference Presentation]. OePG-CMD JOINT MEETING 2026, Graz, Austria.</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/231648
-
dc.description
https://oepg-cmd-jointmeeting2026.uni-graz.at/en/
-
dc.description.abstract
Dataset generation is a critical component for obtaining accurate machine-learned interatomic potentials (MLIPs). Molecular dynamics is widely used for reference data generation; however, it struggles to sample rare events such as transition states. This limitation is particularly problematic when fine-tuning foundation models, in which such configurations are typically underrepresented.
To address this challenge, we employ a recently developed algorithm, stochastic saddle point dynamics (SSPD) [1,2] to generate reference configurations without relying on predefined collective variables. This approach steers Langevin dynamics toward transition states, enabling efficient sampling not only at but also in the vicinity of these configurations. The use of SSPD has recently been demonstrated for identifying transition states in the decomposition of isopropanol and CO dissociation on Co surfaces [3].
Here, we apply SSPD to generate reference data near transition states associated with oxygen ion migration in perovskites. We demonstrate its capability to sample configurations close to transition states in SrTiO3-d, enabling efficient fine-tuning of MACE foundation models to accurately predict migration barriers at the target level of theory. Furthermore, SSPD-driven active learning is used to perform larger-scale investigations of the more complex La1-xSrxFeO3-d system across varying Sr concentrations. We observe substantial variations in migration barriers depending on the migration pathway, revealing a more intricate landscape than previously assumed for identifying efficient transport routes. Overall, SSPD provides a powerful addition to the dataset generation toolkit, addressing a key limitation of conventional approaches.
en
dc.description.sponsorship
FWF - Österr. Wissenschaftsfonds
-
dc.language.iso
en
-
dc.subject
Machine-Learned Interatomic Potentials
en
dc.subject
Stochastic Saddle-Point Dynamics
en
dc.subject
Transition States
en
dc.subject
Atomistic Simulations
en
dc.title
Transition-Point Sampling via Stochastic Saddle Point Dynamics for Training Machine-Learned Interatomic Potentials
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.relation.grantno
COE 5
-
dc.type.category
Conference Presentation
-
tuw.publication.invited
invited
-
tuw.project.title
Cluster of Excellence "Materialien für Energieumwandlung und -speicherung (MECS)"
