Robust global optimization of atomic structures via a learning loss-informed on-the-fly firefly algorithm
AI Agent · 31.03.2026 · 2 (1)
DOI: 10.20517/aiagent.2025.13 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI Agent, online erschienen am 31.03.2026. Verfasst von Giyeok Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
In computational materials science, global optimization is pivotal for bridging theory and experiment but can fail when the theoretical treatment defining the potential energy surface does not accurately predict stability trends. Conventional approaches to address this rely on statistical sampling over numerous independent calculations or the use of more expensive theories throughout the global optimization process, both of which substantially increase computational cost. To overcome this, we present nature-inspired algorithm for robust atomic structure search (NARA), a framework that combines a firefly algorithm-based multimodal search with uncertainty-aware active learning. Instead of converging to a single structure, NARA simultaneously explores multiple distinct configurations, thereby mitigating sensitivity to potential limitations. For the “8” surface oxide on Cu(111), it achieves higher efficiency than the widely used basin-hopping algorithm. For gold clusters, a single run recovers both planar and non-planar structures, resolving stability reversals induced by different theoretical treatments. NARA thus achieves both efficiency and robustness for reliable atomic-structure identification.
Zitieren
APA
Lee, G., Stampfl, C., & Soon, A. (2026). Robust global optimization of atomic structures via a learning loss-informed on-the-fly firefly algorithm. AI Agent, 2(1). https://doi.org/10.20517/aiagent.2025.13
Vancouver
Lee G, Stampfl C, Soon A. Robust global optimization of atomic structures via a learning loss-informed on-the-fly firefly algorithm. AI Agent. 2026;2(1). doi:10.20517/aiagent.2025.13
BibTeX
@article{Lee2026,
author = {Lee, Giyeok and Stampfl, Catherine and Soon, Aloysius},
title = {Robust global optimization of atomic structures via a learning loss-informed on-the-fly firefly algorithm},
journal = {AI Agent},
year = {2026},
volume = {2},
number = {1},
doi = {10.20517/aiagent.2025.13}
}
EUVIMED