Intelligent navigation of potential energy surfaces: leveraging deep reinforcement learning paradigms for accelerated discovery of stable nickel nanoclusters
Abstract
molecular dynamics simulations at 300 K. Crucially, the identified global minima show exact agreement with independent genetic algorithm searches, providing compelling cross-methodological validation. The Deepcluster agent establishes a robust, scalable, and efficient paradigm that transcends the limitations of traditional approaches, paving the way for the accelerated discovery of complex functional nanomaterials for catalysis and energy applications.
Fields of Study & Subjects
Machine Learning in Materials Science
Nanocluster Synthesis and Applications
Advanced Electron Microscopy Techniques and Applications
Publication details
- Journal / source
- Nanoscale
- Publisher
- Royal Society of Chemistry (RSC)
- Volume
- 18
- Issue
- 6
- Pages
- 3245–3261
- Publication date
- 1 January 2026
- Language
- EN