From atomistic models to machine learning: Predictive design of nanocarbons under extreme conditions

Summary

Uses GPU-accelerated ReaxFF reactive molecular dynamics to follow the graphitization and remodeling of detonation nanodiamonds along quench and pressure-release trajectories, and trains a machine-learning model that predicts the resulting nanocarbon structure for a given temperature–pressure path in a fraction of a second.

Keywords

Cite

@article{2026_yan_nanocarbons_extreme_conditions,
  title = {From atomistic models to machine learning: Predictive design of nanocarbons under extreme conditions},
  author = {Xiaoli Yan and Millicent A. Firestone and Murat Keçeli and Santanu Chaudhuri and Eliu Huerta},
  journal = {Carbon 252, 121366 (2026)},
  year = {2026},
  doi = {10.1016/j.carbon.2026.121366}
}