Gradients not needed: ML-driven propagation of nonadiabatic molecular dynamics without reference gradients

Mikołaj Martyka; Joanna Jankowska; Hans Lischka; Pavlo O. Dral

doi:10.1039/d5sc09557c

January 1, 2026Chemical ScienceOpen Access

Gradients not needed: ML-driven propagation of nonadiabatic molecular dynamics without reference gradients

View Full Paper

Ask AI

Bookmark

Share

Key Points

The research aims to improve the efficiency of molecular dynamics simulations by using machine learning.
Developed machine learning models for quantum chemistry calculations.
Applied these models to facilitate nonadiabatic molecular dynamics.
Eliminated the need for reference gradients in simulations.
Demonstrated increased efficiency in molecular simulations.
Showed successful propagation of nonadiabatic effects using ML methodologies.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Machine learning enhances molecular dynamics simulation efficiency by bypassing gradient requirements in quantum chemistry, indicating a breakthrough approach.

Abstract

The recent development of machine learning (ML) methods for quantum chemistry has tremendously boosted the efficiency of molecular calculations. In this work, we use ML to enable nonadiabatic molecular dynamics...

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Martyka et al. (2026) studied this question.

synapsesocial.com/papers/697460acbb9d90c67120a99b https://doi.org/10.1039/d5sc09557c

View Full Paper

Ask AI

Bookmark

Share

Gradients not needed: ML-driven propagation of nonadiabatic molecular dynamics without reference gradients

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Gradients not needed: ML-driven propagation of nonadiabatic molecular dynamics without reference gradients

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading