PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
August 17, 20250 citations

Developing Scalable Reactive Machine Learning Potentials for CHON Chemical Systems

General reactive machine learning potentials for CHON elements

View Full Paper
Ask AI
Bookmark
Share

Authors

BLBowen LiSMShengrun MiJXJin Xiao

Discussion

Loading...

Member takes

Overview

This research reports a framework enhancing predictive accuracy in chemical reactions of C, H, O, and N, suggesting improved simulation efficiency.

Key Points

  • Developing a robust reactive machine learning potential improves predictive accuracy in chemical reaction modeling, enhancing application in catalysis and materials design.
  • State-of-the-art model accuracy was achieved, closely matching coupled cluster calculations while outperforming conventional density functional theory methods across reactive environments.
  • The methodology employed a large-scale dataset creation, integrating active learning and semi-empirical labeling for optimal training of machine learning models.
  • This framework opens pathways for high-fidelity simulations in diverse chemical processes, supporting advancements across multiple scientific and engineering fields.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/68a36c360a429f797333069ahttps://doi.org/10.26434/chemrxiv-2025-1d293-v2
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine Learning of Reactive Potentials2024 · 76 citations
  2. 2Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations2025 · 4 citations
  3. 3ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials2024 · 2 citations
  4. 4(Invited) Machine Learning in Chemistry: Reactive Force Fields for Carbon Structure Formation2024
  5. 5Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential2024 · 132 citations