articleJournal of Chemical Information and ModelingFeb 9, 2026Closed access

Reactive Neural Network Potential Developed for Asphalt Aging Systems Through Active Learning and Enhanced Sampling

ZLZhengwu LongLYLingyun You

Huazhong University of Science and Technology

PubMed
Indexed incrossrefpubmed

Abstract

The atomic-scale mechanisms of asphalt oxidative aging remain poorly understood due to the chemical complexity of asphalt and limitations of conventional methods. Herein, we develop a reactive neural network potential (NNP) for asphalt-oxygen systems via active learning combined with enhanced sampling (well-tempered metadynamics). The NNP achieves quantum-mechanical accuracy while enabling large-scale molecular dynamics simulations. Coupled with multimodal experimental characterization, we uncover a sequential "dehydrogenation-oxidation-crosslinking" reaction network during aging, initiated by thiophene sulfur oxidation and followed by hydrogen abstraction, aromatization, and carbonyl formation. Temperature…

Citation impact

7
total citations
FWCI
59.33
Percentile
100%
References
62
Too recent for citation history.

Authors

2

Topics & keywords

Topics
Keywords
  • Artificial neural network
  • Asphalt
  • Work (physics)
  • Sampling (signal processing)
  • Energy (signal processing)
  • Molecular dynamics
  • Active learning (machine learning)
No related works found for this paper.

Funding