Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
Abstract
Quantitative identification of molecular products and reaction pathways from scanning tunneling microscopy images is difficult when labeled images are unavailable for a new chemical system. We develop a simulation-assisted framework for zero-shot analysis that requires only precursor information for a new target system, with no experimental images or annotations from that system used during model training. The framework couples two functional components: NanoSim generates physics-grounded synthetic images from predicted reaction products and sampled surface scenes, while NanoAnalysis translates molecular detections into product populations, spatial arrangements, and mechanistic interpretations. Applied to a representative on-surface reaction, the detector achieves a micro-averaged F1 score of 0.92 on experimental images. Analysis of the detected molecules reveals annealing-dependent population changes and reaction-site preferences consistent with experimental observations. Beyond this capability, its modular organization allows heterogeneous data from other systems to be used to improve each component independently, providing a scalable route for continued generalization.
Related
- Biologically grounded cell profiling across microscopy modalities
- Simulation-free approximate Bayesian computation for stochastic reaction networks
- Simulation-free approximate Bayesian computation for stochastic reaction networks
- Live-Imaging of Molecular Processes with Real-Time Fluorescence Microscopy
- 2D reaction-diffusion model-based biopsy simulation for dynamic tumor growth parameter estimation
BibTeX
@misc{he2026physicsgrounded,
title = {{Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy}},
author = {Yuanqin He and Zhiyu Wang and Yang Bao and Tao Lin and Hai Bi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40666},
eprint = {2610.40666},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40666},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
AU - Yuanqin He
AU - Zhiyu Wang
AU - Yang Bao
AU - Tao Lin
AU - Hai Bi
PY - 2026
DA - 2026/10/10
PB - arXiv
DO - 10.48550/arxiv.2610.40666
UR - https://arxiv.org/abs/2610.40666
AB - Quantitative identification of molecular products and reaction pathways from scanning tunneling microscopy images is difficult when labeled images are unavailable for a new chemical system. We develop a simulation-assisted framework for zero-shot analysis that requires only precursor information for a new target system, with no experimental images or annotations from that system used during model training. The framework couples two functional components: NanoSim generates physics-grounded synthetic images from predicted reaction products and sampled surface scenes, while NanoAnalysis translates molecular detections into product populations, spatial arrangements, and mechanistic interpretations. Applied to a representative on-surface reaction, the detector achieves a micro-averaged F1 score of 0.92 on experimental images. Analysis of the detected molecules reveals annealing-dependent population changes and reaction-site preferences consistent with experimental observations. Beyond this capability, its modular organization allows heterogeneous data from other systems to be used to improve each component independently, providing a scalable route for continued generalization.
ER -