Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.16461 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913041696686080 |
|---|---|
| author | Millard, Andrew Zhao, Zheng Pedersen, Henrik |
| author_facet | Millard, Andrew Zhao, Zheng Pedersen, Henrik |
| contents | Physics-guided sampling with diffusion priors has recently shown strong performance in solving complex systems of partial differential equations (PDEs) from sparse observations. However, these methods are typically evaluated on benchmark problems that do not fully demonstrate their ability to generate temporally consistent solutions of time-dependent PDEs, often focusing instead on reconstructing a single snapshot. In this work, we apply these methods to gas-phase reaction kinetics problems governed by the advection-reaction-diffusion (ARD) equation, providing a setting that more closely reflects realistic laboratory experiments. We demonstrate that guided sampling can be used to reconstruct full spatiotemporal trajectories, rather than isolated states. Furthermore, we show that these methods generalise to previously unseen parameter regimes, highlighting their potential for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16461 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling Millard, Andrew Zhao, Zheng Pedersen, Henrik Computational Physics Machine Learning Physics-guided sampling with diffusion priors has recently shown strong performance in solving complex systems of partial differential equations (PDEs) from sparse observations. However, these methods are typically evaluated on benchmark problems that do not fully demonstrate their ability to generate temporally consistent solutions of time-dependent PDEs, often focusing instead on reconstructing a single snapshot. In this work, we apply these methods to gas-phase reaction kinetics problems governed by the advection-reaction-diffusion (ARD) equation, providing a setting that more closely reflects realistic laboratory experiments. We demonstrate that guided sampling can be used to reconstruct full spatiotemporal trajectories, rather than isolated states. Furthermore, we show that these methods generalise to previously unseen parameter regimes, highlighting their potential for real-world applications. |
| title | Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling |
| topic | Computational Physics Machine Learning |
| url | https://arxiv.org/abs/2604.16461 |