Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling

Andrew Millard, Zheng Zhao, Henrik Pedersen
Proceedings of the 2nd International Conference on Probabilistic Numerics, PMLR 341:124-168, 2026.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v341-millard26a, title = {Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling}, author = {Millard, Andrew and Zhao, Zheng and Pedersen, Henrik}, booktitle = {Proceedings of the 2nd International Conference on Probabilistic Numerics}, pages = {124--168}, year = {2026}, editor = {Karvonen, Toni and Bosch, Nathanael and Cockayne, Jon and Gessner, Alexandra and Hennig, Philipp and Kouw, Wouter}, volume = {341}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v341/main/assets/millard26a/millard26a.pdf}, url = {https://proceedings.mlr.press/v341/millard26a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling %A Andrew Millard %A Zheng Zhao %A Henrik Pedersen %B Proceedings of the 2nd International Conference on Probabilistic Numerics %C Proceedings of Machine Learning Research %D 2026 %E Toni Karvonen %E Nathanael Bosch %E Jon Cockayne %E Alexandra Gessner %E Philipp Hennig %E Wouter Kouw %F pmlr-v341-millard26a %I PMLR %P 124--168 %U https://proceedings.mlr.press/v341/millard26a.html %V 341 %X 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.
APA
Millard, A., Zhao, Z. & Pedersen, H.. (2026). Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling. Proceedings of the 2nd International Conference on Probabilistic Numerics, in Proceedings of Machine Learning Research 341:124-168 Available from https://proceedings.mlr.press/v341/millard26a.html.

Related Material