Systematic selection of surrogate models for nonequilibrium chemistry
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917408088784896 |
|---|---|
| author | Janssen, Robin Branca, Lorenzo Buck, Tobias |
| author_facet | Janssen, Robin Branca, Lorenzo Buck, Tobias |
| contents | Nonequilibrium chemistry is central to many astrophysical environments but remains a major computational bottleneck in simulations because solving the associated stiff ODE systems is expensive. Neural surrogates promise large speedups, yet existing studies rarely provide systematic comparisons of architectures or rigorous optimization toward both accuracy and efficiency. We introduce CODES, a principled framework for optimizing and benchmarking astrochemical surrogate models. Using CODES, we compare four neural surrogate architectures across four KROME-generated datasets spanning primordial and molecular-cloud chemistry with up to 287 reactions across 37 species. Dual-objective optimization reveals pronounced accuracy-efficiency trade-offs across architectures. Fully connected models achieve the highest accuracy and most reliable uncertainty estimates, while latent-evolution models show improved robustness under iterative prediction. Our results highlight the importance of systematic optimization and architectural comparison. The datasets, metrics, and benchmarking procedure are publicly released within CODES to enable reproducible surrogate benchmarking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08567 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Systematic selection of surrogate models for nonequilibrium chemistry Janssen, Robin Branca, Lorenzo Buck, Tobias Astrophysics of Galaxies Instrumentation and Methods for Astrophysics Nonequilibrium chemistry is central to many astrophysical environments but remains a major computational bottleneck in simulations because solving the associated stiff ODE systems is expensive. Neural surrogates promise large speedups, yet existing studies rarely provide systematic comparisons of architectures or rigorous optimization toward both accuracy and efficiency. We introduce CODES, a principled framework for optimizing and benchmarking astrochemical surrogate models. Using CODES, we compare four neural surrogate architectures across four KROME-generated datasets spanning primordial and molecular-cloud chemistry with up to 287 reactions across 37 species. Dual-objective optimization reveals pronounced accuracy-efficiency trade-offs across architectures. Fully connected models achieve the highest accuracy and most reliable uncertainty estimates, while latent-evolution models show improved robustness under iterative prediction. Our results highlight the importance of systematic optimization and architectural comparison. The datasets, metrics, and benchmarking procedure are publicly released within CODES to enable reproducible surrogate benchmarking. |
| title | Systematic selection of surrogate models for nonequilibrium chemistry |
| topic | Astrophysics of Galaxies Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2603.08567 |