Assessing Emulator Design and Training for Modal Aerosol Microphysics Parameterizations in E3SMv2
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_ | 1866917430467493888 |
|---|---|
| author | Ahmed, Shady E. Wan, Hui Qadeer, Saad Stinis, Panos Chong, Kezhen Mozumder, Mohammad Taufiq Hassan Zhang, Kai Almgren, Ann S. |
| author_facet | Ahmed, Shady E. Wan, Hui Qadeer, Saad Stinis, Panos Chong, Kezhen Mozumder, Mohammad Taufiq Hassan Zhang, Kai Almgren, Ann S. |
| contents | Toward the goal of using Scientific Machine Learning (SciML) emulators to improve the numerical representation of aerosol processes in global atmospheric models, we explore the emulation of aerosol microphysics processes under cloud-free conditions in the 4-mode Modal Aerosol Module (MAM4) within the Energy Exascale Earth System Model version 2 (E3SMv2). To develop an in-depth understanding of the challenges and opportunities in applying SciML to aerosol processes, we begin with a simple feedforward neural network architecture that has been used in earlier studies, but we systematically examine key emulator design choices, including architecture complexity and variable normalization, while closely monitoring training convergence behavior.
Our results show that optimization convergence, scaling strategy, and network complexity strongly influence emulation accuracy. When effective scaling is applied and convergence is achieved, the relatively simple architecture, used together with a moderate network size, can reproduce key features of the microphysics-induced aerosol concentration changes with promising accuracy. These findings provide practical clues for the next stages of emulator development; they also provide general insights that are likely applicable to the emulation of other aerosol processes, as well as other atmospheric physics involving multi-scale variability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21233 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Assessing Emulator Design and Training for Modal Aerosol Microphysics Parameterizations in E3SMv2 Ahmed, Shady E. Wan, Hui Qadeer, Saad Stinis, Panos Chong, Kezhen Mozumder, Mohammad Taufiq Hassan Zhang, Kai Almgren, Ann S. Atmospheric and Oceanic Physics Machine Learning Data Analysis, Statistics and Probability Geophysics Toward the goal of using Scientific Machine Learning (SciML) emulators to improve the numerical representation of aerosol processes in global atmospheric models, we explore the emulation of aerosol microphysics processes under cloud-free conditions in the 4-mode Modal Aerosol Module (MAM4) within the Energy Exascale Earth System Model version 2 (E3SMv2). To develop an in-depth understanding of the challenges and opportunities in applying SciML to aerosol processes, we begin with a simple feedforward neural network architecture that has been used in earlier studies, but we systematically examine key emulator design choices, including architecture complexity and variable normalization, while closely monitoring training convergence behavior. Our results show that optimization convergence, scaling strategy, and network complexity strongly influence emulation accuracy. When effective scaling is applied and convergence is achieved, the relatively simple architecture, used together with a moderate network size, can reproduce key features of the microphysics-induced aerosol concentration changes with promising accuracy. These findings provide practical clues for the next stages of emulator development; they also provide general insights that are likely applicable to the emulation of other aerosol processes, as well as other atmospheric physics involving multi-scale variability. |
| title | Assessing Emulator Design and Training for Modal Aerosol Microphysics Parameterizations in E3SMv2 |
| topic | Atmospheric and Oceanic Physics Machine Learning Data Analysis, Statistics and Probability Geophysics |
| url | https://arxiv.org/abs/2604.21233 |