Reduced Cloud Cover Errors in a Hybrid AI-Climate Model Through Equation Discovery And Automatic Tuning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911283753779200 |
|---|---|
| author | Grundner, Arthur Beucler, Tom Savre, Julien Lauer, Axel Schlund, Manuel Eyring, Veronika |
| author_facet | Grundner, Arthur Beucler, Tom Savre, Julien Lauer, Axel Schlund, Manuel Eyring, Veronika |
| contents | Cloud-related parameterizations remain a leading source of uncertainty in climate projections. Although machine learning holds promise for Earth system models (ESMs), many data-driven parameterizations lack interpretability, physical consistency, and smooth integration into ESMs. Here, a two-step method is presented to improve a climate model with data-driven parameterizations. First, we incorporate a physically consistent cloud cover parameterization -- derived from storm-resolving simulations via symbolic regression, preserving interpretability while enhancing accuracy -- into the ICON global atmospheric model. Second, we apply the gradient-free Nelder-Mead optimizer to automatically recalibrate the hybrid model against Earth observations, tuning in nested stages (2-, 7-, 30- and 365-day runs) to ensure stability and tractability. The tuned hybrid model substantially reduces long-standing biases in cloud cover -- particularly over the Southern Ocean (by 75%) and subtropical stratocumulus regions (by 44%) -- and remains robust under +4K surface warming. These results demonstrate that interpretable machine-learned parameterizations, paired with practical tuning, can efficiently and transparently strengthen ESM fidelity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04358 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reduced Cloud Cover Errors in a Hybrid AI-Climate Model Through Equation Discovery And Automatic Tuning Grundner, Arthur Beucler, Tom Savre, Julien Lauer, Axel Schlund, Manuel Eyring, Veronika Atmospheric and Oceanic Physics Cloud-related parameterizations remain a leading source of uncertainty in climate projections. Although machine learning holds promise for Earth system models (ESMs), many data-driven parameterizations lack interpretability, physical consistency, and smooth integration into ESMs. Here, a two-step method is presented to improve a climate model with data-driven parameterizations. First, we incorporate a physically consistent cloud cover parameterization -- derived from storm-resolving simulations via symbolic regression, preserving interpretability while enhancing accuracy -- into the ICON global atmospheric model. Second, we apply the gradient-free Nelder-Mead optimizer to automatically recalibrate the hybrid model against Earth observations, tuning in nested stages (2-, 7-, 30- and 365-day runs) to ensure stability and tractability. The tuned hybrid model substantially reduces long-standing biases in cloud cover -- particularly over the Southern Ocean (by 75%) and subtropical stratocumulus regions (by 44%) -- and remains robust under +4K surface warming. These results demonstrate that interpretable machine-learned parameterizations, paired with practical tuning, can efficiently and transparently strengthen ESM fidelity. |
| title | Reduced Cloud Cover Errors in a Hybrid AI-Climate Model Through Equation Discovery And Automatic Tuning |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2505.04358 |