CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints
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_ | 1866915751308296192 |
|---|---|
| author | Wang, Xin Chen, Jianda Yang, Juntao Adie, Jeff See, Simon Furtado, Kalli Chen, Chen Arcomano, Troy Maulik, Romit Xue, Wei Mengaldo, Gianmarco |
| author_facet | Wang, Xin Chen, Jianda Yang, Juntao Adie, Jeff See, Simon Furtado, Kalli Chen, Chen Arcomano, Troy Maulik, Romit Xue, Wei Mengaldo, Gianmarco |
| contents | Accurate and efficient climate simulations are crucial for understanding Earth's evolving climate. However, current general circulation models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection. A common solution is to adopt cloud resolving models, that provide more accurate results than the standard subgrid parametrisation schemes typically used in GCMs. However, cloud resolving models, also referred to as super paramtetrizations, remain computationally prohibitive. Hybrid modeling, which integrates deep learning with equation-based GCMs, offers a promising alternative but often struggles with long-term stability and accuracy issues. In this work, we find that water vapor oversaturation during condensation is a key factor compromising the stability of hybrid models. To address this, we introduce CondensNet, a novel neural network architecture that embeds a self-adaptive physical constraint to correct unphysical condensation processes. CondensNet effectively mitigates water vapor oversaturation, enhancing simulation stability while maintaining accuracy and improving computational efficiency compared to super parameterization schemes.
We integrate CondensNet into a GCM to form PCNN-GCM (Physics-Constrained Neural Network GCM), a hybrid deep learning framework designed for long-term stable climate simulations in real-world conditions, including ocean and land. PCNN-GCM represents a significant milestone in hybrid climate modeling, as it shows a novel way to incorporate physical constraints adaptively, paving the way for accurate, lightweight, and stable long-term climate simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints Wang, Xin Chen, Jianda Yang, Juntao Adie, Jeff See, Simon Furtado, Kalli Chen, Chen Arcomano, Troy Maulik, Romit Xue, Wei Mengaldo, Gianmarco Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning Accurate and efficient climate simulations are crucial for understanding Earth's evolving climate. However, current general circulation models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection. A common solution is to adopt cloud resolving models, that provide more accurate results than the standard subgrid parametrisation schemes typically used in GCMs. However, cloud resolving models, also referred to as super paramtetrizations, remain computationally prohibitive. Hybrid modeling, which integrates deep learning with equation-based GCMs, offers a promising alternative but often struggles with long-term stability and accuracy issues. In this work, we find that water vapor oversaturation during condensation is a key factor compromising the stability of hybrid models. To address this, we introduce CondensNet, a novel neural network architecture that embeds a self-adaptive physical constraint to correct unphysical condensation processes. CondensNet effectively mitigates water vapor oversaturation, enhancing simulation stability while maintaining accuracy and improving computational efficiency compared to super parameterization schemes. We integrate CondensNet into a GCM to form PCNN-GCM (Physics-Constrained Neural Network GCM), a hybrid deep learning framework designed for long-term stable climate simulations in real-world conditions, including ocean and land. PCNN-GCM represents a significant milestone in hybrid climate modeling, as it shows a novel way to incorporate physical constraints adaptively, paving the way for accurate, lightweight, and stable long-term climate simulations. |
| title | CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints |
| topic | Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.13185 |