Metraipolis › archive › dc_03303af4cb45
Unmasking Compensating Errors in Numerical Weather Models: A Process-Additive Neural Network Approach — arXiv:2610.19772
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19772
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:51:38.127Z
- SHA-256 of the archived text
58396ed65e29fbbb25d33057645201547ad94b001de4a1889f5c030e83d5653b- Stable URL of this page
https://metraipolis.com/documento/dc_03303af4cb45
How to cite
Unmasking Compensating Errors in Numerical Weather Models: A Process-Additive Neural Network Approach — arXiv:2610.19772 — arXiv (en), https://arxiv.org/abs/2610.19772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_03303af4cb45 (Metraipolis archive dc_03303af4cb45, sha256 58396ed65e29fbbb25d33057645201547ad94b001de4a1889f5c030e83d5653b)
BibTeX
@misc{dc03303af4cb45,
title = {Unmasking Compensating Errors in Numerical Weather Models: A Process-Additive Neural Network Approach — arXiv:2610.19772},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19772},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_03303af4cb45; sha256 58396ed65e29fbbb25d33057645201547ad94b001de4a1889f5c030e83d5653b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This work introduces a Process Additive Neural Network (PANN) framework to disentangle compensating biases in atmospheric models, where errors in different physical processes can offset each other and obscure their origins. Using a single-column model, each PANN branch represents the tendency error associated with a separate physical process, and the summed branch outputs approximate the total error relative to a reference tendency. Once trained successfully, the branch outputs are expected to provide process-level error attributions and, when averaged, estimates of process-level bias. Initial experiments focus on cloud-related processes in OpenIFS SCM case studies, where cloud and convection tendencies are strongly coupled and compensation is difficult to diagnose using standard approaches. The aim is not to replace human interpretation of physical processes, but to extend it to regimes where model complexity, process interaction, and compensating errors make direct diagnosis difficult. By providing a physically structured form of machine-learning interpretability, PANN can help connect complex model behaviour with process-level explanations. This work supports both improved understanding of compensating errors and the development of more physically consistent weather and climate models. Tema degli esploratori: terra, clima ed energia (elenco arXiv physics.ao-ph, nuovi lavori del giorno). Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph). Pagina del lavoro: https://arxiv.org/abs/2610.19772 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T14:03:23.794Z dalla pagina https://arxiv.org/list/physics.ao-ph/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).