Metraipolis › archive › dc_20fcb2b223e7

Learning Aerosol Coagulation Dynamics in Latent Space with a Scale-Covariant Neural ODE — arXiv:2609.31271

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31271
License (as archived)
CC0-1.0
Archived
2026-10-08T03:49:51.815Z
SHA-256 of the archived text
636e26f054dbb60b0365b75ad86bfbe36a14e0ce450da392af0e88d7cb721b25
Stable URL of this page
https://metraipolis.com/documento/dc_20fcb2b223e7

How to cite

Learning Aerosol Coagulation Dynamics in Latent Space with a Scale-Covariant Neural ODE — arXiv:2609.31271 — arXiv (en), https://arxiv.org/abs/2609.31271 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20fcb2b223e7 (Metraipolis archive dc_20fcb2b223e7, sha256 636e26f054dbb60b0365b75ad86bfbe36a14e0ce450da392af0e88d7cb721b25)
BibTeX
@misc{dc20fcb2b223e7,
  title = {Learning Aerosol Coagulation Dynamics in Latent Space with a Scale-Covariant Neural ODE — arXiv:2609.31271},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31271},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20fcb2b223e7; sha256 636e26f054dbb60b0365b75ad86bfbe36a14e0ce450da392af0e88d7cb721b25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31271. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Particle-resolved aerosol models preserve the joint size-composition structure that governs cloud activation, optical properties, and freezing, but their computational cost limits their use in large-scale atmospheric models. We extend AeroMELD from a compact representation of aerosol populations to a prognostic model of coagulation. The resulting AeroMELD-Coag advances nine learned coordinates for population shape and one for total particle number through a scale-covariant neural ordinary differential equation that incorporates the known concentration dependence of coagulation. Across 2,000 held-out trajectories spanning 48 h, median symmetric errors are 3.5% for latent shape and 0.52% for total number. This ten-coordinate state also retains the evolving size-resolved composition and associated cloud-condensation-nuclei (CCN) activation, optical properties, and frozen fraction. Compared with the evaluated 20-bin sectional model with 320 prognostic coordinates, AeroMELD-Coag lowers pooled mean CCN activation error from 1.98% to 1.38% and frozen-fraction error from 1.72% to 0.56%. In a matched integration benchmark, GPU integration time per trajectory, amortized over a batch, is more than three orders of magnitude lower than for both single-core CPU references. These coagulation results provide a proof of concept for advancing aerosol microphysics efficiently in a compact learned state while retaining information about aerosol mixing state. They establish a foundation for future large-scale atmospheric models to represent aerosol microphysics with greater mixing-state detail within practical computational budgets.

Tema degli esploratori: terra, clima ed energia (retro-catalogo arXiv: annunci del 2026-09-28 in physics.ao-ph).
Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.31271 — 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 2026-10-08T03:16:56.657Z dalla pagina https://arxiv.org/catchup/physics.ao-ph/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).