Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.31271

Learning Aerosol Coagulation Dynamics in Latent Space with a Scale-Covariant Neural ODE

Wenhan Tang·Ruqi Yang·Jeffrey H. Curtis·Ehsan Saleh·Lekha Patel·Peter A. Bosler·Nicole Riemer·Matthew West
View original source ↗Read source document ↗Export metadata ↓

Abstract

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.

Explore related subjects

physics.ao-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Wenhan Tang, Ruqi Yang, Jeffrey H. Curtis, Ehsan Saleh, Lekha Patel, Peter A. Bosler, Nicole Riemer, Matthew West. 2026-09-25. Learning Aerosol Coagulation Dynamics in Latent Space with a Scale-Covariant Neural ODE. https://arxiv.org/abs/2609.31271

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting

This study conducts a systematic hyperparameter search across five deep learning architectures, DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2, and nine context lengths (1-168 h) for single-station significant wave height (Hs) forecasting on NDBC buoy 41009, followed by re-evaluation of the best configurations on a 47-buoy, 37-year corpus. The five families converge to a common performance level on the multi-buoy evaluation (between-family SD = 0.0014 m^2, 0.8% of the grand mean), a spread dwarfed by the 4.83x cross-dataset MSE shift between buoy corpora. All multi-buoy trials beat persistence (mean skill +0.062), but no architecture consistently outperforms the others. On the single-buoy experiment, skill peaks at 12-24 h where five trials fall below persistence, per-family Q4/Q3 test MSE ratios range from 2.4 to 2.6, and deep models underperform persistence for the most extreme 1% of waves. These findings are consistent with the interpretation that persistence already captures the dominant linear-inertial signal in univariate Hs, and that architecture engineering under this univariate input setting has reached diminishing returns: cross-buoy variance, not model class, dominates forecast error. Future work should prioritise atmospheric covariates, zero-shot cross-buoy transfer, and decomposition of Hs into swell and wind-sea components. By establishing a rigorous reference baseline for what univariate Hs models can and cannot achieve, this study provides a benchmark against which future multivariate and physics-informed approaches can be calibrated, and offers practical guidance for lightweight buoy-level forecasting in mid-latitude storm-dominated and swell-mixed environments.

physics.ao-ph↗
arXiv2026

The impact of two-dimensional filtering on SWOT observations with white noise

The Surface Water and Ocean Topography (SWOT) mission provides two-dimensional observations of sea surface height (SSH) at unprecedented spatial resolution, enabling exploration of ocean variability down to scales of $O(10~\mathrm{ km})$. At these scales, however, interpreting SSH variability is challenging because ocean dynamical signals overlap with measurement noise, and their respective spectral signatures are not yet fully understood. Recent analyses of SWOT 2-km posting observations have shown that along-track spectra transition to flatter but still red spectra at scales around 30 km. These flatter portions of the spectra have a power-law-like behavior and spectral slopes of approximately $-1$ or steeper, and their magnitudes and slopes are correlated with SWOT measurement noise magnitude. Here, we investigate the hypothesis that these flatter but still red along-track small-scale spectra can arise from two-dimensional filtering and aliasing of spatially uncorrelated (white) noise. Using synthetic experiments, we show that the resulting one-dimensional along-track spectra exhibit a similar transition to red, power-law-like behavior at scales of 15--50 km, qualitatively similar to spectral behavior reported in SWOT observations. The transition scale and apparent spectral slopes depend on the noise level, its cross-track variability, and the background ocean signal. This finding highlights the importance of carefully accounting for measurement noise and processing effects when interpreting SWOT spectra, and suggests that a white noise model should serve as a baseline null hypothesis for small-scale spectral analyses.

physics.ao-ph↗
arXiv2026

Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach

Perturbed parameter ensembles (PPEs) reveal how physics parameters affect climate simulations, but interpreting parameter sensitivities across multivariate, spatially structured outputs remains challenging, particularly when calibrating models against observations. We develop an explainable contrastive learning model that maps 5 monthly cloud and radiation fields into a shared representation space. We train the model on the fields of two 100-member Community Atmosphere Model version 6 (CAM6) PPEs, spanning 34 parameters, that only differ in the warm rain microphysics scheme: KK2000, the default bulk microphysics scheme, and TAU-ML, a neural network emulator of a bin microphysics scheme. The learned representations separates two PPEs with over 94\% linear classification accuracy while preserving the seasonal variability and ensemble spread due to parameter perturbations. In the shared representation space, the representations of satellite observations occupy the same low-dimensional manifold as the PPEs but are displaced from them most strongly during boreal spring and autumn. TAU-ML PPE has a lower distance to observations compared to KK2000 in the representation space. Integrated Gradients attributions highlights the contributions in subtropical low-cloud regions, Northern and Southern Hemisphere storm track regions, and tropical convection regions to differences between PPEs and observations. Regional attributions correlate most strongly with parameters associated with cloud microphysics, boundary layer turbulence, and deep convection. These results demonstrate that explainable representations of climate fields can attribute model differences to specific variables, regions, seasons, and physical parameters.

physics.ao-ph↗