Reconstructing the Aerosol State from Partial Observations with Generative Modeling

Abstract Key aerosol properties that shape climate—such as cloud condensation nuclei (CCN) activity, scattering and absorption, and ice nucleation efficiency—are difficult to infer from measurements that typically capture only a part of the aerosol state. We develop a conditional generative framework that maps a label (a vector of partial observations) to an ensemble of plausible aerosol states and propagates these to diagnostics, yielding mean estimates with confidence intervals. Using synthetic data, we evaluate two label configurations: a low-dimensional setup with limited number distribution and bulk-composition information and a high-dimensional setup including complete number and total mass distributions plus species bulk masses. Generated samples maintain strong label compliance, and higher-dimensional labels markedly reduce variability. CCN activity and volume scattering are well constrained even under the low-dimensional setup, whereas dust- and black carbon (BC)-sensitive diagnostics (frozen fraction, absorption) benefit substantially from the additional information in the high-dimensional case. This framework clarifies which observational inputs most effectively constrain different diagnostics and demonstrates how generative machine learning can provide uncertainty-aware estimates from incomplete aerosol information. Significance Statement Many atmospheric measurements only capture part of the aerosol population, which makes it hard to estimate their climate impacts. This work introduces a way to use machine learning to fill in the missing information and produce a range of possible full aerosol states that match the limited observations. From these, we can estimate important climate properties like cloud-forming ability and light absorption, along with their uncertainty. We also show which kinds of measurements are most useful for constraining these estimates. This approach can guide the design of future field campaigns and help scientists make better use of existing observations.