AODDiff: Probabilistic Reconstruction of Aerosol Optical Depth via Diffusion-based Bayesian Inference

TL;DR

AODDiff is a probabilistic diffusion-based framework that reconstructs Aerosol Optical Depth fields from incomplete data, providing high fidelity results and inherent uncertainty quantification without task-specific retraining.

Contribution

It introduces a novel diffusion-based Bayesian inference method with a corruption-aware training strategy and decoupled annealing sampling for AOD reconstruction.

Findings

Effective in downscaling and inpainting tasks

Maintains high spatial spectral fidelity

Provides uncertainty quantification through multiple sampling

Abstract

High-quality reconstruction of Aerosol Optical Depth (AOD) fields is critical for Atmosphere monitoring, yet current models remain constrained by the scarcity of complete training data and a lack of uncertainty quantification.To address these limitations, we propose AODDiff, a probabilistic reconstruction framework based on diffusion-based Bayesian inference. By leveraging the learned spatiotemporal probability distribution of the AOD field as a generative prior, this framework can be flexibly adapted to various reconstruction tasks without requiring task-specific retraining. We first introduce a corruption-aware training strategy to learns a spatiotemporal AOD prior solely from naturally incomplete data. Subsequently, we employ a decoupled annealing posterior sampling strategy that enables the more effective and integration of heterogeneous observations as constraints to guide the generation process. We validate the proposed framework through extensive experiments on Reanalysis data. Results across downscaling and inpainting tasks confirm the efficacy and robustness of AODDiff, specifically demonstrating its advantage in maintaining high spatial spectral fidelity. Furthermore, as a generative model, AODDiff inherently enables uncertainty quantification via multiple sampling, offering critical confidence metrics for downstream applications.