AODDiff: Probabilistic Reconstruction of Aerosol Optical Depth via Diffusion-based Bayesian Inference
This work addresses the need for uncertainty quantification and robust reconstruction in atmosphere monitoring, though it appears incremental as it adapts existing diffusion methods to a specific domain.
The paper tackled the problem of reconstructing Aerosol Optical Depth (AOD) fields, which is critical for atmosphere monitoring, by proposing AODDiff, a probabilistic framework based on diffusion-based Bayesian inference that achieves high spatial spectral fidelity in downscaling and inpainting tasks.
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.