Physics-Constrained Bayesian Neural Networks for Aerosol Retrieval From Hyperspectral Satellite Measurements With Integrated Uncertainty Quantification

Kurzfassung

This article introduces an innovative operational Bayesian neural network (BNN) framework for high-precision joint retrieval of aerosol optical depth (AOD) and aerosol layer height (ALH) with physically consistent uncertainty decomposition from TROPOMI hyperspectral measurements. Unlike conventional approaches, three different full-physics BNN architectures (implemented via Bayes-by-Backprop, Dropout, and Batch Norm (BN) techniques) are developed to simultaneously estimate target parameters and their heteroscedastic aleatoric uncertainties while preserving radiative transfer constraints. Epistemic uncertainties are quantified via Monte Carlo sampling of stochastic forward propagation, enabling systematic separation of data- versus model-driven uncertainties. A comprehensive validation demonstrates the following: 1) synthetic experiments show that epistemic uncertainties strongly correlate with retrieval errors, particularly for observing geometries outside the training data distribution, outperforming aleatoric estimates and 2) analyses using TROPOMI measurements demonstrate that the framework delivers comparable accuracy to operational products while providing unique uncertainty diagnostics. The framework’s computational efficiency, combined with its probabilistic outputs, establishes a new paradigm for characterizing aerosol properties from satellite measurements, particularly valuable for climate and air quality applications.