Foundation AI Models for Aerosol Optical Depth Estimation from PACE Satellite Data

TL;DR

This paper introduces ViTCG, a novel Vision Transformer-based model that leverages hyperspectral data for more accurate and spatially coherent Aerosol Optical Depth retrieval from satellite observations.

Contribution

It is the first to explore Foundation AI models for AOD retrieval and proposes a new spatial regression framework that reduces bias and error.

Findings

62% reduction in mean squared error compared to state-of-the-art models

Produces spatially coherent AOD fields from hyperspectral radiance data

Validates effectiveness using PACE satellite observations

Abstract

Aerosol Optical Depth (AOD) retrieval is essential for Earth observation, supporting applications from air quality monitoring to climate studies. Conventional physics-based AOD retrieval methods formulate the problem as a pixel-wise inversion, relying on radiative transfer modeling, memory-intensive look-up tables, and auxiliary meteorological data. While recent data-driven approaches have shown promise, many fail to exploit the spatial-spectral coherence of hyperspectral imagery, leading to spatially inconsistent and noise-sensitive retrievals. We present the first study exploring Foundation AI models for AOD retrieval and propose ViTCG, a Vision Transformer with Channel-wise Grouping-based spatial regression framework that reduces retrieval bias and error. ViTCG uses hyperspectral top-of-atmosphere radiance as input and jointly models spatial context and spectral information. Validation with PACE radiance observations demonstrates a 62% reduction in mean squared error compared to state-of-the-art foundation models, including Prithvi, and produces spatially coherent AOD fields.