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

arXiv cs.CV / 5/4/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

The paper introduces Foundation AI models for estimating Aerosol Optical Depth (AOD) from hyperspectral PACE satellite radiance data, aiming to improve Earth observation accuracy.
It argues that traditional physics-based retrievals are hindered by computational and memory costs (e.g., radiative transfer look-up tables) and that many data-driven methods underuse hyperspectral spatial-spectral coherence.
The proposed model, ViTCG, uses a Vision Transformer with channel-wise grouping and a spatial regression framework to jointly learn spatial context and spectral information.
Experiments with PACE observations show a 62% reduction in mean squared error versus leading foundation models (including Prithvi) and yield more spatially coherent AOD maps.

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.