Atmos-Bench: 3D Atmospheric Structures for Climate Insight

TL;DR

Atmos-Bench introduces the first standardized 3D atmospheric benchmark and a novel neural network that improves satellite-based atmospheric structure recovery, enhancing climate understanding without auxiliary inputs.

Contribution

It provides a new 3D atmospheric benchmark dataset and a physics-aware neural network model that outperforms existing methods in atmospheric structure restoration.

Findings

Achieved high-quality 3D atmospheric reconstructions at multiple wavelengths.

Outperformed state-of-the-art models on the Atmos-Bench dataset.

Embedded physical constraints improve energy consistency in reconstructions.

Abstract

Atmospheric structure, represented by backscatter coefficients (BC) recovered from satellite LiDAR attenuated backscatter (ATB), provides a volumetric view of clouds, aerosols, and molecules, playing a critical role in human activities, climate understanding, and extreme weather forecasting. Existing methods often rely on auxiliary inputs and simplified physics-based approximations, and lack a standardized 3D benchmark for fair evaluation. However, such approaches may introduce additional uncertainties and insufficiently capture realistic radiative transfer and atmospheric scattering-absorption effects. To bridge these gaps, we present Atmos-Bench: the first 3D atmospheric benchmark, along with a novel FourCastX: Frequency-enhanced Spatio-Temporal Mixture-of-Experts Network that (a) generates 921,600 image slices from 3D scattering volumes simulated at 532 nm and 355 nm by coupling WRF with an enhanced COSP simulator over 384 land-ocean time steps, yielding high-quality voxel-wise references; (b) embeds ATB-BC physical constraints into the model architecture, promoting energy consistency during restoration; (c) achieves consistent improvements on the Atmos-Bench dataset across both 355 nm and 532 nm bands, outperforming state-of-the-art baseline models without relying on auxiliary inputs. Atmos-Bench establishes a new standard for satellite-based 3D atmospheric structure recovery and paves the way for deeper climate insight.