C3DIR: A Deep Learning 3-Dimensional Cloud Property Retrieval Scheme for Passive Satellite Imagers

2026-07-18

AI Summary

This study addresses the challenge of accurately retrieving three-dimensional distributions of ice water, liquid water, and rainfall within multilayer overlapping clouds from passive satellite imagers by proposing the C3DIR deep learning model. Leveraging an innovative voxel-level geometric co-registration strategy, the method precisely aligns observations from passive imagers with those from active sensors such as EarthCARE, establishing the first operational-oriented framework for 3D cloud property retrieval. The approach significantly outperforms current NOAA operational algorithms in estimating ice water content and column-integrated water paths and effectively resolves complex multilayer cloud structures. Although challenges remain in the retrieval of liquid water and rainfall, the model demonstrates substantial potential for applications in aviation meteorology, numerical weather prediction, and climate research.

Abstract

We develop the Cloud 3-Dimensional Imager Retrieval (C3DIR), a deep learning model that estimates 3-D cloud properties for multiple passive satellite imagers trained to match retrievals from the Earth Cloud Aerosol and Radiation Explorer(EarthCARE) ACM-CAP product. This work is aimed towards moving AI/ML 3-D cloud algorithms closer towards operational use. C3DIR predicts the occurrence water content of ice, cloud liquid, and rain along the imager line-of-sight and uses a voxel-level collocation approach to account for the misaligned viewing geometries of passive imagers and active profiling instruments. This precise collocation methodology allows for constructing vertical profiles using voxels contained by multiple imager pixels to facilitate comparisons with active profiling instruments. Qualitative case studies show that C3DIR can accurately depict multiple distinct overlapping cloud layers, albeit with some smoothing. Quantitative evaluations illustrate that C3DIR overall excels at hydrometeor detection which intuitively tends to be a function of water content. However, detection of voxels classified as liquid cloud remains difficult due to the their small geometric thickness, finer horizontal scale, and frequent tendency to be obscured or embedded within ice clouds. In general, water content estimation is reasonably accurate, yielding the best results in ice clouds but uncertainties remain for liquid and rain water content. Column-integrated water paths are in tighter agreement with EarthCARE. Comparisons with the algorithms underpinning current NOAA operational products highlight several areas where C3DIR may offer improvement. Overall, these results demonstrate the potential for C3DIR to provide flexible 3-D output depicting vertically resolved cloud structure which can offer broader utility for aviation applications, numerical weather modeling, and climate research.

Problem

• 3-D cloud property retrieval
• passive satellite imagers
• cloud vertical structure
• hydrometeor detection
• EarthCARE

Innovation

• deep learning
• 3D cloud retrieval
• voxel-level collocation
• passive satellite imager
• EarthCARE