Recovering Cloud Microstructures with Cascaded Diffusion Inversion

2026-07-06

AI Summary

Current satellite imagery suffers from insufficient spatial resolution to resolve the fine-scale cloud microstructures essential for weather modification efforts such as cloud seeding. This work proposes the first two-stage cascaded diffusion inversion framework tailored for cloud microstructure super-resolution. In the first stage, real paired data are leveraged to model sensor-induced degradation and achieve cross-spectral alignment. The second stage introduces a self-supervised internal degradation strategy to enhance the joint reconstruction of micro-textures and macro-structures. By integrating external supervision with internal self-supervision, the method significantly outperforms existing Transformer- and diffusion-based baselines in both reconstruction accuracy and visual fidelity, successfully recovering critical features such as convective turrets and cloud gaps. This approach provides a high-fidelity AI tool to advance cloud physics research and climate intervention strategies.

Abstract

High-resolution satellite imagery is critical for observing fine-scale cloud structures that inform weather modification strategies like cloud seeding for rain-enhancement. However, the spatial resolution of current geostationary and polar-orbiting satellites is often insufficient for capturing small cloud features. Current super-resolution methodologies are suited for natural images and, therefore, struggle to generalize to satellite-captured spectral images of cloud cover. To address this, we propose a two-stage diffusion-based super-resolution framework to enhance the resolution of multi-spectral cloud microstructures by a factor of $4\times$. Specifically, we use inverse diffusion to recover the high resolution properties from low resolution. Stage 1 utilizes real-world paired data to learn robust degradation handling and inter-sensor alignment, while Stage 2 employs a self-supervised internal downgrading of high resolution data to refine structural learning and texture synthesis. Our approach outperforms the state-of-the-art transformer and diffusion-based baselines in both reconstruction accuracy and visual quality. We demonstrate that the two-stage method better captures fine cloud microstructures (e.g. convective turrets and cloud gaps) that are crucial for effective cloud seeding decisions. Ablation studies confirm the complementary benefits of the two stages: Stage 1 excels in coarse structural fidelity, while Stage 2 contributes enhanced detail and realism. These results highlight a practical path toward improving cloud microphysics analysis and as a step towards utilizing AI for climate and sustainability. Our code and models are publicly available at: https://github.com/hananshafi/superresolution-cloud-microphysics.

Problem

• cloud microstructures
• satellite imagery
• spatial resolution
• super-resolution
• multi-spectral images

Innovation

• diffusion inversion
• super-resolution
• cloud microstructures
• two-stage framework
• self-supervised learning