Generating the Cloud Motion Winds Field from Satellite Cloud Imagery Using Deep Learning Approach

TL;DR

This paper presents a deep learning approach to generate cloud motion winds fields from satellite imagery, outperforming traditional methods by learning features automatically and working with single images.

Contribution

Introduces a novel deep learning model and a large-scale dataset for predicting cloud motion winds from satellite images, enabling single-image wind field estimation.

Findings

Deep learning model accurately predicts wind fields

Single satellite images suffice for wind estimation

Proposed dataset supports model training and evaluation

Abstract

Cloud motion winds (CMW) are routinely derived by tracking features in sequential geostationary satellite infrared cloud imagery. In this paper, we explore the cloud motion winds algorithm based on data-driven deep learning approach, and different from conventional hand-craft feature tracking and correlation matching algorithms, we use deep learning model to automatically learn the motion feature representations and directly output the field of cloud motion winds. In addition, we propose a novel large-scale cloud motion winds dataset (CMWD) for training deep learning models. We also try to use a single cloud imagery to predict the cloud motion winds field in a fixed region, which is impossible to achieve using traditional algorithms. The experimental results demonstrate that our algorithm can predict the cloud motion winds field efficiently, and even with a single cloud imagery as input.