Abstract. We propose a deep learning method for Atmospheric Ozone Interpolation. Our method directly learns an end-to-end mapping between classically interpolated satellite ozone images and the real ozone measurements. The model's architecture represents a deep stack of convolutions (CNN) that takes the already interpolated images (Using the classical state-of-the-art interpolation method) as Input and outputs a more precise Interpolation of the Region of Interest. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art interpolation quality, and achieves optimal data processing latency (∆T) for production-ready near-real-time Atmospheric Image Interpolation, which has a big advantage over the state of the art classical interpolation algorithms. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. This method showcases the potential applications of deep learning in Remote Sensing and Climate Science.