Intermediate and Future Frame Prediction of Geostationary Satellite Imagery With Warp and Refine Network

TL;DR

This paper introduces WR-Net, a novel approach combining optical flow warping and refinement to improve temporal resolution and future frame prediction in geostationary satellite imagery, addressing resolution inconsistencies in climate analysis.

Contribution

The paper proposes WR-Net, a new model that uses optical flow and refinement for better temporal interpolation and future frame prediction in gray-scale satellite images.

Findings

WR-Net improves temporal resolution interpolation from 4 min to 2 min intervals.

Explicit optical flow use enhances future frame prediction accuracy.

The method effectively handles gray-scale geostationary satellite imagery.

Abstract

Geostationary satellite imagery has applications in climate and weather forecasting, planning natural energy resources, and predicting extreme weather events. For precise and accurate prediction, higher spatial and temporal resolution of geostationary satellite imagery is important. Although recent geostationary satellite resolution has improved, the long-term analysis of climate applications is limited to using multiple satellites from the past to the present due to the different resolutions. To solve this problem, we proposed warp and refine network (WR-Net). WR-Net is divided into an optical flow warp component and a warp image refinement component. We used the TV-L1 algorithm instead of deep learning-based approaches to extract the optical flow warp component. The deep-learning-based model is trained on the human-centric view of the RGB channel and does not work on geostationary satellites, which is gray-scale one-channel imagery. The refinement network refines the warped image through a multi-temporal fusion layer. We evaluated WR-Net by interpolation of temporal resolution at 4 min intervals to 2 min intervals in large-scale GK2A geostationary meteorological satellite imagery. Furthermore, we applied WR-Net to the future frame prediction task and showed that the explicit use of optical flow can help future frame prediction.