Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow
This work addresses the need for higher temporal frequency observations in satellite data for applications like weather tracking and severe event study, representing an incremental improvement with domain-specific impact.
The paper tackled the problem of low temporal resolution in geostationary satellite imagery for weather tracking by applying a task-specific optical flow approach with deep convolutional neural networks to up-sample snapshots from 15 minutes to 1 minute, showing effectiveness in interpolating high-frequency severe weather events and capturing variability during convective precipitation events.
Applications of satellite data in areas such as weather tracking and modeling, ecosystem monitoring, wildfire detection, and land-cover change are heavily dependent on the trade-offs to spatial, spectral and temporal resolutions of observations. In weather tracking, high-frequency temporal observations are critical and used to improve forecasts, study severe events, and extract atmospheric motion, among others. However, while the current generation of geostationary satellites have hemispheric coverage at 10-15 minute intervals, higher temporal frequency observations are ideal for studying mesoscale severe weather events. In this work, we apply a task specific optical flow approach to temporal up-sampling using deep convolutional neural networks. We apply this technique to 16-bands of GOES-R/Advanced Baseline Imager mesoscale dataset to temporally enhance full disk hemispheric snapshots of different spatial resolutions from 15 minutes to 1 minute. Experiments show the effectiveness of task specific optical flow and multi-scale blocks for interpolating high-frequency severe weather events relative to bilinear and global optical flow baselines. Lastly, we demonstrate strong performance in capturing variability during a convective precipitation events.