EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task
This dataset supports localized predictions of extreme weather impacts for applications like crop yield and forest health, but it is incremental as it builds on existing video prediction methods with new data.
The authors tackled the problem of forecasting satellite imagery by introducing EarthNet2021, a large-scale dataset with 32,000 samples of Sentinel 2 imagery, topography, and meteorological variables, which enables deep learning models to predict Earth surface conditions and improve spatial resolution by over 50 times compared to numerical models.
Satellite images are snapshots of the Earth surface. We propose to forecast them. We frame Earth surface forecasting as the task of predicting satellite imagery conditioned on future weather. EarthNet2021 is a large dataset suitable for training deep neural networks on the task. It contains Sentinel 2 satellite imagery at 20m resolution, matching topography and mesoscale (1.28km) meteorological variables packaged into 32000 samples. Additionally we frame EarthNet2021 as a challenge allowing for model intercomparison. Resulting forecasts will greatly improve (>x50) over the spatial resolution found in numerical models. This allows localized impacts from extreme weather to be predicted, thus supporting downstream applications such as crop yield prediction, forest health assessments or biodiversity monitoring. Find data, code, and how to participate at www.earthnet.tech