EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task
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
PDF Abstract
Datasets
Introduced in the Paper:
EarthNet2021
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Earth Surface Forecasting | EarthNet2021 IID Track | Channel-U-Net Baseline | EarthNetScore | 0.2902 | # 5 | |
| Earth Surface Forecasting | EarthNet2021 IID Track | Arcon Baseline | EarthNetScore | 0.2803 | # 6 | |
| Earth Surface Forecasting | EarthNet2021 IID Track | Persistence Baseline | EarthNetScore | 0.2625 | # 7 | |
| Earth Surface Forecasting | EarthNet2021 OOD Track | Channel-U-Net Baseline | EarthNetScore | 0.2854 | # 5 | |
| Earth Surface Forecasting | EarthNet2021 OOD Track | Arcon Baseline | EarthNetScore | 0.2655 | # 6 | |
| Earth Surface Forecasting | EarthNet2021 OOD Track | Persistence Baseline | EarthNetScore | 0.2587 | # 7 |
