</> Code with Papers by Syntology

Papers › EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a...

EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task

16 Apr 2021arXiv:2104.10066archive 2025-07-28

Christian Requena-Mesa, Vitus Benson, Markus Reichstein, Jakob Runge, Joachim Denzler

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

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

earthnet2021/earthnet-model-intercomparison-suite official report
earthnet2021/earthnet-toolkit NOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Crop Yield PredictionEarth Surface ForecastingTime Series ForecastingVideo ForensicsVideo Prediction

Datasets

Introduced by this paper, per the archive.

EarthNet2021

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Earth Surface Forecasting EarthNet2021 Extreme Track Channel-U-Net Baseline EarthNetScore 0.2364 #3 of 6 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 Extreme Track Arcon Baseline EarthNetScore 0.2215 #4 of 6 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 Extreme Track Persistence Baseline EarthNetScore 0.1939 #6 of 6 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 IID Track Channel-U-Net Baseline EarthNetScore 0.2902 #5 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 IID Track Arcon Baseline EarthNetScore 0.2803 #6 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 IID Track Persistence Baseline EarthNetScore 0.2625 #7 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 OOD Track Channel-U-Net Baseline EarthNetScore 0.2854 #5 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 OOD Track Arcon Baseline EarthNetScore 0.2655 #6 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 OOD Track Persistence Baseline EarthNetScore 0.2587 #7 of 7 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 Seasonal Track Persistence Baseline EarthNetScore 0.2676 #1 of 6 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 Seasonal Track Channel-U-Net Baseline EarthNetScore 0.1955 #4 of 6 Archive leaderboard report
Earth Surface Forecasting EarthNet2021 Seasonal Track Arcon Baseline EarthNetScore 0.1587 #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections