EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts

Video | Extreme Weather | Prevention

EarthNet2021 is a dataset for Earth surface forecasting, extreme summer prediction, and seasonal cycle prediction. It contains more than 32,000 samples containing Sentinel 2 level 2A imagery and daily climatic conditions. This dataset is introduced for video prediction.

  • ML task type: Video prediction
  • Data Source: Earth Observation Data and GeoSpatial Imagery (Satellite)
  • Size: >32,000 Multicube samples with satellite imagery and climatic conditions
  • Timespan: 2018 (Extreme summer track)
  • Geographical Coverage: Europe
  • Baseline Information
  • Evaluated on: unreported
  • Metrics used: EarthNetScore
  • Results as reported in original paper: unreported

Christian Requena-Mesa, Vitus Benson, Joachim Denzler, Jakob Runge, and Markus Reichstein. EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts. arXiv preprint arXiv:2012.06246, 2020.