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

TL;DR

This paper introduces EarthNet2021, a large-scale satellite imagery dataset and challenge for Earth surface forecasting, framing it as a guided video prediction task conditioned on weather data, aiming to enhance localized impact predictions.

Contribution

It provides a comprehensive dataset and challenge framework for Earth surface forecasting using deep learning, bridging satellite imagery and weather data for improved spatial-temporal predictions.

Findings

Forecasts outperform traditional models by over 50x in spatial resolution

Enables localized impact predictions for extreme weather events

Supports applications like crop yield and biodiversity monitoring

Abstract

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