EarthNet2021: A novel large-scale dataset and challenge for forecasting
localized climate impacts
- URL: http://arxiv.org/abs/2012.06246v1
- Date: Fri, 11 Dec 2020 11:21:00 GMT
- Title: EarthNet2021: A novel large-scale dataset and challenge for forecasting
localized climate impacts
- Authors: Christian Requena-Mesa, Vitus Benson, Joachim Denzler, Jakob Runge and
Markus Reichstein
- Abstract summary: Large Earth observation datasets now enable us to create machine learning models capable of translating coarse weather information into high-resolution Earth surface forecasts.
We define high-resolution Earth surface forecasting as video prediction of satellite imagery conditional on mesoscale weather forecasts.
We introduce EarthNet 2021, a new curated dataset containing target-temporal Sentinel 2 satellite imagery at 20 m resolution, matched with high-resolution topography and mesoscale (1.28 km) weather variables.
- Score: 12.795776149170978
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Climate change is global, yet its concrete impacts can strongly vary between
different locations in the same region. Seasonal weather forecasts currently
operate at the mesoscale (> 1 km). For more targeted mitigation and adaptation,
modelling impacts to < 100 m is needed. Yet, the relationship between driving
variables and Earth's surface at such local scales remains unresolved by
current physical models. Large Earth observation datasets now enable us to
create machine learning models capable of translating coarse weather
information into high-resolution Earth surface forecasts. Here, we define
high-resolution Earth surface forecasting as video prediction of satellite
imagery conditional on mesoscale weather forecasts. Video prediction has been
tackled with deep learning models. Developing such models requires
analysis-ready datasets. We introduce EarthNet2021, a new, curated dataset
containing target spatio-temporal Sentinel 2 satellite imagery at 20 m
resolution, matched with high-resolution topography and mesoscale (1.28 km)
weather variables. With over 32000 samples it is suitable for training deep
neural networks. Comparing multiple Earth surface forecasts is not trivial.
Hence, we define the EarthNetScore, a novel ranking criterion for models
forecasting Earth surface reflectance. For model intercomparison we frame
EarthNet2021 as a challenge with four tracks based on different test sets.
These allow evaluation of model validity and robustness as well as model
applicability to extreme events and the complete annual vegetation cycle. In
addition to forecasting directly observable weather impacts through
satellite-derived vegetation indices, capable Earth surface models will enable
downstream applications such as crop yield prediction, forest health
assessments, coastline management, or biodiversity monitoring. Find data, code,
and how to participate at www.earthnet.tech .
Related papers
- Aurora: A Foundation Model of the Atmosphere [56.97266186291677]
We introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data.
In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts.
arXiv Detail & Related papers (2024-05-20T14:45:18Z) - FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather
Forecasting [56.73502043159699]
This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution.
It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model.
The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
arXiv Detail & Related papers (2024-01-28T13:23:25Z) - Observation-Guided Meteorological Field Downscaling at Station Scale: A
Benchmark and a New Method [66.80344502790231]
We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset.
Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors.
Our proposed method outperforms other specially designed baseline models on multiple surface variables.
arXiv Detail & Related papers (2024-01-22T14:02:56Z) - Residual Diffusion Modeling for Km-scale Atmospheric Downscaling [51.061954281398116]
A cost-effective downscaling model is trained from a high-resolution 2-km weather model over Taiwan.
textitCorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes.
Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to-km-scales machine learning weather predictions.
arXiv Detail & Related papers (2023-09-24T19:57:22Z) - Multi-modal learning for geospatial vegetation forecasting [1.8180482634934092]
We introduce GreenEarthNet, the first dataset specifically designed for high-resolution vegetation forecasting.
We also present Contextformer, a novel deep learning approach for predicting vegetation greenness from Sentinel 2 satellite images.
To the best of our knowledge, this work presents the first models for continental-scale vegetation modeling at fine resolution able to capture anomalies beyond the seasonal cycle.
arXiv Detail & Related papers (2023-03-28T17:59:05Z) - GraphCast: Learning skillful medium-range global weather forecasting [107.40054095223779]
We introduce a machine learning-based method called "GraphCast", which can be trained directly from reanalysis data.
It predicts hundreds of weather variables, over 10 days at 0.25 degree resolution globally, in under one minute.
We show that GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets.
arXiv Detail & Related papers (2022-12-24T18:15:39Z) - Long-term hail risk assessment with deep neural networks [0.0]
Hail risk assessment is necessary to estimate and reduce damage to crops, orchards, and infrastructure.
There are no machine learning models for data-driven forecasting of changes in hail frequency for a given area.
This study compares two approaches and introduces a model suitable for the task of forecasting changes in hail frequency for ongoing decades.
arXiv Detail & Related papers (2022-08-31T18:24:39Z) - EarthNet2021: A large-scale dataset and challenge for Earth surface
forecasting as a guided video prediction task [12.795776149170978]
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.
Resulting forecasts will greatly improve over the spatial resolution found in numerical models.
arXiv Detail & Related papers (2021-04-16T09:47:30Z) - Augmented Convolutional LSTMs for Generation of High-Resolution Climate
Change Projections [1.7503398807380832]
We present auxiliary informed-temporal neural architecture for statistical downscaling.
Current study performs daily downscaling of precipitation variable from an ESM output at 1.15 degrees (115 km) to 0.25 degrees (25 km) over the world's most climatically diversified country, India.
arXiv Detail & Related papers (2020-09-23T17:52:09Z) - CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds [0.0]
In this paper, we present a novel satellite-based dataset called CloudCast''.
It consists of 70,080 images with 10 different cloud types for multiple layers of the atmosphere annotated on a pixel level.
The spatial resolution of the dataset is 928 x 1530 pixels (3x3 km per pixel) with 15-min intervals between frames for the period 2017-01-01 to 2018-12-31.
arXiv Detail & Related papers (2020-07-15T20:20:55Z) - A generative adversarial network approach to (ensemble) weather
prediction [91.3755431537592]
We use a conditional deep convolutional generative adversarial network to predict the geopotential height of the 500 hPa pressure level, the two-meter temperature and the total precipitation for the next 24 hours over Europe.
The proposed models are trained on 4 years of ERA5 reanalysis data from 2015-2018 with the goal to predict the associated meteorological fields in 2019.
arXiv Detail & Related papers (2020-06-13T20:53:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.