video-prediction

Earth Surface Forecasting

3260 papers • 126 benchmarks • 313 datasets

Conditional forecasting of future multi-spectral imagery.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-prediction

Trend

Dataset

Best Model

Actions

EarthNet2021 IID Track

EarthNet2021 OOD Track

Libraries

i

Use these libraries to find video-prediction models and implementations

Datasets

EarthNet2021

Subtasks

No subtasks available.

Most implemented papers

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

M. Reichstein, Joachim Denzler, Christian Requena-Mesa, V. Benson, J. Runge•Thu Apr 15 2021

This work frames Earth surface forecasting as the task of predicting satellite imagery conditioned on future weather, which allows localized impacts from extreme weather to be predicted, thus supporting downstream applications such as crop yield prediction, forest health assessments or biodiversity monitoring.

63

Content

0

Paper Graph

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

M. Reichstein, Joachim Denzler, Christian Requena-Mesa, V. Benson, Jakob Runge•Thu Dec 10 2020

The EarthNetScore is defined, a novel ranking criterion for models forecasting Earth surface reflectance, and EarthNet2021 is introduced, a new, curated dataset containing target spatio-temporal Sentinel 2 satellite imagery at 20 m resolution, matched with high-resolution topography and mesoscale weather variables.

3 0

Paper Graph

Understanding the Role of Weather Data for Earth Surface Forecasting using a ConvLSTM-based Model

Xiao Xiang Zhu, Stephan Günnemann, Codrut, -. Diaconu, Sudipan Saha•Tue May 31 2022

Climate change is perhaps the biggest single threat to humankind and the environment, as it severely impacts our terrestrial surface, home to most of the living species. Inspired by video prediction and exploiting the availability of Copernicus Sentinel-2 images, recent studies have attempted to forecast the land surface evolution as a function of past land surface evolution, elevation, and weather. Further extending this paradigm, we propose a model based on convolutional long short-term memory (ConvLSTM) that is computationally efficient (lightweight), however obtains superior results to the previous baselines. By introducing a ConvLSTM-based architecture to this problem, we can not only ingest the heterogeneous data sources (Sentinel-2 time-series, weather data, and a Digital Elevation Model (DEM)) but also explicitly condition the future predictions on the weather. Our experiments confirm the importance of weather parameters in understanding the land cover dynamics and show that weather maps are significantly more important than the DEM in this task. Furthermore, we perform generative simulations to investigate how varying a single weather parameter can alter the evolution of the land surface. All studies are performed using the EarthNet2021 dataset. The code, additional materials and results can be found at https://github.com/dcodrut/weather2land.

27 0

Paper Graph

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

Xingjian Shi, Zhihan Gao, Hao Wang, Dit-Yan Yeung, Yi Zhu, Yuyang Wang, Mu Li•Mon Jul 11 2022

The idea is to decompose the data into cuboids and apply cuboid-level self-attention in parallel, which achieves state-of-the-art performance on real-world benchmarks about precipitation nowcasting and El Nino/Southern Oscillation forecasting.

259 0

Paper Graph

Deep learning for satellite image forecasting of vegetation greenness

Klaus-Rudolf Kladny, Marco Milanta, Oto Mraz, K. Hufkens, B. Stocker•Tue Aug 16 2022

This work targets the spatial and temporal variations of land surface reflectance and vegetation greenness, measuring the density of green vegetation and active foliage area, conditioned on current and past climate and the local topography.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.