English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Conventionally, Earth system (e.g., weather and climate) forecasting relieson numerical simulation with complex physical models and are hence bothexpensive in computation and demanding on domain expertise. With the explosivegrowth of the spatiotemporal Earth observation data in the past decade,data-driven models that apply Deep Learning (DL) are demonstrating impressivepotential for various Earth system forecasting tasks. The Transformer as anemerging DL architecture, despite its broad success in other domains, haslimited adoption in this area. In this paper, we propose Earthformer, aspace-time Transformer for Earth system forecasting. Earthformer is based on ageneric, flexible and efficient space-time attention block, named CuboidAttention. The idea is to decompose the data into cuboids and applycuboid-level self-attention in parallel. These cuboids are further connectedwith a collection of global vectors. We conduct experiments on the MovingMNISTdataset and a newly proposed chaotic N-body MNIST dataset to verify theeffectiveness of cuboid attention and figure out the best design ofEarthformer. Experiments on two real-world benchmarks about precipitationnowcasting and El Nino/Southern Oscillation (ENSO) forecasting show Earthformerachieves state-of-the-art performance. Code is available:https://github.com/amazon-science/earth-forecasting-transformer .

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting