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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Numerical simulations of Earth's weather and climate require substantialamounts of computation. This has led to a growing interest in replacingsubroutines that explicitly compute physical processes with approximate machinelearning (ML) methods that are fast at inference time. Within weather andclimate models, atmospheric radiative transfer (RT) calculations are especiallyexpensive. This has made them a popular target for neural network-basedemulators. However, prior work is hard to compare due to the lack of acomprehensive dataset and standardized best practices for ML benchmarking. Tofill this gap, we build a large dataset, ClimART, with more than \emph{10million samples from present, pre-industrial, and future climate conditions},based on the Canadian Earth System Model. ClimART poses several methodologicalchallenges for the ML community, such as multiple out-of-distribution testsets, underlying domain physics, and a trade-off between accuracy and inferencespeed. We also present several novel baselines that indicate shortcomings ofdatasets and network architectures used in prior work. Download instructions,baselines, and code are available at: https://github.com/RolnickLab/climart

ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models