Timezone: »
Numerical simulations of Earth's weather and climate require substantial amounts of computation. This has led to a growing interest in replacing subroutines that explicitly compute physical processes with approximate machine learning (ML) methods that are fast at inference time. Within weather and climate models, atmospheric radiative transfer (RT) calculations are especially expensive. This has made them a popular target for neural network-based emulators. However, prior work is hard to compare due to the lack of a comprehensive dataset and standardized best practices for ML benchmarking. To fill this gap, we build a large dataset, ClimART, with more than 10 million samples from present, pre-industrial, and future climate conditions, based on the Canadian Earth System Model. ClimART poses several methodological challenges for the ML community, such as multiple out-of-distribution test sets, underlying domain physics, and a trade-off between accuracy and inference speed. We also present several novel baselines that indicate shortcomings of datasets and network architectures used in prior work.
Author Information
Salva Rühling Cachay (Technical University of Darmstadt)
Venkatesh Ramesh (MILA)
Jason Cole
Howard Barker
David Rolnick (McGill / Mila)
More from the Same Authors
-
2020 : Graph Neural Networks for Improved El Ni√±o Forecasting »
Salva Rühling Cachay -
2021 Spotlight: Techniques for Symbol Grounding with SATNet »
Sever Topan · David Rolnick · Xujie Si -
2021 : ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models »
Salva Rühling Cachay · Venkatesh Ramesh · Jason N. S. Cole · Howard Barker · David Rolnick -
2021 : Detecting Abandoned Oil Wells Using Machine Learning and Semantic Segmentation »
Michelle Lin · David Rolnick -
2021 : ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models »
Salva Rühling Cachay · Venkatesh Ramesh · Jason N. S. Cole · Howard Barker · David Rolnick -
2021 : Detecting Abandoned Oil Wells Using Machine Learning and Semantic Segmentation »
Michelle Lin · David Rolnick -
2021 Poster: Techniques for Symbol Grounding with SATNet »
Sever Topan · David Rolnick · Xujie Si -
2021 Poster: End-to-End Weak Supervision »
Salva Rühling Cachay · Benedikt Boecking · Artur Dubrawski -
2020 Workshop: Tackling Climate Change with ML »
David Dao · Evan Sherwin · Priya Donti · Lauren Kuntz · Lynn Kaack · Yumna Yusuf · David Rolnick · Catherine Nakalembe · Claire Monteleoni · Yoshua Bengio -
2020 : QA Long Presentation I »
Salva Rühling Cachay · Juan Luis GonzalezBello · Gustavo Sutter P. Carvalho · Ariel Ruiz-Garcia -
2020 : Model Misspecification in Multiple Weak Supervision »
Salva Rühling Cachay