weather and climate modeling are based on physics informed numerical models of the atmosphere. • These approaches aim to model the non-linear dynamics and complex interactions between multiple variables, which are challenging to approximate. • Additionally, many such numerical models are computationally intensive, especially when modeling the atmospheric phenomenon at a fine-grained spatial and temporal resolution. • Recent data-driven approaches based on machine learning instead aim to directly solve a downstream forecasting or projection task by learning a data-driven functional mapping using deep neural networks. • However, these networks are trained using curated and homogeneous climate datasets for specific spatiotemporal tasks, and thus lack the generality of numerical models. 4 大気などの観測量の非線形な関係をモデル化すると気象タスクに使えそう。 だけど計算が大変(特に粒度の細かいモデル) なのでDeepでポンしたい。 Deepでポンで結構いい感じに解けるけど、Deepの学習を適当にやると汎用性がないかもしれない。
ClimaX, a flexible and generalizable deep learning model for weather and climate science that can be trained using heterogeneous datasets spanning different variables, spatio-temporal coverage, and physical groundings. • ClimaX extends the Transformer architecture with novel encoding and aggregation blocks that allow effective use of available compute while maintaining general utility. • ClimaX is pre-trained with a self-supervised learning objective on climate datasets derived from CMIP6. • The pre-trained ClimaX can then be fine-tuned to address a breadth of climate and weather tasks, including those that involve atmospheric variables and spatio-temporal scales unseen during pretraining. • Compared to existing data-driven baselines, we show that this generality in ClimaX results in superior performance on benchmarks for weather forecasting and climate projections, even when pretrained at lower resolutions and compute budgets. 5 今流行りのTransformer+事前学習で頑張ったら出来た😄
• 実験評価方法は Rasp and Thuerey 2021 に従う • 詳細は(論文では)後ほど出てくる 18 • WeatherBench [Rasp+2020] ◦ Rasp et al., WeatherBench: a benchmark data set for data-driven weather forecasting, J. of Advances in Modeling Earth Systems, 2020 ◦ (おそらく)元が0.25°のERA5データをregridして、5.625°/2.8125°/1.40625°にしている Appendix C.2 ERA5 ERA5の詳細: https://confluence.ecmwf.int/display/CKB/ERA5%3A+data+documentation
forecasting at a time range between 2 weeks and 2 months [VR,2018] ◦ competition: https://s2s-ai-challenge.github.io/ • あまり注目されていないタスクらしい(けどタスクの意味がよく分からない) 26