Projects per year
Abstract
Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics. Deep learning approaches, such as transformers, have recently challenged the simulation paradigm with complex network forecasts. However, they often act as data-driven black-box models that neglect the underlying physics and lack uncertainty quantification. We address these limitations with ClimODE, a spatiotemporal continuous-time process that implements a key principle of advection from statistical mechanics, namely, weather changes due to a spatial movement of quantities over time. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow, which also enables estimating the uncertainty in predictions. Our approach outperforms existing data-driven methods in global and regional forecasting with an order of magnitude smaller parameterization, establishing a new state of the art.
Original language | English |
---|---|
Title of host publication | The Twelfth International Conference on Learning Representations |
Publisher | International Conference on Learning Representations (ICLR) |
Pages | 1-23 |
Number of pages | 23 |
Publication status | Published - 2024 |
MoE publication type | D3 Professional conference proceedings |
Event | International Conference on Learning Representations - Messe Wien Exhibition and Congress Center, Vienna, Austria Duration: 7 May 2024 → 11 May 2024 Conference number: 12 https://iclr.cc/ |
Conference
Conference | International Conference on Learning Representations |
---|---|
Abbreviated title | ICLR |
Country/Territory | Austria |
City | Vienna |
Period | 07/05/2024 → 11/05/2024 |
Internet address |
Fingerprint
Dive into the research topics of 'ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs'. Together they form a unique fingerprint.Projects
- 1 Active
-
HEALED/Garg: Human-steered next-generation machine learning for reviving drug design
Garg, V. (Principal investigator), Laabid, N. (Project Member) & Verma, Y. (Project Member)
01/09/2021 → 31/08/2025
Project: Academy of Finland: Other research funding