Climate Model
Climate models aim to simulate Earth's climate system, primarily to project future climate change and understand its impacts. Current research heavily focuses on integrating machine learning (ML) techniques, such as neural networks (including convolutional, recurrent, and transformer architectures), and reinforcement learning, into traditional physics-based models to improve accuracy, efficiency, and uncertainty quantification. This hybrid approach addresses limitations in representing subgrid-scale processes and computationally expensive simulations, ultimately enhancing the reliability of climate projections and informing mitigation and adaptation strategies.
Papers
Uncertainty-enabled machine learning for emulation of regional sea-level change caused by the Antarctic Ice Sheet
Myungsoo Yoo, Giri Gopalan, Matthew J. Hoffman, Sophie Coulson, Holly Kyeore Han, Christopher K. Wikle, Trevor Hillebrand
Probabilistic Emulation of a Global Climate Model with Spherical DYffusion
Salva Rühling Cachay, Brian Henn, Oliver Watt-Meyer, Christopher S. Bretherton, Rose Yu
A Temporal Stochastic Bias Correction using a Machine Learning Attention model
Omer Nivron, Damon J. Wischik, Mathieu Vrac, Emily Shuckburgh, Alex T. Archibald
Machine-learning prediction of tipping with applications to the Atlantic Meridional Overturning Circulation
Shirin Panahi, Ling-Wei Kong, Mohammadamin Moradi, Zheng-Meng Zhai, Bryan Glaz, Mulugeta Haile, Ying-Cheng Lai
Generative Adversarial Models for Extreme Downscaling of Climate Datasets
Guiye Li, Guofeng Cao