5 papers
Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning
Savannah L. Ferretti, Jerry Lin, Sara Shamekh +3
Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information across these dimensions in highly no…
Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a $50,000 Kaggle Competition
Jerry Lin, Zeyuan Hu, Tom Beucler +24
Subgrid machine-learning (ML) parameterizations have the potential to introduce a new generation of climate models that incorporate the effects of higher-resolution physics without…
Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations
Gunnar Behrens, Tom Beucler, Fernando Iglesias-Suarez +5
Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here…
Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations
Zeyuan Hu, Akshay Subramaniam, Zhiming Kuang +6
Modern climate projections often suffer from inadequate spatial and temporal resolution due to computational limitations, resulting in inaccurate representations of sub-grid proces…
Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles
Jerry Lin, Sungduk Yu, Liran Peng +6
Machine-learning (ML) parameterizations of subgrid processes (here of turbulence, convection, and radiation) may one day replace conventional parameterizations by emulating high-re…