Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON

Abstract

Machine learning (ML)-based parameterizations have been developed for Earth System Models (ESMs) with the goal to better represent subgrid-scale processes or to accelerate computations. ML-based parameterizations within hybrid ESMs have successfully learned subgrid-scale processes from short high-resolution simulations. However, most studies used a particular ML method to parameterize the subgrid tendencies or fluxes originating from the compound effect of various small-scale processes (e.g., radiation, convection, gravity waves) in mostly idealized settings or from superparameterizations. Here, we use a filtering technique to explicitly separate convection from these processes in simulations with the Icosahedral Non-hydrostatic modelling framework (ICON) in a realistic setting and benchmark various ML algorithms against each other offline. We discover that an unablated U-Net, while showing the best offline performance, learns reverse causal relations between convective precipitation and subgrid fluxes. While we were able to connect the learned relations of the U-Net to physical processes this was not possible for the non-deep learning-based Gradient Boosted Trees. The ML algorithms are then coupled online to the host ICON model. Our best online performing model, an ablated U-Net excluding precipitating tracer species, indicates higher agreement for simulated precipitation extremes and mean with the high-resolution simulation compared to the traditional scheme. However, a smoothing bias is introduced both in water vapor path and mean precipitation. Online, the ablated U-Net significantly improves stability compared to the non-ablated U-Net and runs stable for the full simulation period of 180 days. Our results hint to the potential to significantly reduce systematic errors with hybrid ESMs.

References in corpus (14)

• Scikit-learn: Machine Learning in Python
• Tune: A Research Platform for Distributed Model Selection and Training
• Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions
• Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events
• Data-driven medium-range weather prediction with a Resnet pretrained on climate simulations: A new model for WeatherBench
• Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining
• Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
• Intensification of convective extremes driven by cloud-cloud interaction
• Deep Learning Based Cloud Cover Parameterization for ICON
• A System for Massively Parallel Hyperparameter Tuning
• Causally-informed deep learning to improve climate models and projections
• Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models
• WeatherBench 2: A benchmark for the next generation of data-driven global weather models
• Capturing missing physics in climate model parameterizations using neural differential equations

Cited by in corpus (1)

• Quantum Machine Learning for Climate Modelling