Interpreting and Stabilizing Machine-learning Parametrizations of Convection

Abstract

Neural networks are a promising technique for parameterizing sub-grid-scale physics (e.g. moist atmospheric convection) in coarse-resolution climate models, but their lack of interpretability and reliability prevents widespread adoption. For instance, it is not fully understood why neural network parameterizations often cause dramatic instability when coupled to atmospheric fluid dynamics. This paper introduces tools for interpreting their behavior that are customized to the parameterization task. First, we assess the nonlinear sensitivity of a neural network to lower-tropospheric stability and the mid-tropospheric moisture, two widely-studied controls of moist convection. Second, we couple the linearized response functions of these neural networks to simplified gravity-wave dynamics, and analytically diagnose the corresponding phase speeds, growth rates, wavelengths, and spatial structures. To demonstrate their versatility, these techniques are tested on two sets of neural networks, one trained with a super-parametrized version of the Community Atmosphere Model (SPCAM) and the second with a near-global cloud-resolving model (GCRM). Even though the SPCAM simulation has a warmer climate than the cloud-resolving model, both neural networks predict stronger heating/drying in moist and unstable environments, which is consistent with observations. Moreover, the spectral analysis can predict that instability occurs when GCMs are coupled to networks that support gravity waves that are unstable and have phase speeds larger than 5 m/s. In contrast, standing unstable modes do not cause catastrophic instability. Using these tools, differences between the SPCAM- vs. GCRM- trained neural networks are analyzed, and strategies to incrementally improve both of their coupled online performance unveiled.

References in corpus (2)

• Methods for Interpreting and Understanding Deep Neural Networks
• Deep learning to represent sub-grid processes in climate models

Cited by in corpus (11)

• Will Artificial Intelligence supersede Earth System and Climate Models?
• Bridging observation, theory and numerical simulation of the ocean using Machine Learning
• Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
• Deep Learning Based Cloud Cover Parameterization for ICON
• Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models with Real-Geography Boundary Conditions
• Non-local parameterization of atmospheric subgrid processes with neural networks
• Climbing down Charney's ladder: Machine Learning and the post-Dennard era of computational climate science
• Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer using Neural Networks
• A Multifidelity deep operator network approach to closure for multiscale systems
• Opportunities and challenges of quantum computing for climate modelling
• Towards Physically Consistent Deep Learning For Climate Model Parameterizations