Quantum neural networks for cloud cover parameterizations in climate models

Long-term climate projections require running global Earth system models on timescales of hundreds of years and have relatively coarse resolution (from 40 to 160 km in the horizontal) due to their high computational costs. Unresolved subgrid-scale processes, such as clouds, are described in a semi-empirical manner by so called parameterizations, which are a major source of uncertainty in climate projections. Machine learning (ML) models trained on short high-resolution climate simulations are promising candidates to replace conventional parameterizations. In this work, we take a step further and explore the potential of quantum ML, and in particular quantum neural networks (QNNs), to develop cloud cover parameterizations. QNNs differ from their classical counterparts, and their potentially high expressivity turns them into promising tools for accurate data-driven schemes to be used in climate models. Here we perform an extensive comparative analysis between several QNNs and classical neural networks (NNs), by training both on data coming from high-resolution simulations with the ICOsahedral Non-hydrostatic weather and climate model (ICON). Our results show that the overall performance of the investigated QNNs is comparable to that of classical NNs of similar size, i.e. with the same number of trainable parameters, with both approaches outperforming standard parameterizations used in climate models. Our study also includes an analysis of the generalization ability of the models as well as the geometrical properties of their optimization landscape. We furthermore investigate the effects of finite sampling noise, and show that the training and the predictions of the QNNs are stable even in this noisy setting. This work critically investigates the applicability of quantum ML to learn meaningful patterns in climate data, and is thus relevant for a broad range of problems within the climate modeling community.