arXiv:2502.10131 · Machine Learning Earth

Quantum neural networks for cloud cover parameterizations in climate models

Lorenzo Pastori, Arthur Grundner, Veronika Eyring, Mierk Schwabe

Published Feb 24, 2026• 2 citations

Abstract

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 models trained on short high-resolution climate simulations are promising candidates to replace conventional parameterizations. In this work, we explore the potential of quantum machine learning (QML), 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. We perform an extensive comparative analysis between several QNNs and classical neural networks (NNs), by training both ansatzes 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 ansatzes outperforming standard parameterizations used in climate models. Our study includes an analysis of the generalization ability of the models as well as the geometrical properties of their optimization landscape. We also 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. These results demonstrate the applicability of QML to learn meaningful patterns in climate data, and are thus relevant for a broad range of problems within the climate modeling community.

DOI: 10.1088/3049-4753/ae4981

Related papers

Quantum Machine Learning for Climate Modelling

Mierk Schwabe, Lorenzo Pastori, Valentina Sarandrea +1 more

Quantum machine learning (QML) is making rapid progress, and QML-based models hold the promise of quantum advantages such as potentially higher expressivity and generalizability than their classical counterparts. Here, we present work on using a quantum neural net (QNN) to develop a parameterization of cloud cover for an Earth system model (ESM). ESMs are needed for predicting and projecting climate change, and can be improved in hybrid models incorporating both traditional physics-based components as well as machine learning (ML) models. We show that a QNN can predict cloud cover with a performance similar to a classical NN with the same number of free parameters and significantly better than the traditional scheme. We also analyse the learning capability of the QNN in comparison to the classical NN and show that, at least for our example, QNNs learn more consistent relationships than classical NNs.

quant-pharXiv:2512.14208IEEE International Conference on Quantum Artificial Intelligence (QAI)Dec 17, 20250 citations

Explainable Quantum Machine Learning for cloud cover parameterization

Sarandrea, Valentina

Cloud cover parameterizations play an important role in climate models, influencing radiative transfer, atmospheric dynamics, and hydrological cycles. However, their correct formulation remains a major challenge in climate modeling, as subgrid-scale cloud processes must be approximated. Classical and quantum Neural Networks have been proposed as potential tools for improving these parameterizations. While previous studies suggest that classical neural networks can produce physically meaningful results, it remains unclear whether quantum neural networks (QNNs) exhibit similar capabilities or rely on spurious correlations. This study begins by comparing a classical neural network and a quantum neural network to assess whether they capture comparable physical dependencies when predicting cloud cover, before exploring alternative architectures for each approach. Using explainable AI (XAI) techniques, specifically SHapley Additive exPlanations (SHAP), the learned feature dependencies in both types of models are analyzed. This approach enables us to evaluate not only predictive performance but also the extent to which each model captures the underlying physics of cloud cover. Our results show that both classical and quantum models exhibit similar learning patterns, extracting comparable relationships from the data. While the QNN does not outperform the classical network, it achieves comparable results, suggesting that quantum machine learning (QML) could be a viable approach in this domain. These findings contribute to the ongoing exploration of QML in climate science and highlight the potential of quantum methods for atmospheric modeling. More broadly, this study supports the integration of machine learning into climate science while ensuring physical consistency and interpretability.

Apr 30, 20250 citations

Physics-anchored residual quantum neural networks for cloud-cover parameterization

Zhuo Wang, Ce Yu, Bin Yang

Compact quantum neural networks have been explored for cloud-cover parameterization, but their predictive value depends on how physical knowledge is incorporated and which classical models provide the reference. We investigate an offline residual formulation that retains a fitted \XR\ cloud-cover estimate and learns a correction to its logit in transformed target space. Using released ICON/DYAMOND-derived data, we compare ten model variants in six- and eight-input settings, with three matched replicates and 10,000 training samples per replicate. All quantum circuits use local Z readout and noiseless exact expectation values. Under a common 30-epoch protocol, residual prediction reduced physical-space test mean squared error relative to direct QNN prediction by 54.3\% and 38.8\% for six-input XYZ and ZZXY circuits, and by 49.2\% and 38.9\% for their eight-input versions. Residual QNNs also outperformed the selected compact residual multilayer perceptron in every paired replicate. A larger, longer-trained Grundner-Q1 adaptation nevertheless achieved lower error: residual Q1 reached mean MSEs of 0.00778 and 0.00791, compared with 0.01124 and 0.01082 for residual XYZ. The results support residual prediction for compact simulated QNNs within the tested budget and establish a clear boundary set by stronger classical references. They do not establish computational quantum advantage or online climate-model skill.

quant-pharXiv:2610.26279Oct 20, 20260 citations

Quantum machine learning-based parameterisation for atmospheric boundary layer turbulence

Lena Hannah Dogra, Janis Klamt, Veronika Eyring +1 more

The advent of quantum computing has opened unprecedented promises to tackle humanity' s most pressing challenges: computationally intractable problems might come within reach through quantum advantages. It is imperative for the field of climate modeling to explore possible uses of this emerging technology. Global climate models have successfully projected different future scenarios, but the spread in projections remains large, with subgrid-scale parameterizations being the main origin of these uncertainties. While machine learning models improve these parameterizations, quantum computing could bring decisive further improvements. Atmospheric turbulence affects the climate because it determines the rates of exchange of heat, moisture, and momentum between the Earth surface and the atmosphere, but has been especially hard to predict and model. Here, we develop a quantum machine learning-based subgrid-scale parameterization for the turbulent vertical heat flux. The training data are coarse-grained data from large-eddy-simulations of a dry convective boundary layer in an idealized setup without topography. Training various quantum and classical neural network models, we find that quantum models based on parametrized circuits with just 2 or 3 qubits achieve accuracies similar to classical models with the same number of trainable parameters. In contrast, the Smagorinsky closure applied to the coarse target resolution deviates strongly from the highly resolved flux. Both our quantum and classical models generalize well to unseen atmospheric conditions. Finally, the feature importances in our quantum models are on average more stable with respect to the random initial parameters, highlighting the possibility to exploit quantum advantages in climate and Earth system models.

Aug 5, 20260 citations

QESM: A Leap Towards Quantum-Enhanced ML Emulation Framework for Earth and Climate Modeling

Adib Bazgir, Yuwen Zhang

Current climate models often struggle with accuracy because they lack sufficient resolution, a limitation caused by computational constraints. This reduces the precision of weather forecasts and long-term climate predictions. To address this issue, we explored the use of quantum computing to enhance traditional machine learning (ML) models. We replaced conventional models like Convolutional Neural Networks (CNN), Multilayer Perceptrons (MLP), and Encoder-Decoder frameworks with their quantum versions: Quantum Convolutional Neural Networks (QCNN), Quantum Multilayer Perceptrons (QMLP), and Quantum Encoder-Decoders (QED). These quantum models proved to be more accurate in predicting climate-related outcomes compared to their classical counterparts. Using the ClimSim dataset, a large collection of climate data created specifically for ML-based climate prediction, we trained and tested these quantum models. Individually, the quantum models performed better, but their performance was further improved when we combined them using a meta-ensemble approach, which merged the strengths of each model to achieve the highest accuracy overall. This study demonstrates that quantum machine learning can significantly improve the resolution and accuracy of climate simulations. The results offer new possibilities for better predicting climate trends and weather events, which could have important implications for both scientific understanding and policy-making in the face of global climate challenges.

arXiv:2410.01551Oct 2, 20241 citation

How Hard Is Quantum Advantage? A Cloud Microphysics Stress Test for Variational Quantum Models

Felix Herbort, Ellen Sarauer, Daniel Ohl de Mello +7 more

Quantum machine learning (QML) could have the potential to leverage advantages of quantum over classical computing but still lacks strong evidence of actual improvements and scalability, partly due to phenomena such as barren plateaus. In this paper, we employ a hybrid quantum neural network (QNN) on a dataset on cloud microphysics, containing processes for phase transitions of water in the atmosphere and its related temperature changes, which are highly relevant for accurate climate predictions and projections. To reach optimal performance of our QNNs, we employ a rich and trainable frequency spectrum together with expressivity enhancing classical postprocessing. We find that our QNNs strongly benefit from extensive hyperparameter optimization and thereby demonstrate the feasibility of applying QNNs to complex physical systems. At the same time, the QNNs are outperformed by classical baselines in the form of simple fully-connected neural networks. We discuss identified bottlenecks of this class of quantum models to learn the full complexity of the cloud microphysics dataset to show that there is a need to further understand and improve variational quantum models for machine learning such that they might fill the gap where classical models fail or are inefficient.

quant-pharXiv:2607.04915Jul 7, 20260 citations