Quantum-enhanced deep learning for severe weather prediction: a 10-qubit QCNN-LSTM for bow echo forecasting

Hélène Canot; Philippe Durand; Emmanuel Frénod; Hélène Canot; Philippe Durand; Emmanuel Frénod

doi:10.3934/bdia.2025008

Big Data and Information Analytics

2025, Volume 9, 152-187. doi: 10.3934/bdia.2025008

Previous Article Next Article

Research article

Quantum-enhanced deep learning for severe weather prediction: a 10-qubit QCNN-LSTM for bow echo forecasting

1.
Université de Bretagne-Sud, UMR 6205, Laboratoire de Mathématiques de Bretagne Atlantique, Vannes F-56000, France
2.
Conservatoire National des Arts et Métiers, Département de Mathématiques et Statistiques (M2N), 292 rue Saint-Martin, Paris Cedex 75141, France

Received: 27 September 2025 Revised: 26 October 2025 Accepted: 06 November 2025 Published: 12 November 2025

We present a quantum-enhanced deep learning framework for short-term forecasting of extreme convective weather systems, specifically targeting the formation of bow echo structures through prediction clouds. Our approach integrates a quantum convolutional neural network (QCNN) into a classical convolutional neural network-long short-term memory (CNN-LSTM) pipeline, incorporating a 10-qubit variational quantum circuit executed on the lightning.qubit simulator. The model is trained using heterogeneous meteorological data (satellite images, convective available potential energy (CAPE) fields, lightning activity) from the extreme storm that hit the Corsican coast on August 18, 2022, preceding the convective event and evaluated during the critical intensification window (0700–0800 h). We compare this hybrid quantum model with classical CNN-LSTM and CNN-LSTM-Transformer architectures using three complementary metrics: Root mean squared error (RMSE), structural similarity index (SSIM), and Wasserstein distance. The quantum model demonstrates superior robustness to input noise and adversarial perturbations fast gradient sign method (FGSM), maintaining spatial coherence and stable prediction under degradation. These findings highlight the capacity of quantum circuits to encode more resilient representations for meteorological inference. This study provides a concrete application of hybrid QCNN architectures in the domain of extreme weather forecasting and lays the groundwork for future integration of topological data analysis to assess the preservation of topological features in quantum predictions.
- quantum neural networks,
- extreme weather forecasting,
- bow echo,
- QCNN,
- adversarial robustness,
- deep learning,
- entangled representations
Citation: Hélène Canot, Philippe Durand, Emmanuel Frénod. Quantum-enhanced deep learning for severe weather prediction: a 10-qubit QCNN-LSTM for bow echo forecasting[J]. Big Data and Information Analytics, 2025, 9: 152-187. doi: 10.3934/bdia.2025008

Related Papers:

Abstract

We present a quantum-enhanced deep learning framework for short-term forecasting of extreme convective weather systems, specifically targeting the formation of bow echo structures through prediction clouds. Our approach integrates a quantum convolutional neural network (QCNN) into a classical convolutional neural network-long short-term memory (CNN-LSTM) pipeline, incorporating a 10-qubit variational quantum circuit executed on the lightning.qubit simulator. The model is trained using heterogeneous meteorological data (satellite images, convective available potential energy (CAPE) fields, lightning activity) from the extreme storm that hit the Corsican coast on August 18, 2022, preceding the convective event and evaluated during the critical intensification window (0700–0800 h). We compare this hybrid quantum model with classical CNN-LSTM and CNN-LSTM-Transformer architectures using three complementary metrics: Root mean squared error (RMSE), structural similarity index (SSIM), and Wasserstein distance. The quantum model demonstrates superior robustness to input noise and adversarial perturbations fast gradient sign method (FGSM), maintaining spatial coherence and stable prediction under degradation. These findings highlight the capacity of quantum circuits to encode more resilient representations for meteorological inference. This study provides a concrete application of hybrid QCNN architectures in the domain of extreme weather forecasting and lays the groundwork for future integration of topological data analysis to assess the preservation of topological features in quantum predictions.

References

[1]	Fujita TT, (1978) Manual of downburst identification for project NIMROD (No. NASA-CR-156953).
[2]	Przybylinski RW, (1995) The bow echo: Observations, numerical simulations, and severe weather detection methods. Weather Forecast 10: 203–218. https://doi.org/10.1175/1520-0434(1995)010%3C0203:TBEONS%3E2.0.CO;2 doi: 10.1175/1520-0434(1995)010%3C0203:TBEONS%3E2.0.CO;2
[3]	Klimowsky BA, Hjelmfelt MR, Bunkers MJ, (2004) Radar observations of the early evolution of bow echoes. Weather Forecast 19: 727–734. https://doi.org/10.1175/1520-0434(2004)019%3C0727:ROOTEE%3E2.0.CO;2 doi: 10.1175/1520-0434(2004)019%3C0727:ROOTEE%3E2.0.CO;2
[4]	Davis C, Atkins N, Bartels D, Bosart L, Bosart L, Coniglio M, Bryan G, et al. (2004) The bow echo and MCV experiment: Observations and opportunities: observations and opportunities. Bull Am Meteorol Soc 85: 1075–1093. https://doi.org/10.1175/BAMS-85-8-1075 doi: 10.1175/BAMS-85-8-1075
[5]	Kamani MM, Farhat F, Wistar S, Wang JZ, (2016) Shape matching using skeleton context for automated bow echo detection, In: 2016 IEEE International Conference on Big Data (Big Data), 901–908. https://doi.org/10.1109/BigData.2016.7840685
[6]	Zeng F, Hou J, (2018) Automatic detection of bow echoes from weather radar images, In: 2018 13th World Congress on Intelligent Control and Automation (WCICA), 503–508. https://doi.org/10.1109/WCICA.2018.8630468
[7]	Patil V, Das SK, Phadke A, (2019) Methods for mesoscale convective systems detection and tracking: A survey, In: 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 1–7. https://doi.org/10.1109/ICCCNT45670.2019.8944656
[8]	Johns RH, Hirt WD, (1987) Derechos: Widespread convectively induced windstorms. Weather Forecast 2: 32–49. https://doi.org/10.1175/1520-0434(1987)002%3C0032:DWCIW%3E2.0.CO;2 doi: 10.1175/1520-0434(1987)002%3C0032:DWCIW%3E2.0.CO;2
[9]	Corfidi SF, Coniglio MC, Cohen AE, Mead CM, (2016) A proposed revision to the definition of "derecho". Bull Am Meteorol Soc 97: 935–949. https://doi.org/10.1175/BAMS-D-14-00254.1 doi: 10.1175/BAMS-D-14-00254.1
[10]	Canot H, Durand P, Frénod E, (2025) Bow echo alarm system using topological data analysis. Appl Math Mod Challenges 3: 44–63. https://doi.org/10.3934/ammc.2025002 doi: 10.3934/ammc.2025002
[11]	Púčik T, The Derecho and Hailstorms of 18 August 2022, European Severe Storms Laboratory, 2022. Available from: https://www.essl.org/cms/the-derecho-and-hailstorms-of-18-august-2022/.
[12]	Fery L, Faranda D, (2023) Changes in synoptic circulations associated with documented derechos over France in the past 70 years. Weather Clim Dyn 2023. https://doi.org/10.5194/wcd-2023-8
[13]	Bernatz R, Bow Echo and Strong Rear Inflow Jet, 2023. Available from: https://www.faculty.luther.edu/bernatzr/Courses/Sci123/comet/radar/severe_signatures/navmenu.php_printname_print_bow_echo.htm_page_1.0.0.htm.
[14]	Lee WC, Wakimoto RM, Carbone RE, (1992) The evolution and structure of a "bow-echo-microburst" event. Part Ⅱ: The bow echo. Mon Weather Rev 120: 2211–2225. https://doi.org/10.1175/1520-0493(1992)120%3C2211:TEASOA%3E2.0.CO;2 doi: 10.1175/1520-0493(1992)120%3C2211:TEASOA%3E2.0.CO;2
[15]	Parker MD, Johnson RH, (2000) Organizational modes of midlatitude mesoscale convective systems. Mon Weather Rev 128: 3413–3436. https://doi.org/10.1175/1520-0493(2001)129%3C3413:OMOMMC%3E2.0.CO;2 doi: 10.1175/1520-0493(2001)129%3C3413:OMOMMC%3E2.0.CO;2
[16]	Elhoseiny M, Huang S, Elgammal A, (2015) Weather classification with deep convolutional neural networks, In: 2015 IEEE International Conference on Image Processing (ICIP), 3349–3353. https://doi.org/10.1109/ICIP.2015.7351424
[17]	Trok JT, Barnes EA, Davenport FV, Diffenbaugh NS, (2024) Machine learning—Based extreme event attribution. Sci Adv 10: eadl3242. https://doi.org/10.1126/sciadv.adl3242 doi: 10.1126/sciadv.adl3242
[18]	Liu Y, Racah E, Correa J, Khosrowshahi A, Lavers D, Kunkel K, et al. (2016) Application of deep convolutional neural networks for detecting extreme weather in climate datasets, preprint, arXiv:1605.01156. https://doi.org/10.48550/arXiv.1605.01156
[19]	Gagne II DJ, Haupt SE, Nychka DW, Thompson G, (2019) Interpretable deep learning for spatial analysis of severe hailstorms. Mon Weather Rev 147: 2827–2845. https://doi.org/10.1175/MWR-D-18-0316.1 doi: 10.1175/MWR-D-18-0316.1
[20]	Lagerquist R, McGovern A, Homeyer CR, Gagne II DJ, Smith T, (2020) Deep learning on three-dimensional multiscale data for next-hour tornado prediction. Mon Weather Rev 148: 2837–2861. https://doi.org/10.1175/MWR-D-19-0372.1 doi: 10.1175/MWR-D-19-0372.1
[21]	G Ayzel, M Heistermann, A Sorokin, O Nikitin, O Lukyanova, (2019) All convolutional neural networks for radar-based precipitation nowcasting. Proc Comput Sci 150: 186–192. https://doi.org/10.1016/j.procs.2019.02.036 doi: 10.1016/j.procs.2019.02.036
[22]	Price I, Sanchez-Gonzalez A, Alet F, Andersson TR, El-Kadi A, Masters D, et al. (2025) Probabilistic weather forecasting with machine learning. Nature 637: 84–90. https://doi.org/10.1038/s41586-024-08252-9 doi: 10.1038/s41586-024-08252-9
[23]	Mounier A, Raynaud L, Rottner L, Plu M, Arbogast P, Kreitz M, et al. (2022) Detection of bow echoes in kilometer-scale forecasts using a convolutional neural network. Artif Intell Earth Syst 1: e210010. https://doi.org/10.1175/AIES-D-21-0010.1 doi: 10.1175/AIES-D-21-0010.1
[24]	Gauch M, Kratzert F, Klotz D, Nearing G, Lin J, Hochreiter S, (2021) Rainfall-runoff prediction at multiple timescales with a single long short-term memory network. Hydrol Earth Syst Sci 25: 2045–2062. https://doi.org/10.5194/hess-25-2045-2021 doi: 10.5194/hess-25-2045-2021
[25]	Kratzert F, Klotz D, Shalev G, Klambauer G, Hochreiter S, Nearing G, (2019) Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets. Hydrol Earth Syst Sci 23: 5089–5110. https://doi.org/10.5194/hess-23-5089-2019 doi: 10.5194/hess-23-5089-2019
[26]	Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC, (2015) Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Adv Neural Inf Process Syst 2015: 28.
[27]	Tekin SF, Fazla A, Kozat SS, (2024) Numerical weather forecasting using convolutional-LSTM with attention and context matcher mechanisms. IEEE Trans Geosci Remote Sens 62: 1–13. https://doi.org/10.1109/TGRS.2024.3409084 doi: 10.1109/TGRS.2024.3409084
[28]	Cong I, Choi S, Lukin MD, (2019) Quantum convolutional neural networks. Nat Phys 15: 1273–1278. https://doi.org/10.1038/s41567-019-0648-8 doi: 10.1038/s41567-019-0648-8
[29]	Moreira MS, Guerreschi GG, Vlothuizen W, Marques JF, van Straten J, Premaratne SP, et al. (2023) Realization of a quantum neural network using repeat-until-success circuits in a superconducting quantum processor. NPJ Quantum Inf 9:118. https://doi.org/10.1038/s41534-023-00779-5 doi: 10.1038/s41534-023-00779-5
[30]	Herrmann J, Llima SM, Remm A, Zapletal P, McMahon NA, Scarato C, et al. (2022) Realizing quantum convolutional neural networks on a superconducting quantum processor to recognize quantum phases. Nat Commun 13: 4144. https://doi.org/10.1038/s41467-022-31679-5 doi: 10.1038/s41467-022-31679-5
[31]	Song Y, Li J, Wu Y, Qin S, Wen Q, Gao F, (2024) A resource-efficient quantum convolutional neural network. Front Phys 12: 1362690. https://doi.org/10.3389/fphy.2024.1362690 doi: 10.3389/fphy.2024.1362690
[32]	Gong LH, Pei JJ, Zhang TF, Zhou NR, (2024) Quantum convolutional neural network based on variational quantum circuits. Opt Commun 550: 129993. https://doi.org/10.1016/j.optcom.2023.129993 doi: 10.1016/j.optcom.2023.129993
[33]	Pastori L, Grundner A, Eyring V, Schwabe M, (2025) Quantum neural networks for cloud cover parameterizations in climate model, preprint, arXiv:2502.10131. https://doi.org/10.48550/arXiv.2502.10131
[34]	Lachure S, Damahe L, Lachure J, Sawarkar A, Bhati SS, Chhabra R, et al. (2024) A lightweight hybrid quantum convolution neural network for temperature forecasting, In: AIP Conference Proceedings 3188: 090008. https://doi.org/10.1063/5.0240207
[35]	Bazgir A, Zhang Y, (2024) QESM: A leap towards quantum-enhanced ML emulation framework for earth and climate modeling, preprint, arXiv:2410.01551. https://doi.org/10.48550/arXiv.2410.01551
[36]	Enos GR, Reagor MJ, Henderson MP, Young C, Horton K, Birch M, et al. (2021) Synthetic weather radar using hybrid quantum-classical machine learning, preprint, arXiv:2111.15605. https://doi.org/10.48550/arXiv.2111.15605
[37]	Eswaran U, Eswaran V, Murali K, Eswaran V, (2024) Quantum-based predictive modeling for extreme weather events, In: The Rise of Quantum Computing in Industry 6.0 Towards Sustainability: Revolutionizing Smart Disaster Management, Cham: Springer Nature Switzerland, 123–140. https://doi.org/10.1007/978-3-031-73350-5_8
[38]	Goodfellow IJ, Shlens J, Szegedy C, (2014) Explaining and harnessing adversarial examples, preprint, arXiv:1412.6572. https://doi.org/10.48550/arXiv.1412.6572
[39]	Griffiths DJ, Schroeter DF, (2018) Introduction to Quantum Mechanics, Cambridge University Press. https://doi.org/10.1017/9781316995433
[40]	Hestenes D, (1999) New Foundations for Classical Mechanics, Dordrecht: Springer Netherlands. https://doi.org/10.1007/0-306-47122-1
[41]	Lounesto P, (2001) Clifford algebras and spinors, In: Clifford Algebras and Their Applications in Mathematical Physics, Dordrecht: Springer Netherlands, 25–37. https://doi.org/10.1007/978-94-009-4728-3_2
[42]	Nakahara M, (2018) Geometry, Topology and Physics, CRC Press. https://doi.org/10.1201/9781315275826
[43]	Nielsen MA, Chuang IL, (2010) Quantum Computation and Quantum Information, Cambridge University Press.
[44]	EUMETSAT, Données Satellitaires de l'Orage en Corse du 18 Août 2022, 2022. Available from: https://www.eumetsat.int/.
[45]	Météo-France, Données Météorologiques de l'Orage en Corse du 18 Août 2022, 2022. Available from: https://donneespubliques.meteofrance.fr
[46]	Météorologix, Données Météorologiques de l'orage en Corse du 18 Août 2022, 2022. Available from: https://www.meteorologix.com.
[47]	Quandela, MosaiQ-Quandela's Photonic Quantum Cloud Platform, 2023. Available from: https://www.quandela.com/mosaiq.
[48]	Amazon Web Services, Amazon Braket: Explore and Experiment with Quantum Computing, 2023. Available from: https://aws.amazon.com/braket/.
[49]	OVHcloud, OVHcloud Quantum Project, 2023. Available from: https://www.ovhcloud.com/en/quantum/.

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)