{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:17:05Z","timestamp":1778257025997,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"UKRI New Horizon grant","award":["EP\/X017249\/1"],"award-info":[{"award-number":["EP\/X017249\/1"]}]},{"name":"UKRI New Horizon grant","award":["EP\/X017249\/1"],"award-info":[{"award-number":["EP\/X017249\/1"]}]},{"name":"UKRI New Horizon grant","award":["EP\/X017249\/1"],"award-info":[{"award-number":["EP\/X017249\/1"]}]},{"name":"UKRI AI for Net Zero grant","award":["EP\/Y005619\/1"],"award-info":[{"award-number":["EP\/Y005619\/1"]}]},{"name":"UKRI AI for Net Zero grant","award":["EP\/Y005619\/1"],"award-info":[{"award-number":["EP\/Y005619\/1"]}]},{"name":"ERC Starting Grant PhyCo","award":["949388"],"award-info":[{"award-number":["949388"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In the current Noisy Intermediate Scale Quantum (NISQ) era, the presence of noise deteriorates the performance of quantum computing algorithms. Quantum reservoir computing (QRC) is a type of quantum machine learning algorithm, which, however, can benefit from different types of tuned noise. In this paper, we analyze how finite sampling noise affects the chaotic time series prediction of the gate-based QRC and recurrence-free quantum reservoir computing (RF-QRC) models. First, we examine RF-QRC and show that, even without a recurrent loop, it contains temporal information about previous reservoir states using leaky integrated neurons. This makes RF-QRC different from quantum extreme learning machines (QELM). Second, we show that finite sampling noise degrades the prediction capabilities of both QRC and RF-QRC while affecting QRC more due to the propagation of noise. Third, we optimize the training of the finite-sampled quantum reservoir computing framework using two methods: (a) singular value decomposition (SVD) applied to the data matrix containing noisy reservoir activation states and (b) data-filtering techniques to remove the high frequencies from the noisy reservoir activation states. We show that denoising reservoir activation states improves the signal-to-noise ratios with smaller training loss. Finally, we demonstrate that the training and denoising of the noisy reservoir activation signals in RF-QRC are highly parallelizable on multiple quantum processing units (QPUs) as compared to the QRC architecture with recurrent connections. The analyses are numerically showcased on prototypical chaotic dynamical systems with relevance to turbulence. This work opens opportunities for using quantum reservoir computing with finite samples for time series forecasting on near-term quantum hardware.<\/jats:p>","DOI":"10.1007\/s42484-025-00261-9","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:15:29Z","timestamp":1740640529000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Optimal training of finitely sampled quantum reservoir computers for forecasting of chaotic dynamics"],"prefix":"10.1007","volume":"7","author":[{"given":"Osama","family":"Ahmed","sequence":"first","affiliation":[]},{"given":"Felix","family":"Tennie","sequence":"additional","affiliation":[]},{"given":"Luca","family":"Magri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"261_CR1","doi-asserted-by":"crossref","unstructured":"Aaronson S (2018) Shadow tomography of quantum states. In: Proceedings of the 50th annual ACM SIGACT symposium on theory of computing, pp 325\u2013338","DOI":"10.1145\/3188745.3188802"},{"issue":"4","key":"261_CR2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.6.043082","volume":"6","author":"O Ahmed","year":"2024","unstructured":"Ahmed O, Tennie F, Magri L (2024) Prediction of chaotic dynamics and extreme events: a recurrence-free quantum reservoir computing approach. Phys Rev Res 6(4):043082","journal-title":"Phys Rev Res"},{"key":"261_CR3","doi-asserted-by":"crossref","unstructured":"Boffetta G, Cencini M, Falcioni M et al (2002) Predictability: a way to characterize complexity. Phys Reports 356(6):367\u2013474","DOI":"10.1016\/S0370-1573(01)00025-4"},{"key":"261_CR4","doi-asserted-by":"crossref","unstructured":"Carroll TL (2020) Dimension of reservoir computers. Chaos: An Interdisciplinary J Nonlinear Sci 30(1)","DOI":"10.1063\/1.5128898"},{"key":"261_CR5","doi-asserted-by":"crossref","unstructured":"Carroll TL, Pecora LM (2019) Network structure effects in reservoir computers. Chaos: An Interdiscip J Nonlinear Sci 29(8)","DOI":"10.1063\/1.5097686"},{"key":"261_CR6","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/978-3-030-22747-0_15","volume-title":"Computational Science - ICCS 2019","author":"NAK Doan","year":"2019","unstructured":"Doan NAK, Polifke W, Magri L (2019) Physics-informed echo state networks for chaotic systems forecasting. In: Rodrigues JMF, Cardoso PJS, Monteiro J et al (eds) Computational Science - ICCS 2019. Springer International Publishing, Cham, pp 192\u2013198"},{"key":"261_CR7","doi-asserted-by":"crossref","unstructured":"Domingo L, Carlo G, Borondo F (2023) Taking advantage of noise in quantum reservoir computing. Sci Reports 13(1):8790","DOI":"10.1038\/s41598-023-35461-5"},{"key":"261_CR8","doi-asserted-by":"publisher","unstructured":"Dudas J, Carles B, Plouet E, et\u00a0al (2023) Quantum reservoir computing implementation on coherently coupled quantum oscillators. npj Quantum Inf 9(1):1\u20137. https:\/\/doi.org\/10.1038\/s41534-023-00734-4, https:\/\/www.nature.com\/articles\/s41534-023-00734-4, number: 1 Publisher: Nature Publishing Group","DOI":"10.1038\/s41534-023-00734-4"},{"issue":"1","key":"261_CR9","doi-asserted-by":"publisher","first-page":"19326","DOI":"10.1038\/s41598-023-45015-4","volume":"13","author":"D Fry","year":"2023","unstructured":"Fry D, Deshmukh A, Chen SYC, Rastunkov V, Markov V (2023) Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction. Sci Rep 13(1):19326","journal-title":"Sci Rep"},{"key":"261_CR10","doi-asserted-by":"publisher","unstructured":"Fujii K, Nakajima K (2021) Quantum reservoir computing: a reservoir approach toward quantum machine learning on near-term quantum devices, Springer Singapore, Singapore, pp 423\u2013450. https:\/\/doi.org\/10.1007\/978-981-13-1687-6_18,","DOI":"10.1007\/978-981-13-1687-6_18"},{"key":"261_CR11","doi-asserted-by":"publisher","unstructured":"GABBIANI F, COX SJ (2010) Chapter 10 - reduced single neuron models. In: GABBIANI F, COX SJ (eds) Mathematics for Neuroscientists. Academic Press, London, pp 143\u2013154https:\/\/doi.org\/10.1016\/B978-0-12-374882-9.00010-1, https:\/\/www.sciencedirect.com\/science\/article\/pii\/B9780123748829000101","DOI":"10.1016\/B978-0-12-374882-9.00010-1"},{"issue":"4","key":"261_CR12","volume":"13","author":"F Hu","year":"2023","unstructured":"Hu F, Angelatos G, Khan SA et al (2023) Tackling sampling noise in physical systems for machine learning applications: fundamental limits and eigentasks. Phys Rev X 13(4):041020","journal-title":"Phys Rev X"},{"issue":"10","key":"261_CR13","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1038\/s41567-020-0932-7","volume":"16","author":"HY Huang","year":"2020","unstructured":"Huang HY, Kueng R, Preskill J (2020) Predicting many properties of a quantum system from very few measurements. Nat Phys 16(10):1050\u20131057","journal-title":"Nat Phys"},{"key":"261_CR14","unstructured":"IBM Quantum https:\/\/quantum.ibm.com\/ (2024)"},{"key":"261_CR15","unstructured":"Jaeger H (2001) The\u201d echo state\u201d approach to analysing and training recurrent neural networks-with an erratum note\u2019. Bonn, Germany: German National Research Center for Information Technology GMD Technical Report 148"},{"key":"261_CR16","doi-asserted-by":"publisher","unstructured":"Jaeger H, Mantas, Popovici D, et\u00a0al (2007) Optimization and applications of echo state networks with leaky- integrator neurons. Neural Netw 20(3):335\u2013352. https:\/\/doi.org\/10.1016\/j.neunet.2007.04.016, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S089360800700041X, echo State Networks and Liquid State Machines","DOI":"10.1016\/j.neunet.2007.04.016"},{"issue":"1","key":"261_CR17","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/JSEN.2010.2049351","volume":"11","author":"SK Jha","year":"2010","unstructured":"Jha SK, Yadava R (2010) Denoising by singular value decomposition and its application to electronic nose data processing. IEEE Sensors J 11(1):35\u201344","journal-title":"IEEE Sensors J"},{"key":"261_CR18","unstructured":"Khan SA, Hu F, Angelatos G, et\u00a0al (2021) Physical reservoir computing using finitely-sampled quantum systems. arXiv:2110.13849"},{"key":"261_CR19","doi-asserted-by":"crossref","unstructured":"Khan SA, Kaufman R, Mesits B, et\u00a0al (2023) Practical trainable temporal post-processor for multi-state quantum measurement. arXiv:2310.18519","DOI":"10.1103\/PRXQuantum.5.020364"},{"key":"261_CR20","doi-asserted-by":"crossref","unstructured":"Kobayashi K, Fujii K, Yamamoto N (2024) Feedback-driven quantum reservoir computing for time-series analysis. arXiv:2406.15783","DOI":"10.1103\/PRXQuantum.5.040325"},{"key":"261_CR21","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.22331\/q-2024-06-25-1385","volume":"8","author":"DA Kreplin","year":"2024","unstructured":"Kreplin DA, Roth M (2024) Reduction of finite sampling noise in quantum neural networks. Quantum 8:1385","journal-title":"Quantum"},{"issue":"4","key":"261_CR22","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s00422-008-0237-x","volume":"99","author":"P Lansky","year":"2008","unstructured":"Lansky P, Ditlevsen S (2008) A review of the methods for signal estimation in stochastic diffusion leaky integrate-and-fire neuronal models. Biol Cybernet 99(4):253\u2013262","journal-title":"Biol Cybernet"},{"key":"261_CR23","unstructured":"Lorenz E (1995) Predictability: a problem partly solved. PhD thesis, Shinfield Park, Reading"},{"key":"261_CR24","doi-asserted-by":"publisher","unstructured":"Lukosevicius M (2012) A practical guide to applying echo state networks. In: Montavon G, Orr GB, Muller KR (eds) Neural Networks: Tricks of the trade, Second Edition. Lecture Notes in Computer Science, Springer, Berlin, Heidelberg, pp 659\u2013686, https:\/\/doi.org\/10.1007\/978-3-642-35289-8_36","DOI":"10.1007\/978-3-642-35289-8_36"},{"key":"261_CR25","doi-asserted-by":"publisher","unstructured":"Maass W, Natschl\u00e4ger T, Markram H (2002) Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Computation 14(11):2531\u20132560https:\/\/doi.org\/10.1162\/089976602760407955 https:\/\/direct.mit.edu\/neco\/article-pdf\/14\/11\/2531\/815288\/089976602760407955.pdf","DOI":"10.1162\/089976602760407955"},{"issue":"1","key":"261_CR26","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1038\/s41467-018-07090-4","volume":"9","author":"JR McClean","year":"2018","unstructured":"McClean JR, Boixo S, Smelyanskiy VN et al (2018) Barren plateaus in quantum neural network training landscapes. Nat Commun 9(1):4812","journal-title":"Nat Commun"},{"key":"261_CR27","doi-asserted-by":"crossref","unstructured":"Moehlis J, Faisst H, Eckhardt B (2004) A low-dimensional model for turbulent shear flows. New J Phys 6:56\u201356","DOI":"10.1088\/1367-2630\/6\/1\/056"},{"key":"261_CR28","doi-asserted-by":"publisher","unstructured":"Mujal P, Mart\u00ednez-Pe\u00f1a R, Nokkala J, et\u00a0al (2021) Opportunities in quantum reservoir computing and extreme learning machines. https:\/\/doi.org\/10.48550\/arXiv.2102.11831, https:\/\/ui.adsabs.harvard.edu\/abs\/2021arXiv210211831M, publication Title: arXiv e-prints ADS Bibcode: 2021arXiv210211831M","DOI":"10.48550\/arXiv.2102.11831"},{"key":"261_CR29","doi-asserted-by":"publisher","unstructured":"Mujal P, Mart\u00ednez-Pe\u00f1a R, Giorgi GL, et\u00a0al (2023) Time-series quantum reservoir computing with weak and projective measurements. npj Quantum Inf 9(1):16. https:\/\/doi.org\/10.1038\/s41534-023-00682-z","DOI":"10.1038\/s41534-023-00682-z"},{"key":"261_CR30","volume-title":"Quantum computation and quantum information: 10th","author":"MA Nielsen","year":"2011","unstructured":"Nielsen MA, Chuang IL (2011) Quantum computation and quantum information: 10th. Cambridge University Press, Anniversary"},{"key":"261_CR31","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"261_CR32","doi-asserted-by":"crossref","unstructured":"Pfeffer P, Heyder F, Schumacher J (2022) Hybrid quantum-classical reservoir computing of thermal convection flow. Phys Rev Res 4(3):033176","DOI":"10.1103\/PhysRevResearch.4.033176"},{"issue":"4","key":"261_CR33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.043242","volume":"5","author":"P Pfeffer","year":"2023","unstructured":"Pfeffer P, Heyder F, Schumacher J (2023) Reduced-order modeling of two-dimensional turbulent Rayleigh-B\u00e9nard flow by hybrid quantum-classical reservoir computing. Phys Rev Res 5(4):043242","journal-title":"Phys Rev Res"},{"key":"261_CR34","doi-asserted-by":"crossref","unstructured":"Preskill J (1998) Fault-tolerant quantum computation. In: Introduction to quantum computation and information. World Sci pp 213\u2013269","DOI":"10.1142\/9789812385253_0008"},{"key":"261_CR35","doi-asserted-by":"publisher","unstructured":"Qiskit contributors (2023) Qiskit: an open-source framework for quantum computing. https:\/\/doi.org\/10.5281\/zenodo.2573505","DOI":"10.5281\/zenodo.2573505"},{"key":"261_CR36","doi-asserted-by":"crossref","unstructured":"Racca A, Magri L (2021) Robust optimization and validation of echo state networks for learning chaotic dynamics. Neural Net 142:252\u2013268","DOI":"10.1016\/j.neunet.2021.05.004"},{"key":"261_CR37","doi-asserted-by":"crossref","unstructured":"Racca A, Magri L (2022) Data-driven prediction and control of extreme events in a chaotic flow. Phys Rev Fluids 7(10):104402","DOI":"10.1103\/PhysRevFluids.7.104402"},{"issue":"4","key":"261_CR38","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/MSP.2011.941097","volume":"28","author":"RW Schafer","year":"2011","unstructured":"Schafer RW (2011) What is a Savitzky-Golay filter?[lecture notes]. IEEE Signal Process Mag 28(4):111\u2013117","journal-title":"IEEE Signal Process Mag"},{"issue":"2","key":"261_CR39","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1515\/cdbme-2017-0052","volume":"3","author":"T Schanze","year":"2017","unstructured":"Schanze T (2017) Removing noise in biomedical signal recordings by singular value decomposition. Current Directions Biomed Eng 3(2):253\u2013256","journal-title":"Current Directions Biomed Eng"},{"key":"261_CR40","doi-asserted-by":"crossref","unstructured":"Schuld M, Petruccione F (2021) Machine learning with quantum computers. Springer","DOI":"10.1007\/978-3-030-83098-4"},{"key":"261_CR41","unstructured":"Shlens J (2014) A tutorial on principal component analysis. arXiv:1404.1100"},{"key":"261_CR42","unstructured":"Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. Adv Neural Inf Process Syst 25"},{"key":"261_CR43","doi-asserted-by":"crossref","unstructured":"Sornsaeng A, Dangniam N, Chotibut T (2024) Quantum next generation reservoir computing: an efficient quantum algorithm for forecasting quantum dynamics. Quant Mach Intell 6(2):57","DOI":"10.1007\/s42484-024-00188-7"},{"key":"261_CR44","doi-asserted-by":"crossref","unstructured":"Srinivasan PA, Guastoni L, Azizpour H et al (2019) Predictions of turbulent shear flows using deep neural networks. Phys Rev Fluids 4(5):054603","DOI":"10.1103\/PhysRevFluids.4.054603"},{"key":"261_CR45","doi-asserted-by":"crossref","unstructured":"Suzuki Y, Gao Q, Pradel KC et al (2022) Natural quantum reservoir computing for temporal information processing. Sci Reports 12(1):1353","DOI":"10.1038\/s41598-022-05061-w"},{"issue":"1","key":"261_CR46","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1038\/s41467-017-02717-4","volume":"9","author":"C Teeter","year":"2018","unstructured":"Teeter C, Iyer R, Menon V et al (2018) Generalized leaky integrate-and-fire models classify multiple neuron types. Nat Commun 9(1):709","journal-title":"Nat Commun"},{"key":"261_CR47","doi-asserted-by":"crossref","unstructured":"Tennie F, Laizet S, Lloyd S, Magri L (2025) Quantum computing for nonlinear differential equations and turbulence. Nat Rev Phys 1\u201311","DOI":"10.1038\/s42254-024-00799-w"},{"issue":"1","key":"261_CR48","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/s42484-025-00239-7","volume":"7","author":"W Xiong","year":"2025","unstructured":"Xiong W, Facelli G, Sahebi M, Agnel O, Chotibut T, Thanasilp S, Holmes Z (2025) On fundamental aspects of quantum extreme learning machines. Quant Mach Intell 7(1):20","journal-title":"Quant Mach Intell"},{"key":"261_CR49","doi-asserted-by":"crossref","unstructured":"Yu M, Liu Y, Yang P, et\u00a0al (2022) Quantum fisher information measurement and verification of the quantum Cram\u00e9r\u2013Rao bound in a solid-state qubit. npj Quantum Inf 8(1):56","DOI":"10.1038\/s41534-022-00547-x"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00261-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-025-00261-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-025-00261-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T14:40:48Z","timestamp":1750948848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-025-00261-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["261"],"URL":"https:\/\/doi.org\/10.1007\/s42484-025-00261-9","relation":{},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"2 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"31"}}