IDEAS home Printed from https://ideas.repec.org/a/eee/chsofr/v153y2021ip2s0960077921009243.html
   My bibliography  Save this article

Forecasting of noisy chaotic systems with deep neural networks

Author

Listed:
  • Sangiorgio, Matteo
  • Dercole, Fabio
  • Guariso, Giorgio

Abstract

Recurrent neural networks have recently proved the state-of-the-art approach in forecasting complex oscillatory time series on a multi-step horizon. Researchers in the field investigated different machine learning techniques and training approaches on dynamical systems with different degrees of complexity. Still, these analyses are usually limited to noise-free chaotic time series. This paper extends the analysis from a deterministic to a noisy environment, by considering both observation and structural noise. Observation noise is evaluated by adding different levels of artificially-generated random values on deterministic processes obtained from the simulation of four archetypal chaotic systems. A case of structural noise is implemented through a time-varying version of the logistic map, which exhibits a slow structural change of the system’s dynamic that makes the system non-stationary. Finally, a time series of ozone concentration in Northern Italy is considered to test the theoretical findings on a real-world case study in which both forms of noise play a significant role. Recurrent neural networks formed by LSTM cells are compared with two benchmark feed-forward architectures. LSTM trained without the standard teacher forcing approach, i.e., with training that replicates the setting used in inference mode, proved to have the best performance in compensating the stochasticity generated by the observation noise and reproducing the structural non-stationarity of the process.

Suggested Citation

  • Sangiorgio, Matteo & Dercole, Fabio & Guariso, Giorgio, 2021. "Forecasting of noisy chaotic systems with deep neural networks," Chaos, Solitons & Fractals, Elsevier, vol. 153(P2).
  • Handle: RePEc:eee:chsofr:v:153:y:2021:i:p2:s0960077921009243
    DOI: 10.1016/j.chaos.2021.111570
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960077921009243
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.chaos.2021.111570?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Shi, Xiancheng & Feng, Yucheng & Zeng, Jinsong & Chen, Kefu, 2017. "Chaos time-series prediction based on an improved recursive Levenberg–Marquardt algorithm," Chaos, Solitons & Fractals, Elsevier, vol. 100(C), pages 57-61.
    2. Sangiorgio, Matteo & Dercole, Fabio, 2020. "Robustness of LSTM neural networks for multi-step forecasting of chaotic time series," Chaos, Solitons & Fractals, Elsevier, vol. 139(C).
    3. Cechin, Adelmo L. & Pechmann, Denise R. & de Oliveira, Luiz P.L., 2008. "Optimizing Markovian modeling of chaotic systems with recurrent neural networks," Chaos, Solitons & Fractals, Elsevier, vol. 37(5), pages 1317-1327.
    4. Pei Chen & Rui Liu & Kazuyuki Aihara & Luonan Chen, 2020. "Autoreservoir computing for multistep ahead prediction based on the spatiotemporal information transformation," Nature Communications, Nature, vol. 11(1), pages 1-15, December.
    5. Giorgio Guariso & Giuseppe Nunnari & Matteo Sangiorgio, 2020. "Multi-Step Solar Irradiance Forecasting and Domain Adaptation of Deep Neural Networks," Energies, MDPI, vol. 13(15), pages 1-18, August.
    6. Qinghai Li & Rui-Chang Lin, 2016. "A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network," Mathematical Problems in Engineering, Hindawi, vol. 2016, pages 1-9, December.
    7. Cheng, Wei & Wang, Yan & Peng, Zheng & Ren, Xiaodong & Shuai, Yubei & Zang, Shengyin & Liu, Hao & Cheng, Hao & Wu, Jiagui, 2021. "High-efficiency chaotic time series prediction based on time convolution neural network," Chaos, Solitons & Fractals, Elsevier, vol. 152(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Lampartová, Alžběta & Lampart, Marek, 2024. "Exploring diverse trajectory patterns in nonlinear dynamic systems," Chaos, Solitons & Fractals, Elsevier, vol. 182(C).
    2. Niccolò Borghi & Giorgio Guariso & Matteo Sangiorgio, 2024. "Forecasting Convective Storms Trajectory and Intensity by Neural Networks," Forecasting, MDPI, vol. 6(2), pages 1-17, May.
    3. Sun, Ying & Zhang, Luying & Yao, Minghui, 2023. "Chaotic time series prediction of nonlinear systems based on various neural network models," Chaos, Solitons & Fractals, Elsevier, vol. 175(P1).
    4. Miao, Hua & Zhu, Wei & Dan, Yuanhong & Yu, Nanxiang, 2024. "Chaotic time series prediction based on multi-scale attention in a multi-agent environment," Chaos, Solitons & Fractals, Elsevier, vol. 183(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Sangiorgio, Matteo & Dercole, Fabio, 2020. "Robustness of LSTM neural networks for multi-step forecasting of chaotic time series," Chaos, Solitons & Fractals, Elsevier, vol. 139(C).
    2. Miao, Hua & Zhu, Wei & Dan, Yuanhong & Yu, Nanxiang, 2024. "Chaotic time series prediction based on multi-scale attention in a multi-agent environment," Chaos, Solitons & Fractals, Elsevier, vol. 183(C).
    3. Cheng, Wei & Wang, Yan & Peng, Zheng & Ren, Xiaodong & Shuai, Yubei & Zang, Shengyin & Liu, Hao & Cheng, Hao & Wu, Jiagui, 2021. "High-efficiency chaotic time series prediction based on time convolution neural network," Chaos, Solitons & Fractals, Elsevier, vol. 152(C).
    4. Chafi, Mohammadreza Shafiee & Narm, Hossein Gholizade & Kalat, Ali Akbarzadeh, 2023. "Chaotic and stochastic evaluation in Fluxgate magnetic sensors," Chaos, Solitons & Fractals, Elsevier, vol. 176(C).
    5. Zhou, Ling & You, Zhenzhen & Tang, Yun, 2021. "A new chaotic system with nested coexisting multiple attractors and riddled basins," Chaos, Solitons & Fractals, Elsevier, vol. 148(C).
    6. Lampartová, Alžběta & Lampart, Marek, 2024. "Exploring diverse trajectory patterns in nonlinear dynamic systems," Chaos, Solitons & Fractals, Elsevier, vol. 182(C).
    7. Hajimohammadi, Zeinab & Baharifard, Fatemeh & Ghodsi, Ali & Parand, Kourosh, 2021. "Fractional Chebyshev deep neural network (FCDNN) for solving differential models," Chaos, Solitons & Fractals, Elsevier, vol. 153(P2).
    8. Yin, Linfei & Zhou, Hang, 2024. "Modal decomposition integrated model for ultra-supercritical coal-fired power plant reheater tube temperature multi-step prediction," Energy, Elsevier, vol. 292(C).
    9. Yukthakiran Matla & Rohith Rao Yannamaneni & George Pappas, 2024. "Globalizing Food Items Based on Ingredient Consumption," Sustainability, MDPI, vol. 16(17), pages 1-22, August.
    10. Wu, Tao & Gao, Xiangyun & An, Feng & Xu, Xin & Kurths, Jürgen, 2024. "Forecasting the dynamics of correlations in complex systems," Chaos, Solitons & Fractals, Elsevier, vol. 178(C).
    11. Mirzaee, Hossein, 2009. "Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg–Marquardt learning algorithm," Chaos, Solitons & Fractals, Elsevier, vol. 41(4), pages 1975-1979.
    12. Giorgio Guariso & Giuseppe Nunnari & Matteo Sangiorgio, 2020. "Multi-Step Solar Irradiance Forecasting and Domain Adaptation of Deep Neural Networks," Energies, MDPI, vol. 13(15), pages 1-18, August.
    13. Valle, João & Bruno, Odemir M., 2024. "Dynamics and patterns of the least significant digits of the infinite-arithmetic precision logistic map orbits," Chaos, Solitons & Fractals, Elsevier, vol. 180(C).
    14. Tao Wu & Xiangyun Gao & Feng An & Xiaotian Sun & Haizhong An & Zhen Su & Shraddha Gupta & Jianxi Gao & Jürgen Kurths, 2024. "Predicting multiple observations in complex systems through low-dimensional embeddings," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    15. Chen, Xiaolu & Weng, Tongfeng & Li, Chunzi & Yang, Huijie, 2022. "Equivalence of machine learning models in modeling chaos," Chaos, Solitons & Fractals, Elsevier, vol. 165(P2).
    16. Wu, Tao & Gao, Xiangyun & An, Feng & Kurths, Jürgen, 2023. "The complex dynamics of correlations within chaotic systems," Chaos, Solitons & Fractals, Elsevier, vol. 167(C).
    17. Despotovic, Milan & Voyant, Cyril & Garcia-Gutierrez, Luis & Almorox, Javier & Notton, Gilles, 2024. "Solar irradiance time series forecasting using auto-regressive and extreme learning methods: Influence of transfer learning and clustering," Applied Energy, Elsevier, vol. 365(C).
    18. Shen, Yuewen & Wen, Lihong & Shen, Chaowen, 2024. "Based on hypernetworks and multifractals: Deep distribution feature fusion for multidimensional nonstationary time series prediction," Chaos, Solitons & Fractals, Elsevier, vol. 182(C).
    19. Igor Cavalcante Torres & Daniel M. Farias & Andre L. L. Aquino & Chigueru Tiba, 2021. "Voltage Regulation For Residential Prosumers Using a Set of Scalable Power Storage," Energies, MDPI, vol. 14(11), pages 1-28, June.
    20. Syed Muhammad Mohsin & Tahir Maqsood & Sajjad Ahmed Madani, 2022. "Solar and Wind Energy Forecasting for Green and Intelligent Migration of Traditional Energy Sources," Sustainability, MDPI, vol. 14(23), pages 1-20, December.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:chsofr:v:153:y:2021:i:p2:s0960077921009243. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Thayer, Thomas R. (email available below). General contact details of provider: https://www.journals.elsevier.com/chaos-solitons-and-fractals .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.