Abstract
Accurate forecasting of time series data is essential in many fields. However, real-world time series are often characterized by noise, non-stationarity and multiscale temporal dependencies, which collectively reduce forecasting performance. To address these challenges, MultiScaleWave, a deep learning framework based on time series decomposition, is proposed for univariate forecasting. The MultiScaleWave model first applies multi-level discrete wavelet transforms to decompose the series into multiscale temporal components. Each component is modeled by a granularity-adaptive module, and the outputs are then fused to generate an informative representation for final forecasting. The MultiScaleWave model has been validated on benchmark datasets and achieves superior performance compared to competitive baselines. The results demonstrate the effectiveness and generalizability of the proposed approach.
Similar content being viewed by others
Data availability
The financial datasets used during the current study are available from Yahoo Finance at https://finance.yahoo.com. Yahoo Finance provides publicly accessible financial data under its Terms of Service and does not assign DOIs to individual instruments.
The Weather dataset was obtained from the Max Planck Institute for Biogeochemistry (https://www.bgc-jena.mpg.de/wetter; accessed on 5 September 2025).
The Solar dataset used in this study is publicly available via DOI: https://doi.org/10.1038/s41597-022-01696-6 , published in Scientific Data
The source code supporting this study is publicly available at Zenodo: https://doi.org/10.5281/zenodo.18731595.
References
Kim, D., Park, S. & Choo, J. When model meets new normals: Test-time adaptation for unsupervised time-series anomaly detection. In Proceedings of the AAAI conference on artificial intelligence 38, 13113–13121 (2024).
Wang, X., Zhang, M. & Su, J. Robust temporal alignment for multivariate time series forecasting. Expert Syst. Appl. 289, 128299 (2025).
Bahi, M. C. et al. Fractional view analysis of sexual transmitted human papilloma virus infection for public health. Sci. Rep. 14, 3048 (2024).
Lee, H., Kim, J. H. & Jung, H. S. Deep-learning-based stock market prediction incorporating esg sentiment and technical indicators. Sci. Rep. 14, 10262 (2024).
Echternacht, H. et al. Convolutional neural networks with transfer learning for natural river flow prediction in ungauged basins. Sci. Rep. 15, 23873 (2025).
Yadav, H. & Thakkar, A. Noa-lstm: An efficient lstm cell architecture for time series forecasting. Expert Syst. Appl. 238, 122333 (2024).
Zhang, J. & Liu, Z. Interval prediction of crude oil spot price volatility: An improved hybrid model integrating decomposition strategy, iesn and arima. Expert Syst. Appl. 252, 124195 (2024).
Li, Y., Xu, J. & Anastasiu, D. Learning from polar representation: An extreme-adaptive model for long-term time series forecasting. In Proceedings of the AAAI conference on artificial intelligence 38, 171–179 (2024).
Hu, Y., Liu, P., Zhu, P., Cheng, D. & Dai, T. Adaptive multi-scale decomposition framework for time series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence 39, 17359–17367 (2025).
Zhong, W. et al. Accurate and efficient daily carbon emission forecasting based on improved arima. Appl. Energy 376, 124232 (2024).
Kour, M. Modelling and forecasting of carbon-dioxide emissions in south africa by using arima model. Int. J. Environ. Sci. Technol. 20, 11267–11274 (2023).
Hou, S. et al. Multivariate multi-scale cross-fuzzy entropy and ssa-svm-based fault diagnosis method of gearbox. Meas. Sci. Technol. 35, 056102 (2024).
Fu, Y. et al. Scarf: A new algorithm for continuous prediction of biomass dynamics using machine learning and landsat time series. Remote Sens. Environ. 314, 114348 (2024).
Karkaria, V. et al. Towards a digital twin framework in additive manufacturing: Machine learning and bayesian optimization for time series process optimization. J. Manuf. Syst. 75, 322–332 (2024).
Ghosh, P., Neufeld, A. & Sahoo, J. K. Forecasting directional movements of stock prices for intraday trading using lstm and random forests. Financ. Res. Lett. 46, 102280 (2022).
Kurani, A., Doshi, P., Vakharia, A. & Shah, M. A comprehensive comparative study of artificial neural network (ann) and support vector machines (svm) on stock forecasting. Ann. Data Sci. 10, 183–208 (2023).
Dao, F., Zeng, Y. & Qian, J. Fault diagnosis of hydro-turbine via the incorporation of bayesian algorithm optimized cnn-lstm neural network. Energy 290, 130326 (2024).
Cai, X. et al. A hybrid wind speed forecasting model with rolling mapping decomposition and temporal convolutional networks. Energy 324, 135673 (2025).
Liu, C. et al. Singular value decomposition-based lightweight lstm for time series forecasting. Future Gener. Comput. Syst. 107910 (2025).
Yu, Y. et al. Prformer: Pyramidal recurrent transformer for multivariate time series forecasting. Neural Netw. 107769 (2025).
Rick, R. & Berton, L. Energy forecasting model based on cnn-lstm-ae for many time series with unequal lengths. Eng. Appl. Artif. Intell. 113, 104998 (2022).
Wang, H. et al. MICN: Multi-scale local and global context modeling for long-term series forecasting. In The Eleventh International Conference on Learning Representations (2023).
Luo, D. & Wang, X. Moderntcn: A modern pure convolution structure for general time series analysis. In The twelfth international conference on learning representations 1–43 (2024).
Xuan, Y., Yu, Y. & Wu, K. Prediction of short-term stock prices based on emd-lstm-csi neural network method. In 2020 5th IEEE International Conference on Big Data Analytics (ICBDA) 135–139 (2020).
Wu, H., Xu, J., Wang, J. & Long, M. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Adv. Neural Inf. Process. Syst. 34, 22419–22430 (2021).
Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv:2211.14730 (2022).
Zeng, A., Chen, M., Zhang, L. & Xu, Q. Are transformers effective for time series forecasting?. In Proceedings of the AAAI conference on artificial intelligence 37, 11121–11128 (2023).
Cai, X. & Li, D. M-edem: A mnn-based empirical decomposition ensemble method for improved time series forecasting. Knowl.-Based Syst. 283, 111157 (2024).
Guo, C., Kang, X., Xiong, J. & Wu, J. A new time series forecasting model based on complete ensemble empirical mode decomposition with adaptive noise and temporal convolutional network. Neural Process. Lett. 55, 4397–4417 (2023).
Liu, Z., Su, Z., Shang, L., Sun, H. & Zhao, B. An approach to stock price prediction based on improved eemd and attention-enhanced bilstm. Expert Syst. Appl. 284, 127802 (2025).
Wang, S. et al. Timemixer: Decomposable multiscale mixing for time series forecasting. arXiv preprint arXiv:2405.14616 (2024).
Huang, S., Zhao, Z., Li, C. & Bai, L. Timekan: Kan-based frequency decomposition learning architecture for long-term time series forecasting (2025).
Almaghrabi, S., Rana, M., Hamilton, M. & Rahaman, M. S. Solar power time series forecasting utilising wavelet coefficients. Neurocomputing 508, 182–207 (2022).
Chen, Y. & Xu, J. Solar and wind power data from the chinese state grid renewable energy generation forecasting competition. Sci. Data 9, 577 (2022).
for Biogeochemistry, M. P. I. Weather station. https://www.bgc-jena.mpg.de/wetter
Funding
This research received no external funding. All related expenses were borne by the authors.
Author information
Authors and Affiliations
Contributions
C.Z. participated in the design and conduct of the whole project, contributing to data processing, model construction, result analysis, and manuscript drafting. H.Z. conceived and supervised the project, provided critical methodological guidance, and offered substantial assistance in manuscript preparation and revision. All authors reviewed and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Zheng, C., Zhao, H. MultiScaleWave: a wavelet-based multiscale framework for univariate time series forecasting. Sci Rep (2026). https://doi.org/10.1038/s41598-026-42317-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-42317-1
