Wind speed forecasting in the Isthmus region using partial wavelet reconstruction and machine learning
DOI:
https://doi.org/10.29059/rmic.v1i2.12Keywords:
Wind forecasting, machine learning, wavelet transformation, wind energy, time seriesAbstract
Accurate wind speed prediction is important for optimizing wind energy generation, as it improves power supply planning and the maintenance of wind turbines. This paper proposes a hybrid model that integrates the Discrete Wavelet Transform (DWT) with LSTM neural networks for short-term forecasting. A time series of wind speed data from Nizanda, Oaxaca, was used, applying the Daubechies 4 (db4) wavelet to decompose the signal into approximation and detail components. Multiple partial reconstruction configurations were evaluated to filter noise and highlight relevant patterns. Experimental results demonstrate that selective reconstruction using the approximation and the first two levels of detail outperforms the base model, which consists of an LSTM with raw wind speed data without the wavelet transformation, but also traditional reference models (persistence, ARIMA, SARIMA). This configuration achieved an R² of 0.934 and an RMSE of 0.979 on the test set.
References
Amirteimoury, F., Keynia, F., Amirteimoury, E., Memarzadeh, G., & Shabanian, H. (2025). A novel wind speed prediction model based on neural networks, wavelet transformation, mutual information, and coot optimization algorithm. Sci Rep, 15(1), 10860. https://doi.org/10.1038/s41598-025-94082-2
Azamar Alonso, A., & García Beltrán, Y. M. (2021). Diagnóstico y riesgos de la energía eólica en México. Revista de Geografía Agrícola(67), 27-45. https://doi.org/10.5154/r.rga.2021.67.02
Bergmeir, C., & Benítez, J. M. (2012). On the use of cross-validation for time series predictor evaluation. Information Sciences, 191, 192-213. https://doi.org/10.1016/j.ins.2011.12.028
Buratto, W. G., Muniz, R. N., Nied, A., Barros, C. F. d. O., Cardoso, R., & Gonzalez, G. V. (2024). Wavelet CNN‐LSTM time series forecasting of electricity power generation considering biomass thermal systems. IET Generation, Transmission & Distribution, 18(21), 3437-3451. https://doi.org/10.1049/gtd2.13292
Cano Torres, L. R., & Rodríguez Cruz, L. A. (2020). El impacto social de las energías limpias en comunidades vulnerables. La energía eólica en la comunidad zapoteca de Juchitán de Zaragoza, Oaxaca. Ambiente y Desarrollo, 24(46), 1-18. https://doi.org/10.11144/Javeriana.ayd24-46.isel
Castro, L. R., & Castro, S. M. (1995). Wavelets y sus aplicaciones I Congreso Argentino de Ciencias de la Computación.,
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci, 7, e623. https://doi.org/10.7717/peerj-cs.623
Daubechies, I. (1992). Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611970104
Domínguez-Navarro, J. A., Lopez-Garcia, T. B., & Valdivia-Bautista, S. M. (2021). Applying Wavelet Filters in Wind Forecasting Methods. Energies, 14(11). https://doi.org/10.3390/en14113181
Eólica, A. M. d. E. (2015). El potencial eólico mexicano: Oportunidades y retos en el nuevo sector eléctrico.
Guo, X., Zhu, C., Hao, J., Kong, L., & Zhang, S. (2023). A Point-Interval Forecasting Method for Wind Speed Using Improved Wild Horse Optimization Algorithm and Ensemble Learning. Sustainability, 16(1). https://doi.org/10.3390/su16010094
K U, J., & Kovoor, B. C. (2021). A Wavelet-based hybrid multi-step Wind Speed Forecasting model using LSTM and SVR. Wind Engineering, 45(5), 1123-1144. https://doi.org/10.1177/0309524x20964762
Kio, A. E., Xu, J., Gautam, N., & Ding, Y. (2024). Wavelet decomposition and neural networks: a potent combination for short term wind speed and power forecasting. Frontiers in Energy Research, 12. https://doi.org/10.3389/fenrg.2024.1277464
Lee, G. R., Gommers, R., Wasilewski, F., Wohlfahrt, K., & O’Leary, A. (2019). PyWavelets: A Python package for wavelet analysis. Journal of Open Source Software, 4(36), 1237. https://doi.org/10.21105/joss.01237
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2018). Hyperband: A novel bandit-based approach to hyperparameter optimization. Journal of Machine Learning Research, 18(185), 1--52.
Li, W., & Law, K. L. E. (2024). Deep Learning Models for Time Series Forecasting: A Review. IEEE Access, 12, 92306-92327. https://doi.org/10.1109/access.2024.3422528
Muñoz, R. B., F.; Lebrija-Trejos, E.; Gallardo-Cruz, J. A.; Enríquez, M.; Romero-Romero, M. A.; López-Mendoza, R. D.; Meave, J. A. (2024). Daily weather data from Nizanda, Mexico (2006–2024). https://doi.org/10.5281/zenodo.7970409
Nascimento, E. G. S., de Melo, T. A. C., & Moreira, D. M. (2023). A transformer-based deep neural network with wavelet transform for forecasting wind speed and wind energy. Energy, 278. https://doi.org/10.1016/j.energy.2023.127678
PyTorch. (2026). torch.nn.LSTM — PyTorch documentation. https://pytorch.org/docs/stable/generated/torch.nn.LSTM.html
Shah, A. A., Aftab, A. A., Han, X., Baloch, M. H., Honnurvali, M. S., & Chauhdary, S. T. (2023). Prediction Error-Based Power Forecasting of Wind Energy System Using Hybrid WT–ROPSO–NARMAX Model. Energies, 16(7). https://doi.org/10.3390/en16073295
Soman, S. S., Zareipour, H., Malik, O., & Mandal, P. (2010). A Review of Wind Power and Wind Speed Forecasting Methods With Different Time Horizons.pdf. North American power symposium, 8. https://doi.org/10.1109/NAPS.2010.5619586
Tamilselvi, C., Paul, R. K., Yeasin, M., & Paul, A. K. (2024). Novel wavelet-LSTM approach for time series prediction. Neural Computing and Applications, 37(17), 10521-10530. https://doi.org/10.1007/s00521-024-10561-z
Vishnutheerth, E. P., Vijay, V., Satheesh, R., & Kolhe, M. L. (2024). A Comprehensive Approach to Wind Power Forecasting Using Advanced Hybrid Neural Networks. IEEE Access, 12, 124790-124800. https://doi.org/10.1109/access.2024.3450096
Wang, Y., Zou, R., Liu, F., Zhang, L., & Liu, Q. (2021). A review of wind speed and wind power forecasting with deep neural networks. Applied Energy, 304, 117766. https://doi.org/https://doi.org/10.1016/j.apenergy.2021.117766
Yu, B., Lu, Z., & Qian, W. (2025). Wavelet-denoised graph-Informer for accurate and stable wind speed prediction. Applied Soft Computing, 176, 113182. https://doi.org/https://doi.org/10.1016/j.asoc.2025.113182
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Revista Mexicana de Ingeniería y Ciencias
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
