EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wavelet-Fourier Network Combined with Advanced Preprocessing Techniques for Univariate Daily Rainfall Prediction

Md. Jobayer Parvez Ratul, Usmi Akter, Tajrian Mollick, Eshrat Jahan Mumu, Nondita Deb Nath, Syeda Wasifa Adila, Wafa Saleh Alkhuraiji, Padam Jee Omar, Mohamed Zhran

Water · 23.05.2026 · 18 (11) · 1264

DOI: 10.3390/w18111264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 23.05.2026. Verfasst von Md. Jobayer Parvez Ratul und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rainfall prediction is essential for the enhanced understanding of several issues related to water resources and agriculture, such as flood and drought alerts and flood management. Neural network models are frequently used due to their capability of effectively handling large datasets and addressing the non-stationarity of rainfall data series, resulting in better accuracy and affordable solutions. However, further study is necessary to comprehend the dynamic nature and extreme events of rainfall. Therefore, we implemented a novel wavelet Fourier-enhanced network (W-FENet) that included a Fourier enhancement module (FEMEX) and an improved U-Net mechanism to strengthen the predictive accuracy of daily rainfall. The adopted U-Net structure facilitated efficient multiscale feature extraction and preservation of temporal rainfall information through encoder–decoder connections and residual learning. The results of the developed models for one-day-ahead rainfall prediction were evaluated against two traditional neural network models, i.e., artificial neural networks and long short-term memory networks. Mongla, being a coastal station and having a highly non-linear rainfall pattern, operated by the Bangladesh Meteorological Department, was selected as the study area. Four preprocessing techniques were incorporated to enhance the robustness of the models: empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), variational mode decomposition (VMD), and successive variational mode decomposition (SVMD). The SVMD-enhanced W-FENet model (abbreviated as W5) demonstrated significant improvements over existing literature with RMSE = 2.226 mm, MAE = 1.131 mm, PCC = 0.988, NSE = 0.974, and WI = 0.993 at the testing phase.

Zitieren

APA

Ratul, M. J. P., Akter, U., Mollick, T., Mumu, E. J., Nath, N. D., Adila, S. W., Alkhuraiji, W. S., Omar, P. J., & Zhran, M. (2026). Wavelet-Fourier Network Combined with Advanced Preprocessing Techniques for Univariate Daily Rainfall Prediction. Water, 18(11), 1264. https://doi.org/10.3390/w18111264

Vancouver

Ratul MJP, Akter U, Mollick T, Mumu EJ, Nath ND, Adila SW, et al. Wavelet-Fourier Network Combined with Advanced Preprocessing Techniques for Univariate Daily Rainfall Prediction. Water. 2026;18(11):1264. doi:10.3390/w18111264

BibTeX
@article{Ratul2026,
  author = {Ratul, Md. Jobayer Parvez and Akter, Usmi and Mollick, Tajrian and Mumu, Eshrat Jahan and Nath, Nondita Deb and Adila, Syeda Wasifa and Alkhuraiji, Wafa Saleh and Omar, Padam Jee and Zhran, Mohamed},
  title = {Wavelet-Fourier Network Combined with Advanced Preprocessing Techniques for Univariate Daily Rainfall Prediction},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1264},
  doi = {10.3390/w18111264}
}
Kostenlos starten →