Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 19, 2026Scientific ReportsOpen Access

A synergistic framework integrating CPO-VMD with BiLSTM-TimesNet for accurate prediction of nonlinear and nonstationary runoff time series

View Full Paper
Ask AI
Bookmark
Share

Authors

DXDong-mei XuNorth China University of Water Resources and Electric PowerQWQian WangWuhan Polytechnic UniversityWWWenchuan WangNorth China University of Water Resources and Electric Power

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates improved runoff prediction accuracy, highlighting a synergistic modeling approach.

Key Points

  • This study aims to develop a hybrid prediction framework to accurately forecast nonlinear and nonstationary runoff time series.
  • Integrated multiple models: CPO, VMD, BiLSTM, TimesNet.
  • Utilized daily runoff data from the Quinebaug River (1997-2001) and Elbe River (2019-2022) for validation.
  • Implemented a parameter optimization-signal decomposition-deep modeling framework.
  • Nash-Sutcliffe efficiency improved by 16.15% compared to the LSTM model.
  • Kling-Gupta efficiency improved by 19.34%.
  • Root mean square error decreased by 60.38%, and mean absolute percentage error decreased by 72.56%.

Cite This Study

Xu et al. (2026) studied this question.

synapsesocial.com/papers/6a0bfd7a166b51b53d378d55https://doi.org/10.1038/s41598-026-52745-8
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Hybrid framework for robust runoff forecasting via decomposition and machine learning2026
  2. 2Runoff Forecast Model Integrating Time Series Decomposition and Deep Learning for the Short Term: A Case Study in the Weihe River Basin, China2025 · 2 citations
  3. 3Optimized decomposition and deep learning with bias correction for reliable runoff point-interval prediction2026
  4. 4A Hybrid LSTM and CNN deep learning framework for modeling runoff variability in western United States watersheds using multisource hydrological data2026
  5. 5Decomposition–Migration Cooperative Modeling Approach for Forecasting Runoff in Data-Scarce Watershed Areas2026