Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A deep learning runoff prediction model based on wavelet decomposition and dynamic feature fusion.

Dong-Mei Xu1, Qi-Qi Zeng1, Wen-Chuan Wang2

  • 1College of Water Resources, North China University of Water Resources and Electric Power, Zhengzhou, 450046, China.

Scientific Reports
|October 24, 2025
PubMed
Summary

Related Concept Videos

Design Example: Creating a Hydraulic Model of a Dam Spillway01:21

Design Example: Creating a Hydraulic Model of a Dam Spillway

668
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
668
Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

426
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
426

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multi-feature fusion monthly runoff prediction under different climate conditions using APO-optimized CNN-BiGRU-Self-Attention.

Scientific reports·2026
Same author

How glycemic variability trajectories impact clinical outcomes in critically ill patients with severe pneumonia: a prospective cohort study.

BMC anesthesiology·2026
Same author

Postoperative Blood Glucose Management After Total Pancreatectomy Combined With Total Gastrectomy And Autologous Small Intestine Transplantation.

Journal of visualized experiments : JoVE·2026
Same author

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

Scientific reports·2026
Same author

Anti-PLA2R antibodies promote endothelial pyroptosis and a procoagulant phenotype through FcγRI signaling.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2026
Same author

Hybrid framework for robust runoff forecasting via decomposition and machine learning.

Scientific reports·2026

This study introduces BWDformer, a novel deep learning model for enhanced streamflow forecasting. BWDformer significantly improves prediction accuracy by integrating wavelet decomposition and dynamic feature fusion.

Area of Science:

  • Hydrology
  • Deep Learning
  • Time Series Analysis

Background:

  • Streamflow forecasting faces challenges due to stochasticity, time-varying dynamics, and nonlinearities.
  • Conventional deep learning models struggle with multi-scale feature integration and long-term dependency capture.

Purpose of the Study:

  • To propose BWDformer, a novel deep learning architecture for precise streamflow forecasting.
  • To address limitations in existing models for handling complex runoff data characteristics.

Main Methods:

  • Developed BWDformer, integrating wavelet decomposition, dynamic feature fusion (DFF), and Bayesian optimization.
  • Wavelet decomposition extracts multi-scale features; DFF dynamically adjusts feature weights using attention.
  • Bayesian optimization efficiently tunes hyperparameters for improved training efficiency.
Keywords:
Bayesian optimizationDynamic feature fusionMulti-scale featuresRunoff predictionWavelet decomposition

Related Experiment Videos

Main Results:

  • BWDformer significantly outperformed CNN, LSTM, Transformer, and Informer across four hydrological stations.
  • Demonstrated substantial improvements in Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R, Nash-Sutcliffe Efficiency (NSE), and Kling-Gupta Efficiency (KGE).
  • Specific examples show significant reductions in MAE and RMSE, and increases in R, NSE, and KGE compared to benchmark models.

Conclusions:

  • BWDformer exhibits superior performance in streamflow forecasting accuracy and robustness.
  • The model effectively captures complex runoff dynamics and long-term dependencies.
  • Validated effectiveness across diverse hydrological conditions, confirming practical applicability.