Use of Wavelet and Bootstrap Methods in Streamflow Prediction

Abstract

Streamflow prediction is vital to control the effects of floods and mitigation. Physical prediction model often provides satisfactory results, but these models require massive computational work and hydrogeomorphological variables to develop a prediction system. At the same time, data-driven prediction models are quick to apply, easy to handle, and reliable. This study investigates a new hybrid model, the wavelet bootstrap quadratic response surface, for accurate streamflow prediction. Wavelet analysis is a well-known time-frequency joint analysis technique applied in various fields like biological signals, vibration signals, and hydrological signals. The wavelet analysis is used to denoise the time series data. Bootstrap is a nonparametric method for removing uncertainty that uses an intensive resampling methodology with replacement. The authors analyzed the results of the studied models with different statistical metrics, and it has been observed that the wavelet bootstrap quadratic response surface model provides the most efficient results.

Applicability of Examining the Wavelet Packet Decomposition on Statistical Models for River Stage Forecasting

“…RMSE assesses the variability in error irrespective of sample size, indicating the difference between observed and predicted streamflow values. The RMSE value ranges from zero to plus infinity (Bashir et al, 2023). A decrease in RMSE signifies improved model performance, with a value of 0 indicating precise accuracy where predicted values align perfectly with observed values.…”

“…Selection of suitable decomposition level is an important step to get best results from wavelet transform. The decomposition level of WPT can be find out using mathematical formula given as under (Bashir et al, 2023;Sehgal et al, 2014) ( )…”

“…Response surface (RS) models, comprising MLR, QRS, and nonlinear response surface (NRS), were utilized for forecasting daily runoff variables such as discharge and water level (Yu et al, 2014). Shehzad et al (2023) explore a hybrid approach called the bootstrap quadratic response surface (BQRS), designed to enhance the accuracy of streamflow prediction.…”