Short-Term Streamflow Forecasting Using Hybrid Deep Learning Model Based on Grey Wolf Algorithm for Hydrological Time Series

Short-term streamflow modeling using data-intelligence evolutionary machine learning models

Accurate streamflow prediction is essential for efficient water resources management. Machine learning (ML) models are the tools to meet this need. This paper presents a comparative research study focusing on hybridizing ML models with bioinspired optimization algorithms (BOA) for short-term multistep streamflow forecasting. Specifically, we focus on applying XGB, MARS, ELM, EN, and SVR models and various BOA, including PSO, GA, and DE, for selecting model parameters. The performances of the resulting hybrid models are compared using performance statistics, graphical analysis, and hypothesis testing. The results show that the hybridization of BOA with ML models demonstrates significant potential as a data-driven approach for short-term multistep streamflow forecasting. The PSO algorithm proved superior to the DE and GA algorithms in determining the optimal hyperparameters of ML models for each step of the considered time horizon. When applied with all BOA, the XGB model outperformed the others (SVR, MARS, ELM, and EN), best predicting the different steps ahead. XGB integrated with PSO emerged as the superior model, according to the considered performance measures and the results of the statistical tests. The proposed XGB hybrid model is a superior alternative to the current daily flow forecast, crucial for water resources planning and management.

Short-term forecasts of streamflow in the UK based on a novel hybrid artificial intelligence algorithm

In recent years, the growing impact of climate change on surface water bodies has made the analysis and forecasting of streamflow rates essential for proper planning and management of water resources. This study proposes a novel ensemble (or hybrid) model, based on the combination of a Deep Learning algorithm, the Nonlinear AutoRegressive network with eXogenous inputs, and two Machine Learning algorithms, Multilayer Perceptron and Random Forest, for the short-term streamflow forecasting, considering precipitation as the only exogenous input and a forecast horizon up to 7 days. A large regional study was performed, considering 18 watercourses throughout the United Kingdom, characterized by different catchment areas and flow regimes. In particular, the predictions obtained with the ensemble Machine Learning-Deep Learning model were compared with the ones achieved with simpler models based on an ensemble of both Machine Learning algorithms and on the only Deep Learning algorithm. The hybrid Machine Learning-Deep Learning model outperformed the simpler models, with values of R² above 0.9 for several watercourses, with the greatest discrepancies for small basins, where high and non-uniform rainfall throughout the year makes the streamflow rate forecasting a challenging task. Furthermore, the hybrid Machine Learning-Deep Learning model has been shown to be less affected by reductions in performance as the forecasting horizon increases compared to the simpler models, leading to reliable predictions even for 7-day forecasts.

Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition

Streamflow forecasting is of great significance for water resources planning and management. In recent years, numerous data-driven models have been widely used for streamflow forecasting. However, the traditional single data-driven model ignores the utilization of different streamflow regimes. This study proposed an integrated framework for daily streamflow forecasting based on the regime recognition of flow sequences. The framework integrates self-organizing maps (SOM) for identifying streamflow sub-sequences, the random forests (RF) algorithm to select input variables for different streamflow sub-sequences, and a deep belief network (DBN) for establishing complex relationships between the selected input variables and streamflows for different sub-sequences. Specifically, the integrated framework was applied to forecast daily streamflow at the Xiantao hydrological station in the Hanjiang River Basin, China. The results show that the developed integrated framework has higher streamflow prediction accuracy than the single data-driven model (i.e., the DBN model in this study), with Nash efficiency coefficient (NSE) of 0.91/0.81 and coefficient of determination (R2) of 0.93/0.89 for the integrated framework/DBN model during the validation period, respectively. Additionally, the prediction accuracy of the peak flood was also improved. The relative error of the peak flood derived from the integrated framework was reduced by 4.6%, compared with the single DBN model. Overall, the constructed integration framework, considering the complex characteristic of different flow regimes, could improve the accuracy for daily streamflow forecasting.

Response of Runoff to Meteorological Factors Based on Time-Varying Parameter Vector Autoregressive Model with Stochastic Volatility in Arid and Semi-Arid Area of Weihe River Basin

This study explores the response characteristics of runoff to the variability of meteorological factors. A modified vector autoregressive (VAR) model is proposed by combining time-varying parameters (TVP) and stochastic volatility (SV). Markov chain Monte Carlo (MCMC) is used to estimate parameters. The TVP-SV-VAR model of daily runoff response to the variability of meteorological factors is established and applied to the daily runoff series from the Linjiacun hydrological station, Shaanxi Province, China. It is found that the posterior estimates of the stochastic volatility of the four variables fluctuate significantly with time, and the variance fluctuations of runoff and precipitation have strong synchronicity. The simultaneous impact of precipitation and evaporation on the pulse of runoff is close to 0. Runoff has a positive impulse response to precipitation, which decreases as the lag time increases, and a negative impulse response to temperature and evaporation with fluctuation. The response speed is precipitation > evaporation > temperature. The TVP-SV-VAR model avoids the hypothesis of homoscedasticity of variance and allows the variance to be randomly variable, which significantly improves the analysis performance. It provides theoretical support for the study of runoff response and water resource management under the conditions of climate change.

Predicting Daily Streamflow in a Cold Climate Using a Novel Data Mining Technique: Radial M5 Model Tree

In this study, the viability of radial M5 model tree (RM5Tree) is investigated in prediction and estimation of daily streamflow in a cold climate. The RM5Tree model is compared with the M5 model tree (M5Tree), artificial neural networks (ANN), radial basis function neural networks (RBFNN), and multivariate adaptive regression spline (MARS) using data of two stations from Sweden. The accuracy of the methods is assessed based on root mean square errors (RMSE), mean absolute errors (MAE), mean absolute percentage errors (MAPE), and Nash Sutcliffe Efficiency (NSE) and the methods are graphically compared using time variation and scatter graphs. The benchmark results show that the RM5Tree offers better accuracy in predicting daily streamflow compared to other four models by respectively improving the accuracy of M5Tree with respect to RMSE, MAE, MAPE, and NSE by 26.5, 17.9, 5.9, and 10.9%. The RM5Tree also acts better than the M5Tree, ANN, RBFNN, and MARS in estimating streamflow of downstream station using only upstream data.