Abstract:In the current paper, the efficiency of three new standalone data-mining algorithms [M5 Prime (M5P), Random Forest (RF), M5Rule (M5R)] and six novel hybrid algorithms of bagging (BA-M5P, BA-RF and BA-M5R) and Attribute Selected Classifier (ASC-M5P, ASC-RF and ASC-M5R) for streamflow prediction were assessed and compared with an autoregressive integrated moving average (ARIMA) model as a benchmark. The models used precipitation (P) and streamflow (Q) data from the period 1979-2012 for training and validation (7… Show more
“…Specifically, daytime precipitation data from 2000 to 2020 were used to simulate daytime river flows from 2000 to 2020 and predict the streamflow before one day and six days. In general, the model training process using the machine learning approach encounters several difficulties because the raw streamflow data has nonlinear characteristics, which strongly influence the model if we directly use these data in the model (Khosravi et al, 2021). It is, therefore, necessary to normalize these data.…”
Section: Study Area and Observational Datamentioning
confidence: 99%
“…They can generate predictions through the evaluation and simulation of the hydrological cycle. The use of physical parameters allows us to comprehend the different hydrological processes with relatively high spatial and temporal resolution (Lane et al, 2019;Khosravi et al, 2021). Although considerable effort has been made to improve the precision of physics-based models, they have been restricted by uncertainties in datasets, parameter heterogeneity, and non-linearities in generating streamflow.…”
Precise streamflow prediction is crucial in the optimization of the distribution of water resources. This study develops the machine learning models by integrating recurrent gate unit (GRU) with bacterial foraging optimization (BFO), gray wolf optimizer (GWO), and human group optimization (HGO) to forecast the streamflow in the Tra Khuc River, Vietnam. For this purpose, the time series of daily rainfall and river flow at Son Giang station from 2000 to 2020 were employed to forecast the streamflow. The statistical indices, namely the root mean square error, the mean absolute error, and the coefficient of determination (R²), was utilized to evaluate the performance of the proposed models. The results showed that the three optimization algorithms (HGO, GWO, and BFO) effectively enhanced the performance of the GRU model.
Moreover, among the four models (GRU, GRU-HGO, GRU-GWO, and GRU-BFO), the GRU-GWO model outperformed the other models with R² = 0.883. GRU-HGO achieved R² = 0.879, and GRU-BFO achieved R²=0.878. The results of this study showed that GRU combined with optimization algorithms is a reliable modeling approach in short-term flow forecasting.
“…Specifically, daytime precipitation data from 2000 to 2020 were used to simulate daytime river flows from 2000 to 2020 and predict the streamflow before one day and six days. In general, the model training process using the machine learning approach encounters several difficulties because the raw streamflow data has nonlinear characteristics, which strongly influence the model if we directly use these data in the model (Khosravi et al, 2021). It is, therefore, necessary to normalize these data.…”
Section: Study Area and Observational Datamentioning
confidence: 99%
“…They can generate predictions through the evaluation and simulation of the hydrological cycle. The use of physical parameters allows us to comprehend the different hydrological processes with relatively high spatial and temporal resolution (Lane et al, 2019;Khosravi et al, 2021). Although considerable effort has been made to improve the precision of physics-based models, they have been restricted by uncertainties in datasets, parameter heterogeneity, and non-linearities in generating streamflow.…”
Precise streamflow prediction is crucial in the optimization of the distribution of water resources. This study develops the machine learning models by integrating recurrent gate unit (GRU) with bacterial foraging optimization (BFO), gray wolf optimizer (GWO), and human group optimization (HGO) to forecast the streamflow in the Tra Khuc River, Vietnam. For this purpose, the time series of daily rainfall and river flow at Son Giang station from 2000 to 2020 were employed to forecast the streamflow. The statistical indices, namely the root mean square error, the mean absolute error, and the coefficient of determination (R²), was utilized to evaluate the performance of the proposed models. The results showed that the three optimization algorithms (HGO, GWO, and BFO) effectively enhanced the performance of the GRU model.
Moreover, among the four models (GRU, GRU-HGO, GRU-GWO, and GRU-BFO), the GRU-GWO model outperformed the other models with R² = 0.883. GRU-HGO achieved R² = 0.879, and GRU-BFO achieved R²=0.878. The results of this study showed that GRU combined with optimization algorithms is a reliable modeling approach in short-term flow forecasting.
“…The literature broadly consists of two sets of streamflow prediction models: physics-based and data-based. Physics-based models are developed only using real-life streamflow data (Khosravi et al, 2021;Rahimzad et al, 2021). Although this method has been proven effective in predicting the streamflow of rivers around the world, the development of such models is very complicated and timeconsuming.…”
Section: Introductionmentioning
confidence: 99%
“…Although this method has been proven effective in predicting the streamflow of rivers around the world, the development of such models is very complicated and timeconsuming. In addition, physical-based models require detailed data like topography, precipitation, and land use/land cover to calibrate model parameters, and these models can also be negatively affected when watershed data do not respond well to water balance constraints (Khosravi et al, 2021). The uncertainty of precipitation and hydrology data also greatly influences streamflow prediction, and physics-based models suffer in data-limited regions (Krzysztofowicz, 2002).…”
Accurate prediction of streamflow plays an important role in water resource management and sustainability. Recent years have seen increased interest in data-based models, compared to the more established physics-based models, due to the accuracy of their predictions. Better results mean greater support for those who are tasked with formulating strategies and writing policy around water resource management. The objective of this study is the development of a state-of-the-art streamflow prediction method based on extreme learning machine (ELM), optimized by both hunger games search (HGS) and social spider optimization (SSO) to make accurate predictions for the Tra Khuc River in Vietnam. Rainfall and flow from 2000 to 2020 at Son Giang station on the Tra Khuc River were used to build the streamflow prediction model. The statistical indices root-mean-square error, mean absolute error, and the coefficient of determination (R²) were applied to assess the predictive ability of the proposed models. The results showed that both optimization algorithms successfully improved the ELM model to predict the streamflow for one day and six days ahead by using data from one day and three days before the day in question. Of the proposed models, the ELM-SSO model scored highest, with R²=0.891 for the one-day-ahead prediction and R²=0.701 for six days ahead. Second was ELM-HGS (R²=0.889 and R²=0.699 for one day and six days respectively), and third was ELM (R²=0.883, R²=0.696). The results demonstrate ELM to be a robust data-driven method for simulating time series regimes that is appropriate for various hydrological applications. The models proposed in this study can be generalized to predict streamflow in rivers around the world.
“…For example, in forecasting TRW, ARIMA uses just the time lags of TRW itself and does not need other hydro-meteorological variables, such as air temperature, flow discharge, etc. The ARIMA model is widely used in the prediction of time series data: discharge patterns [45][46][47][48][49][50][51], river water characteristics [52][53][54], and water consumption [55,56]. However, in the literature, there are few studies that use Box-Jenkins stochastic models for forecasting TRW time series.…”
The temperature of river water (TRW) is an important factor in river ecosystem predictions. This study aims to compare two different types of numerical model for predicting daily TRW in the Warta River basin in Poland. The implemented models were of the stochastic type—Autoregressive (AR), Moving Average (MA), Autoregressive Moving Average (ARMA) and Autoregressive Integrated Moving Average (ARIMA)—and the artificial intelligence (AI) type—Adaptive Neuro Fuzzy Inference System (ANFIS), Radial Basis Function (RBF) and Group Method of Data Handling (GMDH). The ANFIS and RBF models had the most fitted outputs and the AR, ARMA and ARIMA patterns were the most accurate ones. The results showed that both of the model types can significantly present suitable predictions. The stochastic models have somewhat less error with respect to both the highest and lowest TRW deciles than the AIs and were found to be better for prediction studies, with the GMDH complex model in some cases reaching Root Mean Square Error (RMSE) = 0.619 °C and Nash-Sutcliff coefficient (NS) = 0.992, while the AR(2) simple linear model with just two inputs was partially able to achieve better results (RMSE = 0.606 °C and NS = 0.994). Due to these promising outcomes, it is suggested that this work be extended to other catchment areas to extend and generalize the results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.