Input attributes optimization using the feasibility of genetic nature inspired algorithm: Application of river flow forecasting

Abstract

In nature, streamflow pattern is characterized with high non-linearity and non-stationarity. Developing an accurate forecasting model for a streamflow is highly essential for several applications in the field of water resources engineering. One of the main contributors for the modeling reliability is the optimization of the input variables to achieve an accurate forecasting model. the main step of modeling is the selection of the proper input combinations. Hence, developing an algorithm that can determine the optimal input combinations is crucial. this study introduces the Genetic algorithm (GA) for better input combination selection. Radial basis function neural network (RBFNN) is used for monthly streamflow time series forecasting due to its simplicity and effectiveness of integration with the selection algorithm. In this paper, the RBFNN was integrated with the Genetic algorithm (GA) for streamflow forecasting. The RBFNN-GA was applied to forecast streamflow at the High Aswan Dam on the Nile River. The results showed that the proposed model provided high accuracy. The GA algorithm can successfully determine effective input parameters in streamflow time series forecasting. BackgroundThe inflow parameter is a significant component of the hydrological process in water resources. Accurate forecasting of river flows for long-term and short-term forecasts are crucial to solving different water engineering problems (e.g., designing agricultural land and flood protection works for urban areas) 1 . Accurate and reliable flow forecasting is a vital reference for making decisions in reservoir system control. Hence, streamflow forecasting modeling has attracted attention and great advances in this field have been developed in recent decades 2 .Conventional models (linear models) cannot capture the non-linearity and non-stationary of hydrological applications. The autoregressive moving average (ARMA) model, autoregressive model, and autoregressive integrated moving average (ARIMA) model are linear models that have been applied in hydrological time series forecasting 3-5 . The need for determining models capable of addressing the nonlinearity and non-stationary that are characteristics of natural reservoir inflow data has led researchers to propose advanced methods 6,7 . Recently, artificial intelligence methods showed relatively good forecasting accuracy. However, they had trouble detecting the highly stochastic pattern of the data.The most popular example of artificial intelligence methods is the artificial neural network (ANN). Wu et al. 8 established the Feed Forward Neural Network (FFNN) model for streamflow simulation. The finding evidenced the potential of the FFNN model for streamflow modeling. Two algorithms including multilayer perceptron (MLP) and radial basis function neural network (RBFNN) developed for river flow prediction 9 . The authors reported that the MLP model outperformed the RBNN model. Danandeh Mehr et al. 10 investigated the ability of successive station forecasting models using ANN in a rain gauge-...

Application of Artificial Intelligence Models for Evapotranspiration Prediction along the Southern Coast of Turkey

“…In addition, a study that covers the whole area of the Mediterranean Sea via one robust model is needed. For further investigation, feature selection approaches can possibly be integrated prior to the predictive learning process to extract the essential input variables for the prediction matrix [98,99].…”

Cross Assessment of Twenty-One Different Methods for Missing Precipitation Data Estimation

“…The correlation coefficient indicates the relationship strength between the observed and estimated data. A higher positive value of Pearson coefficient shows that the estimates will be high or low values when the observed is high or low, respectively, and gives evidence that the used method is suitable for predicting missing data [13,60]. The correlation coefficient can be calculated from the following equation:…”

The Capacity of the Hybridizing Wavelet Transformation Approach With Data-Driven Models for Modeling Monthly-Scale Streamflow

“…In general, hydrological models are divided into data-driven models and physical-based models [13]. Physical-based models are known as white box models that involve the physical process in the hydrological cycle, leading to the need for a large amount of data that is not always available [14].…”