Abstract
Reliable and accurate streamflow simulation has a vital role in water resource development, mainly in agriculture, environment, domestic water supply, hydropower generation, flood control, and early warning systems. In this context, these days, deep learning algorithms have got enormous attention due to their high-performance simulation capacity. In this study, we compared multilayer perceptron (MLP), long short-term memory (LSTM), and gated recurrent unit (GRU) with the proposed new hybrid models, including CNN-LSTM and CNN-GRU. Hence, we can simulate one-step daily streamflow in different agroclimatic conditions, rolling time windows, and a range of variable input combinations. The analysis used daily multivariate and multisite time series data collected from Awash River Basin (Borkena watershed: Ethiopia) and Tiber River Basin (Upper Tiber River Basin: Italy) stations. The datasets were subjected to rigorous quality control processes. Consequently, it rolled to a different time lag to remove noise in the time series and further split into training and testing datasets using a ratio of 80 : 20, respectively. Finally, the results showed that integrating the GRU layer with the convolutional layer and using monthly rolled average daily input time series could substantially improve the simulation of streamflow time series.
Highlights
One of the emerging research areas in hydrology is hydrological simulation [1], through which catchment responses are evaluated in terms of meteorological forcing variables
To the best of our knowledge, we identify minimal literature that shows the performance variation of different hybrid models for streamflow simulation in various input variability conditions at once. us, we compared various forms of hybrid convolutional neural network (CNN)-long short-term memory (LSTM) and CNN-gated recurrent unit (GRU) architectures with the classical multilayer perceptron (MLP), GRU, and LSTM networks to simulate single-step streamflow using two climatic regions, available precipitation, and minimum and maximum temperature data
Deep learning models are part of a broader family of machine learning, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), deep belief networks (DBNs), and deep neural networks (DNNs). ese models have been applied to different fields of study, including speech recognition, computer vision, natural language processing, and time series analysis [13, 16, 34,35,36]. e following sections will briefly discuss some of these architectures that were used in the present study
Summary
One of the emerging research areas in hydrology is hydrological simulation [1], through which catchment responses are evaluated in terms of meteorological forcing variables. River flow simulation is not an easy task since river flow time series are commonly random, dynamic, and chaotic. E relationship between streamflow generation and other hydrologic processes is nonlinear, which is controlled by external climatic factors and global warming and by physical catchment characteristics. Stream flows are mostly recorded at river gauging stations. Different research studies show that the availability of gauging station records is generally decreasing in most parts of the world [4]. Tourian et al [5] gathered a time series plot of the number of stations with available discharge data from the Global Runoff Data Centre (GRDC)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
