Plenary Lecture
Artificial Intelligence-based Multi Station Streamflow Forecasting Using Wavelet-based Denoised Data
Professor Vahid Nourani
Department of Water Resources Engineering
Faculty of Civil Engineering
University of Tabriz, Iran
E-mail: nourani@tabrizu.ac.ir
Abstract: In this study, the ability of threshold based wavelet denoising Least Square Support Vector Machine (LSSVM) and Artificial Neural Network (ANN) models were evaluated for forecasting daily Multi Station (MS) streamflow of the Snoqualmie basin. For this aim at first step, outflows of the basin were forecasted via ad hoc LSSVM and ANN models just considering only data of one station individually at the outlet of the basin. Thereafter, MS-LSSVM and MS-ANN modeling was employed to use entire information of all sub-basins synchronously. Finally, the streamflow data of sub-basins observed at different stations were denoised via the wavelet based thresholding method, and then the purified signals were imposed into the LSSVM and ANN models for MS modeling of streamflow. The results show the superiority of LSSVM to the ANN, MS modeling to the individual sub-basin modeling employing denoised data, e.g., DCLSSVM=0.84 for the single station modeling, DCMS-LSSVM=0.90 for MS modeling and finally, DCDenoised-MS-LSSVM=0.93 for MS modeling using denoised data.
Brief Biography of the Speaker: Received his B.Sc. and M.S. degrees in Civil Engineering from University of Tabriz, Iran in 1998 and 2000, respectively. He then continued his graduate study in Civil and Environmental Engineering in the field of Hydrology at Shiraz University, Iran and Tohoku University, Japan and was graduated in 2005. Prof. Nourani was with the Faculty of Civil Engineering, University of Tabriz as an Assistant Professor from 2005- 2009; as Associate Professor from 2009-2014; as a Professor from 2014 and with Dept. of Civil Eng., University of Minnesota, USA at 2011 as visiting associate professor. In this period, 63 Ph.D. and M.S. students were graduated under his technical supervision. His research interests include rainfall-runoff modeling, Artificial Intelligence applications to water resources engineering, Hydroinformatics and computational hydraulics. His researches outcomes have been published as 102 Journal articles, 2 books, 7 book chapters and more than 120 papers presented in international and national conferences.