Enhanced variational mode decomposition with deep learning SVM kernels for river streamflow forecasting

The present scenario of global climatic change challenges the sustainability and existence of water bodies around the globe. Due to which, it is always important and necessary to forecast the streamflow of rivers with respect to natural precipitation process. In this research study, novel enhanced variational mode decomposition (EVMD) with deep support vector machine (DSVM) kernels is proposed to perform forecasting of river streamflow. The developed computational intelligent machine learning model is a hybrid combination of the new enhanced VMD and the novel deep SVM kernels that is trained suitably to forecast the streamflow with respect to their deep learning layers. Initially, singular spectrum analysis (SSA) is employed for noise removal and the enhanced VMD with its features of decomposing and extracting more prominent features from the data are hybridized with the deep SVM kernel models to predict the streamflow of the considered Cahaba River data sets. Deterministic grey wolf optimizer (DGWO) is modelled in this research paper to fine tune the parameters of the deep SVM model. Previous prediction techniques modelled had difficulties in respect of local and global minima occurrences, stagnation, delayed and premature convergence and so on. Hence, in this study, the hybrid deep learning model forecasted the streamflow for the considered data sets and its superiority was validated with the comparative analysis with the previous forecasting techniques adopted. The developed forecasting model shall be used by the hydrologists for predicting the daily streamflow with the highest prediction accuracy rate of 97.54% with respect to training process and in case of testing mechanism the prediction accuracy rate is 96.47% This 97.54% of training prediction accuracy rate confirms the effectiveness of modelled new deep SVM algorithm for the streamflow forecasting of hydrologists.