Time Series Data Mining in Real Time Surface Runoff Forecasting through Support Vector Machine

Abstract

This study presents support vector machine based model for forecasting the runoff-rainfall events. A SVM based model is either implemented through Radial base or Gaussian based Kernel functions. SVM uses precipitation, temperature, sediment, rainfall, water level and discharge as input variable parameters. In this research the Sequential minimal optimization algorithm (SMO) has been implemented as an effective method for training support vector machines (SVMs) on classification tasks defined on large and sparse real time data sets. In this work, we generalized the SMO so that it can handle regression problem and by dividing datasets into test data and trained data performed future forecasting keeping four major evaluation parameters Root Mean Square Error (RMSE), Mean Absolute error (MAE), Mean Squared error (MSE) and correlation coefficient (CC). Study site for this research is Narmada basin reservoir hosahangabad catchment area and the experimental results on predicting the full natural flow of Narmada River indicates that support vector machine method performs far better and more accurate from the current forecasting practices (Artificial Neural Network).

Comparison of the performances of GEP, ANFIS, and SVM artifical intelligence models in rainfall simulaton

“…According to their results, the predictions of the ANFIS model are more accurate than the classical models. Choubey et al (2014) used the SVM model to predict and analyze the inflow of Narmada Reservoir Dam in the Indian state of Prague showing that this method has a very good ability to simulate and predict the average monthly flow. He et al (2014) used the SVM model to predict river flow in mountainous and semi-arid regions in the northwestern part of China, and they found that SVM has better performance than ANN and ANFIS, to predict river flow in the semi-arid mountainous areas.…”