Daily monsoon rainfall prediction using Artificial Neural Network (ANN) and Wavelet Based Artificial Neural Network (WANN) models
Loading...
Date
2018-07
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand)
Abstract
Rainfall is the most complex and difficult elements of hydrologic cycle to understand and to model due to the complexity of atmospheric processes. Long term Rainfall prediction is very important for countries whose economy depends mainly on agriculture. It is widely used in the energy industry for efficient resource planning and management including famine and disease control, rainwater catchment and ground water management. Considering these facts, a study has been carried out to assess the monsoon rainfall prediction in Parbhani Maharastara, India. The daily monsoon meteorological data of 30 years (1st June, 1985 – 30th Sept, 2014) were collected from meteorological observatory located at Vasantrao Naik Marathwada Krishi Vidyapeeth, Parbhani of Maharastra State, India. In the present study, Artificial Neural Network (ANN) and wavelet based Artificial Neural Network (WANN) techniques were used to predict the daily monsoon rainfall. The daily data for monsoon period (1st June to 30th September) of years 1985-2008 and 2008-2014 were used to train and test models, respectively. The best combination of input variables was selected on the basis of Gamma statistic. In case of ANN and WANN, back-propagation algorithm and tan sigmoid activation function were used to train and test the models. The performance of the models were evaluated qualitatively by visual observations and quantitatively using various performances indices Viz. RMSE, correlation coefficient, MSE, coefficient of efficiency and pooled average relative error. Finally, it can be concluded from the results that the performance of the WANN model is better than the ANN model.
Description
Keywords
null