Author : Anand M. Sharan

Present work uses four separate methods to arrive at the prediction value by taking the average of the results of these four. Here, the calculations are based on past 32 year history of rainfall in Telangana. The four methods are: (1) The Root Mean Square (RMS) values, (2) the Artificial Neural Network (ANN) method, (3) The Fast Fourier Transform (FFT) method, and the Time Series method. Out of these the first and the last methods involve linear regression hence the results obtained exhibit a linear curve. Here, the prediction can be made about 8 months in advance to give sufficient time for planning to the farmers or hydro-electric power generators, or the governments at different levels.

Keywords: Monsoon rain prediction, annual rainfall, rainfall frequency spectrum, El Nino and La Nina influence on rainfall, drought and famine, crop failure, drinking water shortage.

Article published in International Journal of Current Engineering and Technology, Vol.10, No.5 (Sept/Oct 2020)