Time Series Analysis of Reference Crop Evapotranspiration Using Machine Learning Techniques For Ganjam District, Odisha, India

Abstract

Evapotranspiration (ET0) influences water resources and it is considered as a vital process in aridic hydrologic frameworks. It is one of the most important measure in finding the drought condition. Therefore, time series forecasting of evapotranspiration is very important in order to help the decision makers and water system mangers build up proper systems to sustain and manage water resources. Time series considers that -history repeats itself, hence by analysing the past values, better choices, or forecasts, can be carried out for the future. In this work, an attempt is made to acquire a long-term forecast of monthly averaged evapotranspiration data in Ganjam area, Odisha, India. Ten years of ET0 data was used as a part of this study to make sure a satisfactory forecast of monthly values. Nevertheless, the change of inherent characteristics in the ET0 may occur very slowly and time-series models may be useful for long-term planning of water resource management. In this study, three models: a seasonal time series Autoregressive and Moving Average (ARIMA) mathematical model, artificial neural network model, support vector machine model are presented. These three models are used for forecasting monthly reference crop evapotranspiration (ET0) based on ten years of past historical records (1991-2001) of measured evaporation at Ganjam region, Odisha, India without considering the climate data. The developed SVM model provides reasonable and adequate estimates, compared to other methods.