Water Quality Prediction of Ganga River using Time-series Models

Abstract

Life of Living organism have present on the earth depends on Water. Water Quality is also equally important as Water. Ganga river is fulfilling the needs of water of a large population of India. Being a citizen of India it’s our responsibility to keep the Ganga River neat & clean. A large number of governments funded base stations available for forecasting the Water Quality of ganga river. But there is a need of low-cost prediction techniques of water quality based on data available from these base stations. It can help the government to take the necessary decisions to cure the water quality of Ganga River & save the lives of many livings’ organism depends on Ganga River. Monitoring & forecasting of water quality of Ganga River is most important because ganga river is the main source of drinking water of a large population of India. In this paper two time series-based models such as Auto-Regressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA) have been used to predict the water quality of Ganga River. The models are developed on water quality data available of 10 base stations on the Uttarakhand Pollution Control Board’s official website. Four water quality parameters-Temp, pH, DO, BOD data is used for models training & calculating WQI (Water Quality Index). The result of experiment shows that SARIMA model predict the water quality parameters as well as Water Quality Index (WQI) more accurately.