Air Quality Assessment of Uttarakhand (India) Using Satellite Data and Machine Learning Techniques
Divyanshu Chandra *
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
Govind Verma
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
Navtej Anand
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
Subodh Prasad
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
Binay Kumar Pradey
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
Shikha Goswami
Department of Information Technology, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.
*Author to whom correspondence should be addressed.
Abstract
Degrading Air Quality is a major concern for all species on this planet. Over the years, it is seen that air quality is constantly degrading mainly because of the reasons such as industrialisation, deforestation, and green-house effect. Main parameters to be considered for the Air Quality are the Carbon Monoxide (CO), Nitrogen Dioxide (NO2), Sulphur Dioxide (SO2), Ozone (O3) and Aerosols. A study of these parameters changing over time is necessary so to keep a check on the degrading air quality.
In this study, the data of Carbon Monoxide (CO), Nitrogen Dioxide (NO2), Sulphur Dioxide (SO2), Ozone (O3) and Aerosols are taken for the past 5 years i.e. 2018 to 2022 and their time series is extracted thereafter a test on stationarity is done so as to know whether these series are stationary or not. Two machine learning models namely Holt winter’s Smoothing and FbProphet is applied to predict the value adjacent to the original value and a error metric is comparison is done to find out which model is best suited for forecasting these Air Quality parameters.
Keywords: Air quality, FbProphet model, Holt winter’s method, trend analysis, time series, time series analysis