PREDICTION OF AIR POLLUTION USING MACHINE LEARNING

PREDICTION OF AIR POLLUTION USING MACHINE LEARNING

V.GOKULAKRISHNAN¹, BINKENA KEERTHANA², GARIGAPATI YAMINI³, MADALA SUPRIYA⁴, MAHESHWARI.M⁵

¹Assistant Professor, Department of Computer Science and Engineering, Dhanalakshmi Srinivasan Engineering College (Autonomous), Perambalur

²Student, Department of Computer science and Engineering, Dhanalakshmi Srinivasan Engineering College (Autonomous), Perambalur

³Student, Department of Computer science and Engineering, Dhanalakshmi Srinivasan Engineering College (Autonomous), Perambalur

⁴Student, Department of Computer science and Engineering, Dhanalakshmi Srinivasan Engineering College (Autonomous), Perambalur

⁵Student, Department of Computer science and Engineering, Dhanalakshmi Srinivasan Engineering College (Autonomous), Perambalur

ABSTRACT

Air pollution is a growing problem in many parts of the world and has serious health and environmental impacts. Machine learning techniques can be used to predict air pollution levels, which can help government and public health officials make informed decisions to reduce the impact of pollution. One common approach to predicting air pollution is to use machine learning algorithms to analyse data from air quality monitoring stations. This data can include information on levels of pollutants such as particulate matter (PM), nitrogen oxides (NOx), and sulphur dioxide (SO2), as well as meteorological data such as temperature, wind speed, and humidity. By analysing this data, machine learning algorithms can identify patterns and make predictions about future pollution levels. Another approach is to use satellite data to predict air pollution levels. This approach involves analysing satellite images to detect changes in land use, traffic patterns, and other factors that can contribute to air pollution. Machine learning algorithms can then use this data to predict future pollution levels. Overall, machine learning has the potential to improve our understanding of air pollution and help us develop more effective strategies to reduce its impact.

Keywords: SVR, Ridge Regression, Elastic Net Regression, Random Forest