Sensor Based Air Pollutants Monitoring Using Unmanned Aerial Vehicle in Raipur City

Abstract

Sensor based air quality monitoring systems has an ability to provide real-time data with higher resolution. In the current study, small and portable sensor-based air quality monitoring system coupled with an unmanned aerial vehicle (UAV) platform has been used. Air pollutants such as particulate matter (PM10 and PM2.5), nitrogen dioxide (NO2), carbon monoxide (CO), and sulphur dioxide (SO2) are vertically monitored at eight different locations spread across four zones (i.e., industrial, transportation, residential, and public-place zone) in Raipur city. Vertical variation of pollutants at 5, 10, 15, and 20 m from ground level are monitored and analysed. Data has been analysed for the above five pollution causing parameters and it is observed that there is decreasing trend in the concentration has been observed to be winter > post-monsoon > monsoon season as reported in the previous studies for Raipur city. This type of monitoring system is cost effective as it requires UAV, sensors, mobile, and less skilled person for operation when compared to above mentioned monitoring systems in India. There are certain limitations of the study which includes less flying endurance of the UAV used with additional payload, observation of air pollutant concentration at lower altitude, and restrictions imposed on flying UAV at any location by the local authority due to COVID-19.

Keywords: attention-based encoder-decoder recurrent neural network, algal blooms, chlorophyll-a, gated recurrent unit neural network, long short-term memory neural network, time-series forecasting