UAV-Based Real-Time Air Quality Monitoring and Prediction Using Machine Learning Approach

Globally, air pollution has become a major problem due to the growth of the human population and rapid urbanization, posing a serious threat to the environment and human health. Currently, most monitoring systems are based on fixed monitoring stations and are inefficient due to slow response time. An accurate and real-time air quality monitoring and prediction (AQMP) system is required to prevent health problems caused by air pollution. With the swift advancement of Internet of Things (IoT) technologies, such as low-cost sensors and advanced wireless communication systems capable of sensing their environment, connecting with other systems, and interacting with users. To overcome the problems of existing systems, this article aims to develop an unmanned aerial vehicle (UAV)-based real-time AQMP system by integrating artificial intelligence and data science technologies. The proposed UAV is equipped with lightweight air quality sensors, including particulate matter (i.e., ${\mathrm { PM}}_{2.5}$ and PM₁₀), carbon monoxide (CO), carbon dioxide (CO₂), and ozone (O₃), and meteorological sensors. The sensors are mounted on the UAV via the microcomputer, and the sensors’ reading data is transmitted to the Web server via a message queueing telemetry transport (MQTT) protocol using a 5G mobile network module. Practical experiments were conducted in Hsinchu County and the industrial area of Yunlin County, Taiwan, to collect real-time air pollutant data. Then, we employed a hybrid of attention mechanism, convolutional neural network (CNN) and gated recurrent unit (GRU) algorithms to predict future air quality levels. Experimental results show that the proposed system improves prediction performance compared with baseline time series algorithms.