3D AQI Mapping Data Assessment of Low-Altitude Drone Real-Time Air Pollution Monitoring

Air pollution primarily originates from substances that are directly emitted natural or anthropogenic processes, such as carbon monoxide (CO) gas in vehicle exhaust sulfur dioxide (SO2) released factories. However, a major air problem is particulate matter (PM), which an adverse effect of wildfires and open burning. Application tools for monitoring risk areas using real-time with drones have emerged. A new quality index (AQI) display, three-dimensional (3D) mapping based on data assessment, essential timely environmental surveying. The objective this paper to present 3D AQI assessment hybrid model machine-learning method drone (Dr-TAPM). Dr-TAPM was designed by equipping multi-environmental sensors (CO), ozone (O3), nitrogen (NO2), (PM2.5,10), (SO2), pre- post-processing the model. proposed backpropagation neural network (BPNN) convolutional (CNN) algorithms. Experimentally, we considered case study detecting smoke emissions burning scenario. As result, PM2.5,10 CO were detected pollutants map locations shown validation learning rates apparent, accuracy predicted 98%.