UAV-based PM 2.5 Monitoring for Small-Scale Urban Areas

Abstract

Air quality data such as Particulate Matter PM2.5 collection near the ground is difficult, particularly in small complex regions. This study aims to introduce a PM2.5 prediction algorithm based on measurements from Unmanned Arial Vehicle (UAV)-based sensing system and validate the model at a specified low altitude. Observations were applied around 1.6 km² area in University Putra Malaysia. This study uses an empirical method via applying amassed records of PM2.5 and meteorological parameters to produce a predictive Geographically Weighted Regression (GWR) model. An accuracy value is computed from the probability value given by the regression analysis model. To validate this approach, we have utilized training and testing data. To evaluate and validate the suggested model, we applied the model to the training set. The obtained result indicated that there is a good statistical correlation, and demonstrated that the characteristics obtained by analysis are able to predict the concentration of PM2.5.