UAV-Based Air Pollutant Source Localization Using Combined Metaheuristic and Probabilistic Methods

Abstract

Air pollution is one of the greatest risks for the health of people. In recent years, platforms based on Unmanned Aerial Vehicles (UAVs) for the monitoring of pollution in the air have been studied to deal with this problem, due to several advantages, such as low-costs, security, multitask and ease of deployment. However, due to the limitations in the flying time of the UAVs, these platforms could perform monitoring tasks poorly if the mission is not executed with an adequate strategy and algorithm. Their application can be improved if the UAVs have the ability to perform autonomous monitoring of the areas with a high concentration of the pollutant, or even to locate the pollutant source. This work proposes an algorithm to locate an air pollutant’s source by using a UAV. The algorithm has two components: (i) a metaheuristic technique is used to trace the increasing gradient of the pollutant concentration, and (ii) a probabilistic component complements the method by concentrating the search in the most promising areas in the targeted environment. The metaheuristic technique has been selected from a simulation-based comparative analysis between some classical techniques. The probabilistic component uses the Bayesian methodology to build and update a probability map of the pollutant source location, with each new sensor information available, while the UAV navigates in the environment. The proposed solution was tested experimentally with a real quadrotor navigating in a virtual polluted environment. The results show the effectiveness and robustness of the algorithm.

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

“…Recently, various machine and deep learning methods have been used to increase the probability of target recognition. Research on probabilistic searches includes [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ], and search methods using artificial intelligence include [ 28 , 29 , 30 , 31 , 32 ]. Symington et al [ 20 ] conducted an early study on stochastic searches.…”

Using a Unmanned Aerial Vehicle to Assess Air Pollution and Identify Dominant Emission Sources

“…Due to significant distortions of measurement conditions related to the influence of air streams generated by the UAV's propellers and its movement in relation to the turbulent air around the inlet to the measurement systems, extensive work is also required to properly calibrate the measurement devices, as well as to determine corrections making the obtained results more realistic [Alvarado et al, 2017]. An interesting extension of the measurement methodology using UAV may be the automatization of flights, allowing on the one hand less human involvement in the measurement procedure, thus reducing the cost and increasing the availability of measurement, as well as improving the repeatability and thus the quality of measurements on the other hand [Yungaicela-Naula et al, 2019]. It is also important to interpret the results obtained solely on the basis of pollutant concentrations together with meteorological conditions taken under consideration [Køcks, 2016].…”

Optimization of air pollution measurements with unmanned aerial vehicle low-cost sensor based on an inductive knowledge management method

“…Generally, the approaches to investigating the fine-scale spatiotemporal distribution of air pollutants can be classified into three categories: air pollution dispersion models, fixed-site measurements, and mobile measurements (Cao et al 2020). Tracing of atmospheric pollutants release of and validation of the measurements using unmanned aerial vehicles is still difficult task from a mathematical point of view (Šmídl and Hofman 2013;Yungaicela-Naula et al 2019;Villa et al 2016).…”