scholarly journals Wireless Sensors Network Monitoring of Saharan Dust Events in Bari, Italy

Proceedings ◽  
2018 ◽  
Vol 2 (13) ◽  
pp. 898 ◽  
Author(s):  
Michele Penza ◽  
Domenico Suriano ◽  
Valerio Pfister ◽  
Mario Prato ◽  
Gennaro Cassano
Keyword(s):  
Air Quality ◽  
Low Cost ◽  
Cost Effective ◽  
Saharan Dust ◽  
Quality Monitoring ◽  
Sensor Data ◽  
Air Quality Monitoring ◽  
Dust Events ◽  
Air Quality Monitoring Stations ◽  
Monitoring Stations

A sensors network based on 8 stationary nodes distributed in Bari (Southern Italy) hasbeen deployed for urban air quality monitoring during advection events of Saharan dust in theperiod 2015–2017. The low-cost sensor-systems have been installed in specific sites (buildings,offices, schools, streets, airport) to assess the PM10 concentration at high spatial and temporalresolution in order to supplement the expensive official air monitoring stations for citizen sciencepurposes. Continuous measurements were performed by a cost-effective optical particle counter(PM10), including temperature and relative humidity sensors. They are operated to assess theperformance during a long-term campaign (July 2015–December 2017) of 30 months for smart citiesapplications. The sensor data quality has been evaluated by comparison to the reference data of the9 Air Quality Monitoring Stations (AQMS), managed by local environmental agency (ARPA-Puglia)in the Bari city.

scholarly journals Developing Relative Humidity and Temperature Corrections for Low-Cost Sensors Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3338
Author(s):  
Ivan Vajs ◽  
Dejan Drajic ◽  
Nenad Gligoric ◽  
Ilija Radovanovic ◽  
Ivan Popovic
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Relative Humidity ◽  
Low Cost ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Lower Accuracy ◽  
Wide Range ◽  
The Impact ◽  
Monitoring Stations

Existing government air quality monitoring networks consist of static measurement stations, which are highly reliable and accurately measure a wide range of air pollutants, but they are very large, expensive and require significant amounts of maintenance. As a promising solution, low-cost sensors are being introduced as complementary, air quality monitoring stations. These sensors are, however, not reliable due to the lower accuracy, short life cycle and corresponding calibration issues. Recent studies have shown that low-cost sensors are affected by relative humidity and temperature. In this paper, we explore methods to additionally improve the calibration algorithms with the aim to increase the measurement accuracy considering the impact of temperature and humidity on the readings, by using machine learning. A detailed comparative analysis of linear regression, artificial neural network and random forest algorithms are presented, analyzing their performance on the measurements of CO, NO2 and PM10 particles, with promising results and an achieved R2 of 0.93–0.97, 0.82–0.94 and 0.73–0.89 dependent on the observed period of the year, respectively, for each pollutant. A comprehensive analysis and recommendations on how low-cost sensors could be used as complementary monitoring stations to the reference ones, to increase spatial and temporal measurement resolution, is provided.

Sign in / Sign up

Export Citation Format

Share Document