Figure 1 - available via license: CC BY
Content may be subject to copyright.
Source publication
When the air quality problem of PM 2.5 first raised public attention and an emerging low-cost sensor technology appeared suitable as a monitoring measure for said problem, Taiwan’s Environmental Protection Administration devised a nationwide project involving large-scale sensor deployment for effective pollution monitoring and management. However,...
Context in source publication
Context 1
... on the spatial manipulation, the rapid deployment method is devised as three phases (Figure 1): the preparation phase, the implementation phase, and the modification phase. In the preparation phase, the steps include the objectives setting, elimination rules, and the spatial data preparation. ...
Similar publications
RESUMEN: Con este trabajo lo que se busca es dar a conocer las capacidades de los sistemas de información geográfica de código abierto como una alternativa viable, tanto técnica como económica, para el ordenamiento territorial. A través de un caso de estudio del anteproyecto del complejo de investigación y prestación de servicios en tecnología agro...
Citations
... By verifying performance, they concluded that low-cost sensor networks could be a valuable solution for air quality monitoring, but that in-field calibration and recalibration models should be applied to improve the accuracy of the measurement. In the paper [9], the authors proposed and described a new rapid deployment method for low-cost sensor deployment (in Taiwan) that consisted of the following phases: preparation, implementation, and modification. First, basic input data were defined (objectives, spatial data locations, elimination rules). ...
Public air quality monitoring relies on expensive monitoring stations which are highly reliable and accurate but require significant maintenance and cannot be used to form a high spatial resolution measurement grid. Recent technological advances have enabled air quality monitoring that uses low-cost sensors. Being inexpensive and mobile, with wireless transfer support, such devices represent a very promising solution for hybrid sensor networks comprising public monitoring stations supported by many low-cost devices for complementary measurements. However, low-cost sensors can be influenced by weather and degradation, and considering that a spatially dense network would include them in large numbers, logistically adept solutions for low-cost device calibration are essential. In this paper, we investigate the possibility of a data-driven machine learning calibration propagation in a hybrid sensor network consisting of One public monitoring station and ten low-cost devices equipped with NO2, PM10, relative humidity, and temperature sensors. Our proposed solution relies on calibration propagation through a network of low-cost devices where a calibrated low-cost device is used to calibrate an uncalibrated device. This method has shown an improvement of up to 0.35/0.14 for the Pearson correlation coefficient and a reduction of 6.82 µg/m³/20.56 µg/m³ for the RMSE, for NO2 and PM10, respectively, showing promise for efficient and inexpensive hybrid sensor air quality monitoring deployments.
... An example that shows that crowdsensing is not an easy process is the project of Taiwan's Environmental Protection Administration, a nationwide project where large-scale distributed sensors were deployed to effectively monitor and manage the emission of pollutants (Chen and Liu 2020). However, the methods used to optimize sensor distribution were inadequate for deploying thousands of sensors because geographic features were not considered. ...
The spatiotemporal heterogeneity of the air pollutants complicates appropriate monitoring. The collective measures or crowdsensing is a promising approach to achieve a better air pollution assessment because it includes the local concentration of pollutants, as well as the position and mobility of people. Thus, compared to traditional static monitoring, the participatory sensing data by low-cost sensors can avoid the misclassification of exposition to air pollutants, enabling a comprehensive understanding of their health effects. This systematic review integrates each core part of what is required to achieve crowdsensing for air pollution: sensors, portable devices, and data models. Despite the limitations of sensors in terms of sensitivity and selectivity, it has been possible to use portable air monitors to determine pollution hotspots around the world. However, limited models for data processing, performance issues when using low-cost devices, in addition to lack of community engagement, are the challenges to overcome for the feasibility of air pollution assessment with portable monitors.
Graphical abstract
... It was quite a long campaign (June 2015-December 2017) and after a detailed result analysis, it was concluded that the usage of low-cost sensor devices showed promising results that could address the data quality objective of the indicative measurements [6]. The authors of [41] developed a rapid deployment method for low-cost sensors deployment. The method has three phases: preparation, implementation and modification. ...
In this paper, we present a detailed analysis of the public data provided by low-cost sensors (LCS), which were used for spatial and temporal studies of air quality in Krakow. A PM (particulate matter) dataset was obtained in spring in 2021, during which a fairly strict lockdown was in force as a result of COVID-19. Therefore, we were able to separate the effect of solid fuel heating from other sources of background pollution, mainly caused by urban transport. Moreover, we analyzed the historical data of PM2.5 from 2010 to 2019 to show the effect of grassroots efforts and pro-clean-air legislation changes in Krakow. We designed a unique workflow with a time-spatial analysis of PM1, PM2.5, and PM10, and temperature data from Airly(c) sensors located in Krakow and its surroundings. Using geostatistical methods, we showed that Krakow’s neighboring cities are the main sources of air pollution from solid fuel heating in the city. Additionally, we showed that the changes in the law in Krakow significantly reduced the PM concentration as compared to neighboring municipalities without a fossil fuel prohibition law. Moreover, our research demonstrates that informative campaigns and education are important initiating factors in order to bring about cleaner air in the future.
... It was quite a long campaign (June 2015-December 2017) and after a detailed result analysis, it was concluded that the usage of low-cost sensor devices showed promising results that could address the data quality objective of the indicative measurements [6]. The authors of [41] developed a rapid deployment method for low-cost sensors deployment. The method has three phases: preparation, implementation and modification. ...
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.
