Professional Documents
Culture Documents
a r t i c l e i n f o a b s t r a c t
Article history: The poor air quality found in big cities is harmful to human health. The aim of the LIFE PHOTOSCALING
Received 28 November 2017 Project (LPP) is to assess the effectiveness of different photocatalytic pavements in reducing NO2 pol-
Received in revised form 14 March 2018 lution. The objective of this preliminary study is to determine how well low cost AQmesh sensors can
Accepted 4 April 2018
accurately enough measure NO2 concentrations to be able to determine the effects of using photocat-
Available online 11 April 2018
alytic pavements. Data was collected from AQmesh sensors that were installed in two Air Quality Stations
in order to monitor NO2 under traffic and urban background conditions. The NO2 measurements were
Keywords:
unreliable, resulting in an unsatisfactory level of accuracy. A two-step calibration method was devised
Electrochemical sensors
Neuronal networks
in order to overcome this limitation. This method consisted of supervised statistical machine learning
Uncertainty regression algorithms. A first Multivariate Linear Regression provided a new explanatory variable that
Nitrogen dioxide contained valuable information about the error. This variable was fed into more sophisticated equations,
Air quality such as Random Forests, Support Vector Machines and Artificial Neural Networks. The various models
were evaluated by calculating statistics of errors and relative expanded uncertainties, and through Taylor
Diagrams. After a careful calibration, AQmesh sensors met the Air Quality Directive’s standards of accu-
racy at high concentrations of NO2 . However, we found that each individual sensor behaves differently
and thus, each unit requires the development and application of a specific calibration model.
© 2018 Elsevier B.V. All rights reserved.
https://doi.org/10.1016/j.snb.2018.04.021
0925-4005/© 2018 Elsevier B.V. All rights reserved.
246 J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254
Low-cost sensors (LCS) are being developed through initiatives rect measurements were evaluated. This process had to be repeated
such as AirSensEUR [9,10] and are based in both electrochemical for every POD under each ambient condition. This study should be
or solid state microsensors designed to monitor urban ambient air repeated in order to account time drift [20] and seasonally variable
gases like NOx , CO, SO2 or O3 . Networks of mobile or fixed LCSs gas meteorological conditions.
sensors permit the mapping of wider areas of the city [11] with a
high time resolution. The sensors are normally calibrated against 2. Materials and methods
the measurements recorded in nearby AQSs in a co-location cam-
paign. LCSs are versatile, autonomous, and can make measurements 2.1. Air quality stations
at several points over wide areas [12], as well as remote spaces [13],
reducing the cost of detection in comparison to AQSs and allowing Reference measurements were collected from two AQSs. One of
the generation of large observation datasets. However, this technol- these was located in a traffic area in a neighbourhood of Arturo Soria
ogy has its challenges as well: LCSs show cross-sensitivity between street in the city of Madrid. The other was located in an urban back-
the target gas and other gases in the urban atmosphere. In particu- ground area in the town of Arganda del Rey, located about 25 km
lar, NO2 and O3 electrochemical sensors are prone to show mutual southeast of Madrid city. As a consequence, the behaviour of the
cross-sensitivities [14]. LCSs are also dependent on weather condi- AQmesh PODs could be studied under two different environmental
tions, and suffer from short term and long term drift. In addition, conditions. The measurement techniques utilized were:
units of the same type are highly variable [15], poorly selective, and
not very stable [16–18]. • Chemiluminescence, to measure levels NO and NO2 .
LCSs have been extensively checked and calibrated in labora- • UV absorption, to measure levels of O3 .
tory. However, the results change dramatically when the devices
are deployed in urban sites [15,17–19]. This is because the con-
Meteorological parameters were recorded only in Arganda del
ditions of the urban atmosphere cannot be exactly reproduced in
Rey because the Arturo Soria AQS did not have a meteorological
the laboratory. Consequently, in-field calibrations of these devices,
station.
under the conditions in which the LCSs will be used, are essential
The Arturo Soria AQS is managed by the Madrid City Council and
for obtaining accurate readings in the urban atmosphere. There-
the Arganda del Rey AQS is managed by the Comunity of Madrid
fore, a calibration method has to be designed for each individual
autonomous government.
device under the particular conditions it will be used.
These limitations make the calibration of these devices difficult,
and complex equations are required to assure the reliability of these 2.2. AQmesh PODs
instruments. As part of the MacPoll Project, the Joint Research Cen-
tre has published several reports on this subject and has designed AQmesh PODs were selected as model LCSs. Our group had
a calibration protocol for LCSs [20]. In most of these studies, sta- extensive experience with LCSs that were either electrochemical
tistical methods, such as linear regression (LR), multivariate linear or MeO based. AQmesh was chosen because they provide accu-
regression (MLR) and artificial neural networks (ANN) [13,21,23,25] rate readings over a wide range of values: from 0 to 4000 ppb for
are used to fit the signals. A recent work provides a comprehen- NO and NO2 , and from 0 to 1800 ppb for O3. All the gas sensors
sive comparison of several machine learning algorithms, including in the AQmesh PODs tested were Alphasense electrochemical sen-
training, optimization and validation [22]. Some ANN studies have sors [28]. Detailed technical specifications can be found in reference
relied on predictive variables from different sensors as inputs [29]. The POD’s supplier applies a proprietary algorithm which con-
[19,20], an approach that solved the primary problem of interfer- verts the electrical signals into concentration units. The user could
ence between sensor measurements and external variables. This download the resulting information from a website. From here
strategy has led to more accurate results. Another approach has on in, we will refer to this downloaded data as “raw” despite the
been to use a reference station to update the parameters of the prior treatment. However, treating the data with the proprietary
calibrated sensors, thereby correcting for the drift [24]. In other algorithm alone did not result in the required level of accuracy.
study [26] other sophisticated machine learning algorithms such Therefore, the data required further treatment.
as boosted regression trees and Gaussian process emulators were
successfully applied to process the raw signal of their LCSs, solv- 2.3. Calibration by statistical models
ing the main complex interferences in the measurements. Here we
report the results of using ANNs and less commonly utilized meth- Four PODs were placed on an iron stand near the sampling points
ods, such as Support Vector Machines (SVM) and Random Forests of selected AQ stations. This operation was carried out between
(RF), to fit the data using AQS reference data as objective variables. 11–28 March 2017 in Arturo Soria, and between 28 March to 10
The goal of the LIFE PHOTOSCALING Project (LPP) is to achieve April 2017 in Arganda del Rey. Once the operation was finished,
the sustainable use photocatalytic technologies on urban pave- both the data from the reference stations and the data from the
ments. As part of the LPP, different photocatalytic materials will be PODs were utilized for the calibration. The calibration of the PODs
tested for using as pavements [27]. To evaluate the effectiveness of was carried out using statistical machine learning methods.
these materials, accurate and precise methods for measuring NO2 The data treatment was performed using the open source lan-
are crucial. The objective of this study is to validate the LCS gas sen- guage R and using the IDE Rstudio software [30,31].
sor technology for use in the context of the LPP. We report here a At first sight, an acceptable correlation was observed between
more advanced method for calibrating LCS devices, making them the station and the POD raw data. Only a small variability between
more accurate and precise. the data sets was observed. For being low cost sensors, AQmesh per-
AQmesh units (PODs) were used as model LCSs. Manufacturer formed relatively well, but did not provide the accuracy required
calibration of these devices was not found to be satisfactory in for use by the LIFE PHOTOSCALING Project. Therefore, the data was
terms of accuracy. Four PODs were installed in two AQSs in the treated further.
Community of Madrid. These AQSs covered two different ambient To carry out the data treatment, a novel regression algorithm
conditions: traffic and urban background. Data was gathered from was applied in two steps (see Fig. 1). First, a MLR model was fit-
both the PODs and AQSs. Various statistical methods were applied ted using explanatory variables measured by the sensors (CNO2 ,
to fit the data. Interactions between variables that obscured the cor- CNO , CO3 , T). RH was discarded applying a backward elimination
J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254 247
Fig. 2. A representative diagnostic of the MLR model. The results for POD 1 are shown. The residuals vs. fitted values plot is seen on the left. The histogram of the residuals
is seen on the right.
process due to its high p-value. MLR is a suitable model for electro- Random Forests were calculated using the RandomForest soft-
chemical sensors because their response to gas concentrations is ware package [36]. Random Forests are decision trees combined
linear and the cross-sensitivities are additive. From this model, we with a bagging process. Several decision trees are calculated and
derived a new variable called diff, which is the difference between averaged. The individual trees are computed via samples selected
the model predictions and the measure of the AQmesh itself. The from an initial input set [37]. It was found that using more than 500
new variable diff was used to account for the error between pre- trees did not improve the accuracy of the model in this study case,
dicted and observed data and provided useful information about so we set this hyperparameter to 500.
interference among variables. In the second step, along with the A subsequent complete calibration will be required in the future
same explanatory variables, diff was fed into more sophisticated on a quarterly basis because of the expected drift and changes in
regression methods such as SVMs, RFs and ANNs. meteorological conditions.
Using the Neuralnet software package [32], ANNs were calcu-
lated using an algorithm that had resilient back-propagation and
weight backtracking features [33]. Several ANNs architectures were 2.4. Model evaluation
tested and the one that showed the best fit with a reasonable degree
of complexity was selected. As a result, we used a configuration The model learning process was carried out randomly splitting
including 2 hidden layers, one with 10 nodes and the other with 5 the dataset into two smaller datasets. The training set, used for
nodes. The inputs were scaled to have a mean of zero and standard the model learning and containing the 75% of the data while the
deviation of 1. test set, with the remaining 25% of the data. Once the models were
SVMs were fitted using the e1071 software package [34]. SVMs trained, they were preliminary evaluated using the test dataset. The
are a popular nonparametric technique primarily developed to errors calculated by means of the following equations were used to
solve classification problems. This technique makes use of hyper- validate the models:
planes to search for the maximum separation between classes using n 2
kernel functions. The SVMs were then modified so that they could SSE i=1
y − yi,pred
i
r2 = 1 − =1− n
(1)
be applied to regression problems [35]. In our case, the regression SST
i=1 (yi
− ȳ)2
problem was linear so a linear kernel was set in the algorithm. Other
authors have used other kernel function to test their impact in the 1 n 2
MSE = y − yi (2)
performance of their models n i=1 i,pred
248 J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254
Fig. 3. Time series from the Arganda del Rey AQS. The T plot is on the left, and RH plot is on the right. AQS measurements are plotted with a black line. All other plot colours
represent POD measurements.
Fig. 4. Time series of NO2 concentration in Arturo Soria AQS for each POD. Blue lines represent the individual PODs, black lines represent the AQS. (For interpretation of the
references to colour in this figure legend, the reader is referred to the web version of this article.)
100 n yi,pred − yi
1 n 2 MAPE = | | (5)
RMSE = yi,pred − yi (3) n i=1 yi
n i=1
Where:
SSE , is the sum of squared error values
1 n SST , is the total sum of squares
MAE = |yi,pred − yi | (4)
n i=1 yi,pred , is the ith value predicted by the model
J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254 249
Fig. 5. The top plots represent the Arturo Soria data and the bottom plots represent the Arganda del Rey data. Plots on the left side show a comparison between the “raw”
NO2 measurements from four PODs. Mean concentration values and standard deviations calculated from the POD data and are shown in the plots on the right side.
yi , is the reference ith value The MLR model requirements were validated by diagnosing the
ȳ, is the global mean of the reference data residuals from the first step of the regression procedure (see Fig. 2
n, is the size of the sample for a representative example).
This procedure gave a preliminary insight on the model perfor- The residuals vs. fitted values plot clearly showed constant vari-
mance. Other authors [24] split the dataset into train, validation ance, indicating homoscedasticity. The histograms of the residuals
and test sets for a more accurate evaluation. Our dataset is small resembled normal distributions. We concluded that the data was
to proceed in the same manner. This issue is overcame with the independent and identically distributed. In this way, the MLR mod-
application of the k-fold cross-validation method to the final mod- els were validated.
els. This method consists of splitting the dataset into k folds. Then, In line with AQD guidelines, the relative expanded uncertainty
all but one of them is used for training and the other as test data. The was calculated and plotted vs. the NO2 concentration. The thresh-
models are fitted with this configuration for all the possible com- olds for the relative expanded uncertainty for NO2 are 15% for the
binations among training and testing datasets. Using this method reference and 25% for the indicative methods. This plot served as
allows to calculate RMSE and r2 for k models along with their stan- an indication of the validity of the different models under the con-
dard deviation. dition of a real atmosphere. The following equations were used in
Furthermore, we performed a grid search to find the best hyper- these calculations [39]:
parameters by using the R caret package [38]. This procedure
RSS 2
changes the values of selected hyperparameters and runs the model 2 (n−2)
− u2 (xi ) + [b0 + (b1 − 1) xi ]
for each one of them to compare the response and to identify the Ur (yi ) = (6)
yi
value that yields an optimal error metric (the lowest RMSE in this
case). We only found significant improvements regarding hyperpa- 2
RSS = (yi − bo − b1 xi ) (7)
rameters discussed in Section 2.3. The remaining hyperparameters
were set to the default values. Ur , is the relative expanded uncertainty.
250 J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254
Table 1
Errors of the linear regression between “raw” and reference data.
Arturo Soria Arganda del Rey Arturo Soria Arganda del Rey Arturo Soria Arganda del Rey Arturo Soria Arganda del Rey
Table 2
The r2 of the linear regression between “raw” and reference data sorted according to type of pollutant.
POD NO2 O3 NO
Arturo Soria Arganda del Rey Arturo Soria Arganda del Rey Arturo Soria Arganda del Rey
Fig. 7. AQmesh NO2 measures vs. AQS for “raw” data and different models. Bands of 95% confidence are seen in blue. The bands of prediction are depicted with red lines.
POD1 is used as the representative example. From this plot, we can see that the bands of the intervals of “raw” data were already greatly reduced when the primary MLR
model was applied. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
Table 3 prediction intervals (Fig. 7). As shown in Fig. 7, MLR, SVM, RF and
Representative MLR regression summary. Results from the analysis of POD1 data
ANN seemed to improve the predictions, since the confidence and
are shown.
prediction intervals become narrower in comparison to the “raw”
Parameter Estimate Std. Error t value Pr (>|t|) data. However, some variability was observed: the slopes and the
a 11.5426675 1.47 7.85 7.97 10−14 dispersion of the data points differed from one method to another.
b 0.72700464 0.03 22.75 <2.22 10−17 Due to the variability, further analysis will be needed in order to
c 0.09725934 0.01 9.21 <2.22 10−17 confirm the validity of these models.
d −0.43709431 0.04 −11.90 <2.22 10−17
The error in the predictions decreased in proportion to the
e 1.54167776 0.09 16.44 <2.22 10−17
sophistication of regression methods (Table 4). Thus, the coeffi-
cient of determination r2 improved with respect to the original MLR
model. To further evaluate our models accuracy, k-Fold cross val-
(Table 3), and we decided to keep it in the model to allow consider-
idation method was used and its results are shown in (Table 5)
ing its effect over measured NO2 concentration under a wider range
using four folds. Consistent low RMSE, high r2 values point out the
of values (future campaigns over different seasons of the year). The
robustness of our validation approach.
p-values for all the other variables showed statistical significance
To have a better picture of the accuracy of the statistical models,
so they were included in the MLR model. The following MLR model
Taylor Diagrams for each POD were obtained (see Fig. 8).
was then used:
In the case of POD1, the SVM model performed well because
NO2,predicted = a + bNO2 + cNO + dO3 + eT its variability in terms of standard deviation was similar to the
variability of observed data (Fig. 8). The r2 and RMSE values were
Where a, b, c, d and e are the model coefficients. comparable in all the models. However, the RF model offered the
In fact, all the coefficients, as well as the overall model, were highest r2 and the lowest centred RMSE of all the models. The vari-
statistically significant at a 95% confidence level, as determined by ance of the RF model was low in comparison to the observed data.
t-tests and F-test, respectively (Table 3). In the case of POD2, the RF and SVM models performed better than
As part of the regression procedure, the diff variable was com- the ANN and MLR models. For POD 3, a pattern similar to POD1
puted. SVM, RF and ANN models were fitted using this variable emerged, but this time ANN performed slightly better than SVM.
and the same inputs of the MLR. Predicted versus observed values In the case of POD 4, SVM and RF again gave the highest r2 and
from all four methods were plotted along with 95% confidence and the lowest centred RMSE, but the RF model showed less variance
252 J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254
Table 4
Statistics of error calculated for each of the four PODs and the test set, sorted according to model (MLR, RF, SVM, and ANN).
than the observed data. The variation in the results means that a
model should be chosen for each specific sensor model and condi-
tion under which the sensor is used.
According to the analysis of relative expanded uncertainties
(Fig. 9), the uncertainty varied according to the concentrations
measured. In the case of POD1, POD2 and POD3, the RF model
resulted in the least uncertainty at concentrations below about
40 g/m3 . Above that concentration, ANNs and SVMs had lower
uncertainty, with the exception of the ANN model construction for
POD2. When taking into account the full range of concentrations,
the RF model was considered best for POD4. At above 40 g/m3 and
with the correct choice of model, the uncertainty of AQmesh PODs
was below 25%. These results demonstrate that AQmesh PODs are
valid for use as indicators.
4. Conclusions
Fig. 9. Relative expanded uncertainties in percent for each POD with respect to each calibration method. The horizontal red line shows the limit of 25% for the indicative
methods. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
the PODs at concentrations higher than 40 g/m3 , but RFs per- Acknowledgements
formed better below this threshold. In this study, AQmesh PODs
were shown to be useful indicators at high concentrations because This work has been partially funded by the European LIFE
their relative expanded uncertainties were below 25%. PHOTOSCALING project entitled “Sustainability of photocatalytic
From our results, we cannot propose a specific model to be gen- technologies on urban pavements: from laboratory tests to in field
erally used for future applications. Instead, we created base R-code compliance criteria (LIFE13 ENV/ES/001221)”. This work was a joint
for a two-stage calibration procedure to automatically select the research effort in collaboration with the TECNAIRE-CM (innova-
best model for each sensor. This approach allows obtaining the tive technologies for the assessment and improvement of urban
most accurate results and even meet the AQD guidelines regarding air quality) scientific programme funded by the Directorate Gen-
maximum uncertainty for indicative measurements. Consequently, eral for Universities and Research of the Greater Madrid Region
we deem AQmesh sensors suitable to estimate photocatalytic (S2013/MAE-2972). We thank the General Directorate of Sus-
efficiencies within the LIFE-PHOTOSCALING Project. Nonetheless, tainability (Madrid City Council) and the General Directorate of
further research is needed to gain a better understanding of the Environment (Madrid Greater Region) for granting us access to the
performance of the methodology presented under a wider range air quality monitoring stations and corresponding data used for cal-
of conditions and thus, its applicability for other urban air quality- ibration purposes in this study. We also want to thank Envirodata
related applications. for lending us one of the PODs used in this work.
254 J.M. Cordero et al. / Sensors and Actuators B 267 (2018) 245–254
Appendix A. Supplementary data [22] S. De Vito, E. Esposito, M. Salvato, O. Popoola, F. Formisano, R. Jones, G. Di
Francia, Chemical calibrating chemical multisensory devices for real world
applications: an in-depth comparison of quantitative machine learning
Supplementary data associated with this article can be found, in approaches, Sens. Actuators B Chem. 255 (2018) 1191–1210, http://dx.doi.
the online version, at https://doi.org/10.1016/j.snb.2018.04.021. org/10.1016/j.snb.2017.07.155.
[23] G. Huyberechts, P. Szeco, Simultaneous quantification of carbon monoxide
and methane in humid air using a sensor array and an artificial neural
References network, Sens. Actuator B-Chem. 45 (1997) 123–130.
[24] E. Esposito, S. De Vito, M. Salvato, V. Bright, R.L. Jones, O. Popoola, Dynamic
[1] World Health Organization, Ambient Air Pollution: A global assessment of neural network architectures for on field stochastic calibration of indicative
exposure and burden of disease, 2016, pp. 1–131 (9789241511353). low cost air quality sensing systems, Sens. Actuators B Chem. 231 (2016)
[2] C. Guerreiro, A. Gonzalez Ortiz, F. de Leeuw, M. Viana, J. Horalek, Air quality in 701–713, http://dx.doi.org/10.1016/j.snb.2016.03.038.
Europe — 2016 report, 2016, http://dx.doi.org/10.2800/413142. [25] K. Brudzewski, Gas analysis system composed of a solid-state sensor array
[3] Directive 2008/50/EC of the European Parliament and of the Council of 21 and hybrid neural network structure, Sens. Actuators B 55 (1999) 38–46,
May 2008 on ambient air quality and cleaner air for Europe, 2008. http://dx.doi.org/10.1016/S0925-4005(99)00040-4.
[4] LIFE-MINOx STREET, (n.d.). http://www.lifeminoxstreet.com/life/inicio/. [26] A.C. Lewis, J.D. Lee, P.M. Edwards, M.D. Shaw, M.J. Evans, S.J. Moller, K.R.
[5] LIFE-EQUINOX, (n.d.). http://life-equinox.eu/. Smith, J.W. Buckley, M. Ellis, S.R. Gillot, A. White, Evaluating the performance
[6] LIFE-DIGITALIFE, (n.d.). http://digitalife.active-ceramic.com/. of low cost chemical sensors for air pollution research, Faraday Discuss. 189
[7] LIFE-PHOTOCITYTEX, (n.d.). http://www.ceam.es/PHOTOCITYTEX/home.htm. (2016) 85–103, http://dx.doi.org/10.1039/c5fd00201j.
[8] J.L. Santiago, R. Borge, F. Martin, D. de la Paz, A. Martilli, J. Lumbreras, B. [27] LIFE-PHOTOSCALING. http://www.life-photoscaling.eu.
Sanchez, Evaluation of a CFD-based approach to estimate pollutant [28] Alphasense. http://www.alphasense.com/.
distribution within a real urban canopy by means of passive samplers, Sci. [29] AQmesh. http://www.aqmesh.com/.
Total Environ. 576 (2017) 46–58, http://dx.doi.org/10.1016/j.scitotenv.2016. [30] CRAN. https://cran.r-project.org/.
09.234. [31] Rstudio. https://www.rstudio.com/.
[9] AIRSENSEUR. http://www.airsenseur.org/website/. [32] S. Fritsch, F. Guenther, Neuralnet: Training of Neural Networks, 2016
[10] A. Kotsev, S. Schade, M. Craglia, M. Gerboles, L. Spinelle, M. Signorini, Next (https://cran.r-project.org/package=neuralnet).
generation air quality platform: openness and interoperability for the [33] M. Riedmiller, Advanced supervised learning in multi-layer perceptrons —
internet of things, Sensors (Switzerland) 16 (2016) 1–16, http://dx.doi.org/10. from backpropagation to adaptive learning algorithms, Comput. Stand.
3390/s16030403. Interfaces 16 (1994) 265–278, http://dx.doi.org/10.1016/0920-
[11] D. Hasenfratz, O. Saukh, S. Sturzenegger, L. Thiele, Participatory air pollution 5489(94)90017-5.
monitoring using smartphones, in: 2nd Int. Work. Mob. Sens., 2012, pp. 1–5 [34] D. Meyer, E. Dimitriadou, K. Hornik, A. Weingessel, F. Leisch, Misc Functions of
(//ftp.tik.ee.ethz.ch/pub/people/hdavid/HSST2012.pdf). the Department of Statistics, Probability Theory Group (Formerly: E1071), TU
[12] G. Miskell, J.A. Salmond, D.E. Williams, Use of a handheld low-cost sensor to Wien, 2017, pp. e1071 (https://cran.r-project.org/package=e1071).
explore the effect of urban design features on local-scale spatial and temporal [35] H. Drucker, C.J.C. Burges, L. Kaufman, A. Smola, V. Vapnik, Support vector
air quality variability, Sci. Total Environ. 619 (2018) 480–490, http://dx.doi. regression machines, in: M.C. Mozer, M.I. Jordan, T. Petsche (Eds.), Adv.
org/10.1016/j.scitotenv.2017.11.024. NEURAL Inf. Process. Syst. 9 Proc. 1996 Conf., MIT Press, Five Cambridge
[13] L. Spinelle, M. Gerboles, M.G. Villani, M. Aleixandre, F. Bonavitacola, Field Center, Cambridge, MA 02142, 1997, pp. 155–161.
calibration of a cluster of low-cost available sensors for air quality [36] A. Liaw, M. Wiener, Classification and Regression by random Forest, 2002
monitoring. Part A: Ozone and nitrogen dioxide, Sens. Actuators, B Chem. 215 (http://cran.r-project.org/doc/Rnews).
(2015) 249–257, http://dx.doi.org/10.1016/j.snb.2015.03.031. [37] L. Breiman, Random forests, Mach. Learn. 45 (2001) 5–32, http://dx.doi.org/
[14] R. Baron, J. Saffell, Amperometric gas sensors as a low cost emerging 10.1023/A:1010933404324.
technology platform for air quality monitoring applications: a review, ACS [38] M. Kuhn, Caret: Classification and Regression Training, 2017 (https://cran.r-
Sens. 2 (2017) 1553–1566, http://dx.doi.org/10.1021/acssensors.7b00620. project.org/package=caret).
[15] N. Castell, F.R. Dauge, P. Schneider, M. Vogt, U. Lerner, B. Fishbain, D. Broday, [39] EC working group, Guide To The Demonstration Of Equivalence Of Ambient
A. Bartonova, Can commercial low-cost sensor platforms contribute to air Air Monitoring Methods, 2010.
quality monitoring and exposure estimates? Environ. Int. 99 (2017) 293–302,
http://dx.doi.org/10.1016/j.envint.2016.12.007.
[16] M.C. Carotta, G. Martinelli, L. Crema, M. Gallana, M. Merli, G. Ghiotti, E. Biographies
Traversa, Array of thick film sensors for atmospheric pollutant monitoring,
Sens. Actuators B Chem. 68 (2000) 1–8, http://dx.doi.org/10.1016/S0925-
4005(00)00439-1. Dr José María Cordero is a PhD researcher in the Department of Chemical and Envi-
[17] C. Borrego, A.M. Costa, J. Ginja, M. Amorim, M. Coutinho, K. Karatzas, T. ronmental Engineering at the Technical University of Madrid (UPM). He completed
Sioumis, N. Katsifarakis, K. Konstantinidis, S. De Vito, E. Esposito, P. Smith, his doctorate in the INCAR-CSIC, Spain, studying the sulphation kinetics and capaci-
P.G.N. Andr, W. Reimringer, R.P. Otjes, O. Von Sicard, R. Pohle, B. Elen, ties of CaO in Calcium Looping reactors to capture CO2 . He is currently investigating
Assessment of air quality microsensors versus reference methods: the the sustainable use of photocatalytic pavements for NO2 mitigation in the City of
EuNetAir joint exercise, Atmos. Environ. 147 (2016) 246–263, http://dx.doi. Madrid.
org/10.1016/j.atmosenv.2016.09.050.
Dr Rafael Borge is an Associate Professor in the Department of Chemical and
[18] N. Masson, R. Piedrahita, M. Hannigan, Approach for quantification of metal
Environmental Engineering at the Technical University of Madrid (UPM). He has
oxide type semiconductor gas sensors used for ambient air quality
extensive experience on air quality modelling and air quality management. He
monitoring, Sens. Actuators B. Chem. 208 (2015) 339–345, http://dx.doi.org/
currently leads the Laboratory of Environmental Modelling and coordinates the
10.1016/j.snb.2014.11.032.
TECNAIRE-CM research project that aims at the development and integration of
[19] M. Kamionka, P. Breuil, C. Pijolat, Calibration of a multivariate gas sensing
new technologies and methods for multiscale modelling and measuring of urban air
device for atmospheric pollution measurement, Sens. Actuators B Chem. 118
pollution.
(2006) 323–327, http://dx.doi.org/10.1016/j.snb.2006.04.058.
[20] JRC Technical report, Protocol of evaluation and calibration of low-cost gas Dr Adolfo Narros is an Associate Professor in the Department of Chemical and Envi-
sensors for the monitoring of air pollution, 2013. doi: 10.2788/9916. ronmental Engineering at the Technical University of Madrid (UPM). His expertise is
[21] L. Spinelle, M. Gerboles, M.G. Villani, M. Aleixandre, F. Bonavitacola, Field in chemical analysis of air pollutants and in the use of sensors in the measurement
calibration of a cluster of low-cost commercially available sensors for air of the air quality.
quality monitoring. Part B: NO, CO and CO2 , Sens. Actuators B Chem. 238
(2017) 706–715, http://dx.doi.org/10.1016/j.snb.2016.07.036.