This page has only limited features, please log in for full access.

Dr. Álvaro Gómez-Losada
Departamento de Estadística e Investigación Operativa, Facultad de Matemáticas, Universidad de Sevilla, Sevilla (España).

Basic Info


Research Keywords & Expertise

0 Air Pollution
0 Machine Learning
0 Environmental data science
0 Knowledge discovery from databases
0 Spatial and temporal forecasting

Fingerprints

Air Pollution
Machine Learning

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

Alvaro is Data scientist at the Energy, Transport and Climate Directorate of the Joint Research Centre, the in-house science service of the European Commission. He is specialized in the design, implementation and evaluation of machine learning algorithms. Educational background includes PhD, MSc and BSc in Statistics (University of Seville, Spain) and MSc and BSc in Biology (University of Córdoba). Previous experience as Data scientist in the Innovation Department of Banco Santander (Madrid). Conducted research for doctoral thesis while balancing a full-time position at the Data Centre in the Environment and Water Agency of Andalusia (Seville). Since 2020, he is lecturer in the Statistics and Operative Research Department at the University of Seville.

Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 23 December 2020 in Atmosphere
Reads 0
Downloads 0

North African dust intrusions can contribute to exceedances of the European PM10 and PM2.5 limit values and World Health Organisation standards, diminishing air quality, and increased mortality and morbidity at higher concentrations. In this study, the contribution of North African dust in Mediterranean countries was estimated using the time series clustering method. This method combines the non-parametric approach of Hidden Markov Models for studying time series, and the definition of different air pollution profiles (regimes of concentration). Using this approach, PM10 and PM2.5 time series obtained at background monitoring stations from seven countries were analysed from 2015 to 2018. The average characteristic contributions to PM10 were estimated as 11.6 ± 10.3 µg·m−3 (Bosnia and Herzegovina), 8.8 ± 7.5 µg·m−3 (Spain), 7.0 ± 6.2 µg·m−3 (France), 8.1 ± 5.9 µg·m−3 (Croatia), 7.5 ± 5.5 µg·m−3 (Italy), 8.1 ± 7.0 µg·m−3 (Portugal), and 17.0 ± 9.8 µg·m−3 (Turkey). For PM2.5, estimated contributions were 4.1 ± 3.5 µg·m−3 (Spain), 6.0 ± 4.8 µg·m−3 (France), 9.1 ± 6.4 µg·m−3 (Croatia), 5.2 ± 3.8 µg·m−3 (Italy), 6.0 ± 4.4 µg·m−3 (Portugal), and 9.0 ± 5.6 µg·m−3 (Turkey). The observed PM2.5/PM10 ratios were between 0.36 and 0.69, and their seasonal variation was characterised, presenting higher values in colder months. Principal component analysis enabled the association of background sites based on their estimated PM10 and PM2.5 pollution profiles.

ACS Style

Álvaro Gómez-Losada; José Pires. Estimation of Particulate Matter Contributions from Desert Outbreaks in Mediterranean Countries (2015–2018) Using the Time Series Clustering Method. Atmosphere 2020, 12, 5 .

AMA Style

Álvaro Gómez-Losada, José Pires. Estimation of Particulate Matter Contributions from Desert Outbreaks in Mediterranean Countries (2015–2018) Using the Time Series Clustering Method. Atmosphere. 2020; 12 (1):5.

Chicago/Turabian Style

Álvaro Gómez-Losada; José Pires. 2020. "Estimation of Particulate Matter Contributions from Desert Outbreaks in Mediterranean Countries (2015–2018) Using the Time Series Clustering Method." Atmosphere 12, no. 1: 5.

Journal article
Published: 23 August 2020 in Atmospheric Environment
Reads 0
Downloads 0

The estimation of the background atmospheric concentration allows to assess local contributions and helping to the design of air quality improvement policies. Using clustering techniques and bivariate analysis, this study aims to characterize the background concentration of PM10 (particulate matter with an aerodynamic diameter less than or equal to 10 μm) and PM2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) in environments with heterogeneous emission sources. Background PM10 and PM2.5 pollution was characterized using Hidden Markov and Finite Mixture Models in four air quality monitoring stations, from 2011 to 2017. Average background concentrations in all stations were of 12.7 ± 2.2 μg m-3 for PM10 and 4.6 ± 0.4 μg m-3 for PM2.5. The contribution of background concentration to ambient pollution (both PM10 and PM2.5) was high (more than 40%) in all studied stations, being a 10% higher in background stations (Camping Temisas and Parque de San Juan) compared with stations influenced by an anthropogenic source (Castillo Romeral and San Agustín). Estimated background concentration showed significant differences among studied areas according to Kruskal-Wallis test (p < 0.001) and coefficients of divergence, which were greater than 0.2. PM10 and PM2.5 monthly profiles (concentration level) showed that the traffic urban station presented seasonality, probably due to the summer tourism, and daily profiles exhibited a differentiated bimodal distribution. The estimation of background concentrations in this study will allow to quantify local contributions from Saharan outbreaks and to study its possible effects on human health and marine biota.

ACS Style

Yumara Martín-Cruz; Antonio Vera-Castellano; Álvaro Gómez-Losada. Characterization of background particulate matter concentrations using the combination of two clustering techniques in zones with heterogeneous emission sources. Atmospheric Environment 2020, 243, 117832 .

AMA Style

Yumara Martín-Cruz, Antonio Vera-Castellano, Álvaro Gómez-Losada. Characterization of background particulate matter concentrations using the combination of two clustering techniques in zones with heterogeneous emission sources. Atmospheric Environment. 2020; 243 ():117832.

Chicago/Turabian Style

Yumara Martín-Cruz; Antonio Vera-Castellano; Álvaro Gómez-Losada. 2020. "Characterization of background particulate matter concentrations using the combination of two clustering techniques in zones with heterogeneous emission sources." Atmospheric Environment 243, no. : 117832.

Conference paper
Published: 17 December 2019 in Business Information Systems
Reads 0
Downloads 0

A key feature of the Amazon marketplace is that multiple sellers can sell the same product. In such cases, Amazon recommends one of the sellers to customers in the so-called ‘buy-box’. In this study, the dynamics among sellers for occupying the buy-box was modelled using a classification approach. Italy’s Amazon webpage was crawled during ten months and features from products analyzed to estimate the more relevant ones Amazon could consider for a seller occupy the buy-box. Predictive models showed that the more relevant features are the ratio between consecutive prices in products and their number of assessment received by customers.

ACS Style

Álvaro Gómez-Losada; Néstor Duch-Brown. Competing for Amazon’s Buy Box: A Machine-Learning Approach. Business Information Systems 2019, 445 -456.

AMA Style

Álvaro Gómez-Losada, Néstor Duch-Brown. Competing for Amazon’s Buy Box: A Machine-Learning Approach. Business Information Systems. 2019; ():445-456.

Chicago/Turabian Style

Álvaro Gómez-Losada; Néstor Duch-Brown. 2019. "Competing for Amazon’s Buy Box: A Machine-Learning Approach." Business Information Systems , no. : 445-456.

Journal article
Published: 08 November 2019 in Social Sciences
Reads 0
Downloads 0

Social Network Analysis can be applied to describe the patterns of communication within an organisation. We explore how extending standard methods, by accounting for the direction and volume of emails, can reveal information regarding the roles of individual members. We propose an approach that models certain operational aspects of the organization, based on directional and weighted indicators. The approach is transferable to other types of social network with asymmetrical connections among its members. However, its applicability is limited by privacy concerns, the existence of multiple alternative communication channels that evolve over time, the difficulty of establishing clear links between organisational structure and efficiency and, most importantly, the challenge of setting up a system that measures the impact of communication behavior without influencing the communication behaviour itself.

ACS Style

Panayotis Christidis; Álvaro Gomez Losada. Email Based Institutional Network Analysis: Applications and Risks. Social Sciences 2019, 8, 306 .

AMA Style

Panayotis Christidis, Álvaro Gomez Losada. Email Based Institutional Network Analysis: Applications and Risks. Social Sciences. 2019; 8 (11):306.

Chicago/Turabian Style

Panayotis Christidis; Álvaro Gomez Losada. 2019. "Email Based Institutional Network Analysis: Applications and Risks." Social Sciences 8, no. 11: 306.

Journal article
Published: 24 August 2019 in Atmospheric Research
Reads 0
Downloads 0

The background PM2.5 concentration represents the combined emissions from natural domestic and foreign sources, which has implications for the maximum effect, in terms of air-quality control, that can be achieved by reducing emissions. However, estimating the background PM2.5 concentration via background monitoring sites for a densely populated region (e.g., Taiwan) has been a challenge. In this study, we compared two statistical methods of estimating the background concentration using an 11-year time series (2005–2016) of data from three air-quality stations in Taiwan. The results of two methods showed good agreement for the background PM2.5 concentration estimation, which was about 4.4 μg m−3 and comparable to literature reports. According to the trend analysis, the concentration has decreased at a rate of 1–2 μg m−3 decade−1 as a result of better emissions control in East Asia in recent years. Furthermore, the local concentration can exceed the regional background value by up to 5 times due to local emissions, topographic effects, and weather regimes. When considering the cross-county transport of PM2.5, a difference as high as 5 μg m−3 exists between two prevailing-wind scenarios. This study provides crucial information to policy-makers on setting an achievable and reasonable goal for PM2.5 reduction.

ACS Style

Sheng-Hsiang Wang; Ruo-Ya Hung; Neng-Huei Lin; Álvaro Gómez-Losada; José C.M. Pires; Kojiro Shimada; Shiro Hatakeyama; Akinori Takami. Estimation of background PM2.5 concentrations for an air-polluted environment. Atmospheric Research 2019, 231, 104636 .

AMA Style

Sheng-Hsiang Wang, Ruo-Ya Hung, Neng-Huei Lin, Álvaro Gómez-Losada, José C.M. Pires, Kojiro Shimada, Shiro Hatakeyama, Akinori Takami. Estimation of background PM2.5 concentrations for an air-polluted environment. Atmospheric Research. 2019; 231 ():104636.

Chicago/Turabian Style

Sheng-Hsiang Wang; Ruo-Ya Hung; Neng-Huei Lin; Álvaro Gómez-Losada; José C.M. Pires; Kojiro Shimada; Shiro Hatakeyama; Akinori Takami. 2019. "Estimation of background PM2.5 concentrations for an air-polluted environment." Atmospheric Research 231, no. : 104636.

Conference paper
Published: 18 May 2019 in Business Information Systems
Reads 0
Downloads 0

This study proposes a forecasting methodology for univariate time series (TS) using a Recommender System (RS). The RS is built from a given TS as only input data and following an item-based Collaborative Filtering approach. A set of top-N values is recommended for this TS which represent the forecasts. The idea is to emulate RS elements (the users, items and ratings triple) from the TS. Two TS obtained from Italy’s Amazon webpage were used to evaluate this methodology and very promising performance results were obtained, even the difficult environment chosen to conduct forecasting (short length and unevenly spaced TS). This performance is dependent on the similarity measure used and suffers from the same problems that other RSs (e.g., cold-start). However, this approach does not require high computational power to perform and its intuitive conception allows for being deployed with any programming language.

ACS Style

Álvaro Gómez-Losada; Néstor Duch-Brown. Time Series Forecasting by Recommendation: An Empirical Analysis on Amazon Marketplace. Business Information Systems 2019, 45 -54.

AMA Style

Álvaro Gómez-Losada, Néstor Duch-Brown. Time Series Forecasting by Recommendation: An Empirical Analysis on Amazon Marketplace. Business Information Systems. 2019; ():45-54.

Chicago/Turabian Style

Álvaro Gómez-Losada; Néstor Duch-Brown. 2019. "Time Series Forecasting by Recommendation: An Empirical Analysis on Amazon Marketplace." Business Information Systems , no. : 45-54.

Journal article
Published: 24 December 2018 in Computers, Environment and Urban Systems
Reads 0
Downloads 0

Model developments to assess different air pollution exposures within cities are still a key challenge in environmental epidemiology. Background air pollution is a long-term resident and low-level concentration pollution difficult to quantify, and to which population is chronically exposed. In this study, hourly time series of four key air pollutants were analysed using Hidden Markov Models to estimate the exposure to background pollution in Madrid, from 2001 to 2017. Using these estimates, its spatial distribution was later analysed after combining the interpolation results of ordinary kriging and inverse distance weighting. The ratio of ambient to background pollution differs according to the pollutant studied but is estimated to be on average about six to one. This methodology is proposed not only to describe the temporal and spatial variability of this complex exposure, but also to be used as input in new modelling approaches of air pollution in urban areas.

ACS Style

Álvaro Gómez-Losada; Francisca M. Santos; Karina Gibert; José C.M. Pires. A data science approach for spatiotemporal modelling of low and resident air pollution in Madrid (Spain): Implications for epidemiological studies. Computers, Environment and Urban Systems 2018, 75, 1 -11.

AMA Style

Álvaro Gómez-Losada, Francisca M. Santos, Karina Gibert, José C.M. Pires. A data science approach for spatiotemporal modelling of low and resident air pollution in Madrid (Spain): Implications for epidemiological studies. Computers, Environment and Urban Systems. 2018; 75 ():1-11.

Chicago/Turabian Style

Álvaro Gómez-Losada; Francisca M. Santos; Karina Gibert; José C.M. Pires. 2018. "A data science approach for spatiotemporal modelling of low and resident air pollution in Madrid (Spain): Implications for epidemiological studies." Computers, Environment and Urban Systems 75, no. : 1-11.

Journal article
Published: 16 November 2018 in Journal of Hazardous Materials
Reads 0
Downloads 0

Air pollution is an increasing concern due to the negative impacts on human health, environment, and patrimony. The implementation of a Low Emission Zone (LEZ) is an important air quality policy action to reduce air pollutant emissions. This study aims to assess the air quality improvements in Lisbon with the LEZ implementation, analysing its impact on the air pollutant concentrations. The analysis performed from 2009 to 2016 showed an improvement in air quality. In the Zone 1, the reduction of PM10 and NO2 annual average concentrations were 29% and 12%, respectively, while, in the Zone 2, the reduction of PM10 and NO2 annual average concentrations were 23% and 22%, respectively. The background pollution analysis showed the LEZ effect on the lowest levels of ambient air pollution to which the population is chronically exposed. The achieved reductions of PM10 and NO2 levels were 30.5% and 9.4% in Zone 1, and 22.5% and 12.9% in the Zone 2, respectively. Concluding, this study evidenced an air quality improvement mainly for PM10 and NO2; however, insignificant reductions were observed for NOx and PM2.5. Therefore, stricter restriction standards should be defined, combining with other air quality policy decisions to reduce the population exposure to air pollutants.

ACS Style

Francisca M. Santos; Álvaro Gómez-Losada; José C.M. Pires. Impact of the implementation of Lisbon low emission zone on air quality. Journal of Hazardous Materials 2018, 365, 632 -641.

AMA Style

Francisca M. Santos, Álvaro Gómez-Losada, José C.M. Pires. Impact of the implementation of Lisbon low emission zone on air quality. Journal of Hazardous Materials. 2018; 365 ():632-641.

Chicago/Turabian Style

Francisca M. Santos; Álvaro Gómez-Losada; José C.M. Pires. 2018. "Impact of the implementation of Lisbon low emission zone on air quality." Journal of Hazardous Materials 365, no. : 632-641.

Journal article
Published: 01 November 2018 in Atmospheric Pollution Research
Reads 0
Downloads 0
ACS Style

Álvaro Gómez-Losada. Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information. Atmospheric Pollution Research 2018, 9, 1052 -1061.

AMA Style

Álvaro Gómez-Losada. Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information. Atmospheric Pollution Research. 2018; 9 (6):1052-1061.

Chicago/Turabian Style

Álvaro Gómez-Losada. 2018. "Forecasting ozone threshold exceedances in urban background areas using supervised classification and easy-access information." Atmospheric Pollution Research 9, no. 6: 1052-1061.

Journal article
Published: 20 August 2018 in Environmental Modelling & Software
Reads 0
Downloads 0

Surface ozone (O3) is considered an hazard to human health, affecting vegetation crops and ecosystems. Accurate time and location O3 forecasting can help to protect citizens to unhealthy exposures when high levels are expected. Usually, forecasting models use numerous O3 precursors as predictors, limiting the reproducibility of these models to the availability of such information from data providers. This study introduces a 24 h-ahead hourly O3 concentrations forecasting methodology based on bagging and ensemble learning, using just two predictors with lagged O3 concentrations. This methodology was applied on ten-year time series (2006–2015) from three major urban areas of Andalusia (Spain). Its forecasting performance was contrasted with an algorithm especially designed to forecast time series exhibiting temporal patterns. The proposed methodology outperforms the contrast algorithm and yields comparable results to others existing in literature. Its use is encouraged due to its forecasting performance and wide applicability, but also as benchmark methodology.

ACS Style

Álvaro Gómez-Losada; G. Asencio–Cortés; Francisco Martínez-Álvarez; J.C. Riquelme. A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information. Environmental Modelling & Software 2018, 110, 52 -61.

AMA Style

Álvaro Gómez-Losada, G. Asencio–Cortés, Francisco Martínez-Álvarez, J.C. Riquelme. A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information. Environmental Modelling & Software. 2018; 110 ():52-61.

Chicago/Turabian Style

Álvaro Gómez-Losada; G. Asencio–Cortés; Francisco Martínez-Álvarez; J.C. Riquelme. 2018. "A novel approach to forecast urban surface-level ozone considering heterogeneous locations and limited information." Environmental Modelling & Software 110, no. : 52-61.

Journal article
Published: 26 February 2018 in Environmental Modelling & Software
Reads 0
Downloads 0

Background pollution represents the lowest levels of ambient air pollution to which the population is chronically exposed, but few studies have focused on thoroughly characterizing this regime. This study uses clustering statistical techniques as a modelling approach to characterize this pollution regime while deriving reliable information to be used as estimates of exposure in epidemiological studies. The background levels of four key pollutants in five urban areas of Andalusia (Spain) were characterized over an 11-year period (2005–2015) using four widely-known clustering methods. For each pollutant data set, the first (lowest) cluster representative of the background regime was studied using finite mixture models, agglomerative hierarchical clustering, hidden Markov models (hmm) and k-means. Clustering method hmm outperforms the rest of the techniques used, providing important estimates of exposures related to background pollution as its mean, acuteness and time incidence values in the ambient air for all the air pollutants and sites studied.

ACS Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. Modelling background air pollution exposure in urban environments: Implications for epidemiological research. Environmental Modelling & Software 2018, 106, 13 -21.

AMA Style

Álvaro Gómez-Losada, José Carlos M. Pires, Rafael Pino-Mejías. Modelling background air pollution exposure in urban environments: Implications for epidemiological research. Environmental Modelling & Software. 2018; 106 ():13-21.

Chicago/Turabian Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. 2018. "Modelling background air pollution exposure in urban environments: Implications for epidemiological research." Environmental Modelling & Software 106, no. : 13-21.

Conference paper
Published: 05 July 2017 in Data Science
Reads 0
Downloads 0

In order to study the cluster of monitoring sites from an urban air quality monitoring network (AQMN) with respect to the background and ambient pollution of key pollutants, a combined methodology is proposed: firstly, to obtain the ambient and background levels of air pollution from every selected pollutant, time series obtained from the AQMN were modeled with hidden Markov models; secondly, to study the grouping of these monitoring sites according to these levels of pollution, both ambient and background pollution, multidimensional scaling (Smacof MDS) was used and the stability of these solutions obtained with a Jacknife procedure (smacof library—R software). Results show that the clustering behaviour of sites is different when studying the ambient from the background pollution. However, sites marked with a distinct pollution contribution could locate them distant from the main cluster of sites as long as they show a marked stability in the MDS solutions.

ACS Style

Álvaro Gómez-Losada. Clustering Air Monitoring Stations According to Background and Ambient Pollution Using Hidden Markov Models and Multidimensional Scaling. Data Science 2017, 123 -132.

AMA Style

Álvaro Gómez-Losada. Clustering Air Monitoring Stations According to Background and Ambient Pollution Using Hidden Markov Models and Multidimensional Scaling. Data Science. 2017; ():123-132.

Chicago/Turabian Style

Álvaro Gómez-Losada. 2017. "Clustering Air Monitoring Stations According to Background and Ambient Pollution Using Hidden Markov Models and Multidimensional Scaling." Data Science , no. : 123-132.

Conference paper
Published: 15 July 2016 in Proceedings of The 1st International Electronic Conference on Atmospheric Sciences
Reads 0
Downloads 0

Exploratory analysis of time series (TS) data is an important approach in experimental studies, with a large range of applications in many different fields, including air pollution studies. To identify structures in single (univariate) TS, main clustering analyses are based on general-purpose clustering algorithms (e.g., k-means, hierarchical clustering methods) and made the assumption that the samples (data) of a TS are independent, ignoring the correlations in consecutive sample values in time. This is specially the case of air pollutant studies based on monitoring data. Air pollutants TS can be studied using TS clustering techniques and as a result, pollution profiles or concentration regimes detected as well as the dependency structure between consecutive data is preserved. Once TS clustering applied over the TS data stream, a set of clusters group the data according to their similar concentration values, and therefore, different pollution profiles can be defined and their estimated range of concentration values. Hidden Markov Models (HMMs) are flexible general-purpose models for univariate and multivariate TS. The TS data are assumed to have a Markov property, and may be viewed as the results of a probabilistic walk along a fixed set of (no directly observable) states. This class of approach considers that each TS is generated by a mixture of underlying probability distributions, typically the Gaussian ones. In this study, HMMs were applied to cluster daily average particulate matter with aerodynamic diameter of 10 μm or less (PM10) TS collected at background monitoring stations from the Iberian Peninsula and Canarian Archipelago (Spain). As a result, PM10 concentration regimes were studied and in particular, the contribution to PM10 ambient concentration levels from the regimes associated to transport of air masses from North Africa deserts was estimated. Regarding this last contribution, we later compared to those obtained using the monthly moving 40th percentile (P40) method over the same TS and no significant quantitative differences were detected. However, the results obtained with HMMs seem to correct the net load of PM10 given by the P40 method, and attributes less impact on areas suffering greater influence from African episodes. The method proposed in this work to estimate PM10 from deserts could improve the P40 method in two ways since it avoids: (i) the smoothed effect which is implicit in the P40 methods after applying a mobile procedure in the TS treatment; and (ii) the empirical approach based on a correlation analysis applied in order to select this particular percentile (40th). Moreover, the use of statistical replicative techniques (bootstrap) together with HMMs has let to obtain an interval confidence in the PM10 contribution estimates from North African deserts. This methodology may be used to estimate particulate matter contributions from any desert; however, a consensus among experts is required to give the regimes...

ACS Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. Time Series Clustering to Estimate Particulate Matter Contributions from Deserts. Proceedings of The 1st International Electronic Conference on Atmospheric Sciences 2016, 1 .

AMA Style

Álvaro Gómez-Losada, José Carlos M. Pires, Rafael Pino-Mejías. Time Series Clustering to Estimate Particulate Matter Contributions from Deserts. Proceedings of The 1st International Electronic Conference on Atmospheric Sciences. 2016; ():1.

Chicago/Turabian Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. 2016. "Time Series Clustering to Estimate Particulate Matter Contributions from Deserts." Proceedings of The 1st International Electronic Conference on Atmospheric Sciences , no. : 1.

Journal article
Published: 01 February 2016 in Atmospheric Environment
Reads 0
Downloads 0
ACS Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. Characterization of background air pollution exposure in urban environments using a metric based on Hidden Markov Models. Atmospheric Environment 2016, 127, 255 -261.

AMA Style

Álvaro Gómez-Losada, José Carlos M. Pires, Rafael Pino-Mejías. Characterization of background air pollution exposure in urban environments using a metric based on Hidden Markov Models. Atmospheric Environment. 2016; 127 ():255-261.

Chicago/Turabian Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. 2016. "Characterization of background air pollution exposure in urban environments using a metric based on Hidden Markov Models." Atmospheric Environment 127, no. : 255-261.

Journal article
Published: 01 September 2015 in Atmospheric Environment
Reads 0
Downloads 0
ACS Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. Time series clustering for estimating particulate matter contributions and its use in quantifying impacts from deserts. Atmospheric Environment 2015, 117, 271 -281.

AMA Style

Álvaro Gómez-Losada, José Carlos M. Pires, Rafael Pino-Mejías. Time series clustering for estimating particulate matter contributions and its use in quantifying impacts from deserts. Atmospheric Environment. 2015; 117 ():271-281.

Chicago/Turabian Style

Álvaro Gómez-Losada; José Carlos M. Pires; Rafael Pino-Mejías. 2015. "Time series clustering for estimating particulate matter contributions and its use in quantifying impacts from deserts." Atmospheric Environment 117, no. : 271-281.

Journal article
Published: 01 July 2014 in Science of The Total Environment
Reads 0
Downloads 0

Existing air quality monitoring programs are, on occasion, not updated according to local, varying conditions and as such the monitoring programs become non-informative over time, under-detecting new sources of pollutants or duplicating information. Furthermore, inadequate maintenance may cause the monitoring equipment to be utterly deficient in providing information. To deal with these issues, a combination of formal statistical methods is used to optimize resources for monitoring and to characterize the monitoring networks, introducing new criteria for their refinement. Monitoring data were obtained on key pollutants such as carbon monoxide (CO), nitrogen dioxide (NO2), ozone (O3), particulate matter (PM10) and sulfur dioxide (SO2) from 12 air quality monitoring sites in Seville (Spain) during 2012. A total of 49 data sets were fit to mixture models of Gaussian distribution using the expectation-maximization (EM) algorithm. To summarize these 49 models, the mean and coefficient of variation were calculated for each mixture and carried out a hierarchical clustering analysis (HCA) to study the grouping of the sites according to these statistics. To handle the lack of observational data from the sites with unmonitored pollutants, the missing statistical values were imputed by applying the random forests technique and then later, a principal component analysis (PCA) was carried out to better understand the relationship between the level of pollution and the classification of monitoring sites. All of the techniques were applied using free, open-source, statistical software. One example of source attribution and contribution is analyzed using mixture models and the potential for mixture models is posed in characterizing pollution trends. The mixture statistics have proven to be a fingerprint for every model and this work presents a novel use of them and represents a promising approach to characterizing mixture models in the air quality management discipline. The imputation technique used is allowed for estimating the missing information from key unmonitored pollutants to gather information about unknown pollution levels and to suggest new possible monitoring configurations for this network. Posterior PCA confirmed the misclassification of one site detected with HCA. The authors consider the stepwise approach used in this work to be promising and able to be applied to other air monitoring network studies.

ACS Style

Álvaro Gómez-Losada; Antonio Lozano-García; Rafael Pino Mejías; Juan Contreras-González. Finite mixture models to characterize and refine air quality monitoring networks. Science of The Total Environment 2014, 485-486, 292 -299.

AMA Style

Álvaro Gómez-Losada, Antonio Lozano-García, Rafael Pino Mejías, Juan Contreras-González. Finite mixture models to characterize and refine air quality monitoring networks. Science of The Total Environment. 2014; 485-486 ():292-299.

Chicago/Turabian Style

Álvaro Gómez-Losada; Antonio Lozano-García; Rafael Pino Mejías; Juan Contreras-González. 2014. "Finite mixture models to characterize and refine air quality monitoring networks." Science of The Total Environment 485-486, no. : 292-299.