Articles de revistahttp://hdl.handle.net/2117/33572024-03-29T02:15:12Z2024-03-29T02:15:12ZFrom the global to the subnational scale: landing the compositional monitoring of drinking water and sanitation servicesQuispe Coica, Filimon AlejandroPérez Foguet, Agustíhttp://hdl.handle.net/2117/3702272022-07-17T16:57:47Z2022-07-14T17:38:26ZFrom the global to the subnational scale: landing the compositional monitoring of drinking water and sanitation services
Quispe Coica, Filimon Alejandro; Pérez Foguet, Agustí
Monitoring of access to water and sanitation services is stipulated in Sustainable Development Goals (SDG) 6.1 and 6.2, respectively. The monitoring is carried out with a global, regional and country vision. However, in most developing countries, decentralization of services in water and sanitation management has tended to the sub-national level or has shared responsibilities between national and sub-national governments. Management at the subnational level becomes more important, since everything that is done there will impact the objectives and goals of the country. However, little or nothing progress has been made in harmonizing global indicators with those at the subnational level. Therefore, in this study we have proposed a way to disaggregate information and form WASH ladders at the subnational level. The results show using disaggregated data to interpolate models at the subnational level requires overcoming three main points: the validation of the data through statistical methods, interpolation techniques that go according to the compositional characteristics of the data and the incorporation of the uncertainty of the data into the model results. It also shows that subnational behavior is heterogeneous, which a general analysis does not capture correctly, i.e., there is a masking effect of subnational trends that the country's trend does not represent. However, these have been exceptional cases in some specific categories. Finally, the applicability of non-linear models is contrasted in a broader context, an issue that is still under discussion for its application to global monitoring. This study also provides a way to disaggregate information from the global to the sub-national level, allowing any sector analyst to replicate the methodology in a broader context.
2022-07-14T17:38:26ZQuispe Coica, Filimon AlejandroPérez Foguet, AgustíMonitoring of access to water and sanitation services is stipulated in Sustainable Development Goals (SDG) 6.1 and 6.2, respectively. The monitoring is carried out with a global, regional and country vision. However, in most developing countries, decentralization of services in water and sanitation management has tended to the sub-national level or has shared responsibilities between national and sub-national governments. Management at the subnational level becomes more important, since everything that is done there will impact the objectives and goals of the country. However, little or nothing progress has been made in harmonizing global indicators with those at the subnational level. Therefore, in this study we have proposed a way to disaggregate information and form WASH ladders at the subnational level. The results show using disaggregated data to interpolate models at the subnational level requires overcoming three main points: the validation of the data through statistical methods, interpolation techniques that go according to the compositional characteristics of the data and the incorporation of the uncertainty of the data into the model results. It also shows that subnational behavior is heterogeneous, which a general analysis does not capture correctly, i.e., there is a masking effect of subnational trends that the country's trend does not represent. However, these have been exceptional cases in some specific categories. Finally, the applicability of non-linear models is contrasted in a broader context, an issue that is still under discussion for its application to global monitoring. This study also provides a way to disaggregate information from the global to the sub-national level, allowing any sector analyst to replicate the methodology in a broader context.Spatially-structured human mortality modelling using air pollutants with a compositional approachSánchez Balseca, JosephPérez Foguet, Agustíhttp://hdl.handle.net/2117/3651302024-01-03T01:25:52Z2022-03-31T18:20:41ZSpatially-structured human mortality modelling using air pollutants with a compositional approach
Sánchez Balseca, Joseph; Pérez Foguet, Agustí
The human mortality models with a demographic approach are performed in function of time. The addition of information (social, economic, and environmental) in the structure of demographic models allows fitting observed values better. Air pollution influences human mortality and could be used as an environmental covariate in the demographic models. The levels of air pollutants describe quantitatively the parts of a whole (air), called composition, and their statistical treatment should consider this characteristic in the modelling process. This article evaluated the association between human mortality data with levels of air pollutants as a composition using a spatially-structured model. The spatially-structured modelling approach in the human mortality data captures the spatial heterogeneity of air pollutant concentrations (local environmental conditions). Human mortality data is defined as the number of deaths, and in this work, it was analyzed with both total and disaggregated presentation. The disaggregation was by (i) sex and (ii) sex and age-group. A likelihood ratio test suggested the model with air pollutants as covariates treated under a compositional approach (proposed model) is more appropriate than the model based only on time explanatory variable in yearly basis. The proposed model was evaluated in 48 counties in Spain, each with its mortality and air pollution dataset. The modelling approach in this work presented adequate quality model indexes and could be applied to make short-term predictions with different air pollution scenarios.
2022-03-31T18:20:41ZSánchez Balseca, JosephPérez Foguet, AgustíThe human mortality models with a demographic approach are performed in function of time. The addition of information (social, economic, and environmental) in the structure of demographic models allows fitting observed values better. Air pollution influences human mortality and could be used as an environmental covariate in the demographic models. The levels of air pollutants describe quantitatively the parts of a whole (air), called composition, and their statistical treatment should consider this characteristic in the modelling process. This article evaluated the association between human mortality data with levels of air pollutants as a composition using a spatially-structured model. The spatially-structured modelling approach in the human mortality data captures the spatial heterogeneity of air pollutant concentrations (local environmental conditions). Human mortality data is defined as the number of deaths, and in this work, it was analyzed with both total and disaggregated presentation. The disaggregation was by (i) sex and (ii) sex and age-group. A likelihood ratio test suggested the model with air pollutants as covariates treated under a compositional approach (proposed model) is more appropriate than the model based only on time explanatory variable in yearly basis. The proposed model was evaluated in 48 counties in Spain, each with its mortality and air pollution dataset. The modelling approach in this work presented adequate quality model indexes and could be applied to make short-term predictions with different air pollution scenarios.A new measure of hygiene inequality applied to urban-rural comparisonQuispe Coica, Filimon AlejandroPérez Foguet, Agustíhttp://hdl.handle.net/2117/3649772023-10-29T00:27:29Z2022-03-29T18:21:25ZA new measure of hygiene inequality applied to urban-rural comparison
Quispe Coica, Filimon Alejandro; Pérez Foguet, Agustí
Access to hygiene services remains one of the most urgent challenges facing countries, especially low-income ones. This has become much more critical in the current context of the COVID-19 pandemic. The WHO/UNICEF Joint Monitoring Program globally monitors access to hygiene service levels. As data are in three parts with a constant sum and a positive value, they are compositional data. Inequality is monitored in disaggregated data; in the urban–rural case, this is done through a simple difference between the urban and rural service levels. However, this simple form of calculation does not take into account the characteristics of the data, which can lead to erroneous interpretations of the results. Therefore, we propose an alternative measure of inequality that uses a ternary diagram and does not infringe on the data properties. The results of the new urban–rural inequality measure show spatial heterogeneity. The highest inequality occurs in Colombia, with a value of 37.1 percentage points, and the lowest in Turkmenistan, with a value of zero. Our results also show that 73 of the 76 countries evaluated have higher basic hygiene services in urban areas than in rural areas. This means that urban households have more availability of a handwashing facility on-premises with soap and water than rural households. Likewise, by subdividing the ternary diagram into ternary parcels, we could group and rank the countries based on hygiene service conditions in a hierarchical order using tripartite information. Finally, our study finds that a multivariate measure of inequality can be important for the public policies of the sector with a general vision, which underscores the value of making evidence-based decisions.
2022-03-29T18:21:25ZQuispe Coica, Filimon AlejandroPérez Foguet, AgustíAccess to hygiene services remains one of the most urgent challenges facing countries, especially low-income ones. This has become much more critical in the current context of the COVID-19 pandemic. The WHO/UNICEF Joint Monitoring Program globally monitors access to hygiene service levels. As data are in three parts with a constant sum and a positive value, they are compositional data. Inequality is monitored in disaggregated data; in the urban–rural case, this is done through a simple difference between the urban and rural service levels. However, this simple form of calculation does not take into account the characteristics of the data, which can lead to erroneous interpretations of the results. Therefore, we propose an alternative measure of inequality that uses a ternary diagram and does not infringe on the data properties. The results of the new urban–rural inequality measure show spatial heterogeneity. The highest inequality occurs in Colombia, with a value of 37.1 percentage points, and the lowest in Turkmenistan, with a value of zero. Our results also show that 73 of the 76 countries evaluated have higher basic hygiene services in urban areas than in rural areas. This means that urban households have more availability of a handwashing facility on-premises with soap and water than rural households. Likewise, by subdividing the ternary diagram into ternary parcels, we could group and rank the countries based on hygiene service conditions in a hierarchical order using tripartite information. Finally, our study finds that a multivariate measure of inequality can be important for the public policies of the sector with a general vision, which underscores the value of making evidence-based decisions.Compositional spatio-temporal PM2.5 modelling in wildfiresSánchez Balseca, JosephPérez Foguet, Agustíhttp://hdl.handle.net/2117/3648392022-03-27T15:50:31Z2022-03-24T17:47:25ZCompositional spatio-temporal PM2.5 modelling in wildfires
Sánchez Balseca, Joseph; Pérez Foguet, Agustí
Wildfires are natural ecological processes that generate high levels of fine particulate matter (PM2.5) that are dispersed into the atmosphere. PM2.5 could be a potential health problem due to its size. Having adequate numerical models to predict the spatial and temporal distribution of PM2.5 helps to mitigate the impact on human health. The compositional data approach is widely used in the environmental sciences and concentration analyses (parts of a whole). This numerical approach in the modelling process avoids one common statistical problem: the spurious correlation. PM2.5 is a part of the atmospheric composition. In this way, this study developed an hourly spatio-temporal PM2.5 model based on the dynamic linear modelling framework (DLM) with a compositional approach. The results of the model are extended using a Gaussian–Mattern field. The modelling of PM2.5 using a compositional approach presented adequate quality model indices (NSE = 0.82, RMSE = 0.23, and a Pearson correlation coefficient of 0.91); however, the correlation range showed a slightly lower value than the conventional/traditional approach. The proposed method could be used in spatial prediction in places without monitoring stations.
2022-03-24T17:47:25ZSánchez Balseca, JosephPérez Foguet, AgustíWildfires are natural ecological processes that generate high levels of fine particulate matter (PM2.5) that are dispersed into the atmosphere. PM2.5 could be a potential health problem due to its size. Having adequate numerical models to predict the spatial and temporal distribution of PM2.5 helps to mitigate the impact on human health. The compositional data approach is widely used in the environmental sciences and concentration analyses (parts of a whole). This numerical approach in the modelling process avoids one common statistical problem: the spurious correlation. PM2.5 is a part of the atmospheric composition. In this way, this study developed an hourly spatio-temporal PM2.5 model based on the dynamic linear modelling framework (DLM) with a compositional approach. The results of the model are extended using a Gaussian–Mattern field. The modelling of PM2.5 using a compositional approach presented adequate quality model indices (NSE = 0.82, RMSE = 0.23, and a Pearson correlation coefficient of 0.91); however, the correlation range showed a slightly lower value than the conventional/traditional approach. The proposed method could be used in spatial prediction in places without monitoring stations.Modelling hourly spatio-temporal PM2.5 concentration in wildfire scenarios using dynamic linear modelsSánchez Balseca, JosephPérez Foguet, Agustíhttp://hdl.handle.net/2117/3494602022-04-13T00:29:39Z2021-07-15T13:56:11ZModelling hourly spatio-temporal PM2.5 concentration in wildfire scenarios using dynamic linear models
Sánchez Balseca, Joseph; Pérez Foguet, Agustí
Particulate matter with aerodynamic diameter < 2.5 μm (PM2.5) is one of the main pollutants generated in wildfire events with negative impacts on human health. In research involving wildfires and air quality, it is common to use emission models. However, the commonly used emission approach can generate errors and contradict the empirical data. This paper adopted a statistical approach based in evidence of ground level monitoring and satellite data. An hourly PM2.5 spatio-temporal model based on a dynamic linear modelling framework with Bayesian approach was proposed in a territorial context with a reduced number of monitoring stations for particulate matter. The model validation is complicated by the fact that all monitoring stations are used in the model calibration. The novel validation method proposed considered both the particulate matter with aerodynamic diameter < 10 μm (PM10) recorded as daily value from 24-h mean every six days as well as the PM2.5/PM10 ratio. Modelling was carried out to provide satisfactorily the exposure level of PM2.5 in a case study of wildfire event.
2021-07-15T13:56:11ZSánchez Balseca, JosephPérez Foguet, AgustíParticulate matter with aerodynamic diameter < 2.5 μm (PM2.5) is one of the main pollutants generated in wildfire events with negative impacts on human health. In research involving wildfires and air quality, it is common to use emission models. However, the commonly used emission approach can generate errors and contradict the empirical data. This paper adopted a statistical approach based in evidence of ground level monitoring and satellite data. An hourly PM2.5 spatio-temporal model based on a dynamic linear modelling framework with Bayesian approach was proposed in a territorial context with a reduced number of monitoring stations for particulate matter. The model validation is complicated by the fact that all monitoring stations are used in the model calibration. The novel validation method proposed considered both the particulate matter with aerodynamic diameter < 10 μm (PM10) recorded as daily value from 24-h mean every six days as well as the PM2.5/PM10 ratio. Modelling was carried out to provide satisfactorily the exposure level of PM2.5 in a case study of wildfire event.Influence of atmospheric parameters on human mortality data at different geographical levelsSánchez Balseca, JosephPérez Foguet, Agustíhttp://hdl.handle.net/2117/3464372022-12-10T01:26:27Z2021-05-31T15:20:12ZInfluence of atmospheric parameters on human mortality data at different geographical levels
Sánchez Balseca, Joseph; Pérez Foguet, Agustí
Human mortality data are often modeled using a demographic approach as a function of time. This approach does not present an adequate fit model for the number of deaths with great variability. For this reason, additional information (social, economic and environmental) is required for complementing and improving demographic modelling. This article evaluated the association between human mortality data (segregated by age and sex) with meteorological and air pollutant covariates at three geographical levels: country, macro-climate regions and county. The modelling was based on a generalized linear modelling framework and takes into account the common characteristic of overdispersion in human mortality data through the application of negative binomial distribution. The proposed approach improved the dynamic behavior of the Farrington-like model (basic demographic model) and took into account the extreme meteorological and natural air pollution events. Notably, the proposed modelling worked well in cases where the amount of data was scarce.
2021-05-31T15:20:12ZSánchez Balseca, JosephPérez Foguet, AgustíHuman mortality data are often modeled using a demographic approach as a function of time. This approach does not present an adequate fit model for the number of deaths with great variability. For this reason, additional information (social, economic and environmental) is required for complementing and improving demographic modelling. This article evaluated the association between human mortality data (segregated by age and sex) with meteorological and air pollutant covariates at three geographical levels: country, macro-climate regions and county. The modelling was based on a generalized linear modelling framework and takes into account the common characteristic of overdispersion in human mortality data through the application of negative binomial distribution. The proposed approach improved the dynamic behavior of the Farrington-like model (basic demographic model) and took into account the extreme meteorological and natural air pollution events. Notably, the proposed modelling worked well in cases where the amount of data was scarce.Child mortality levels and trends: a new compositional approachEzbakhe, FatinePérez Foguet, Agustíhttp://hdl.handle.net/2117/3423962022-05-17T12:02:23Z2021-03-24T15:53:53ZChild mortality levels and trends: a new compositional approach
Ezbakhe, Fatine; Pérez Foguet, Agustí
Background: Trend analysis of child mortality is vital to evaluate countries’ progress towards achieving the Sustainable Development Goal on health (SDG 3). However, strictly speaking, child mortality data are probabilities, and thus subject to non-negativity and constant-sum constraints.
Objective: Our objective is to assess the application of compositional data analysis for estimating levels and trends in child mortality.
Methods: We compare two data transformations: logit, which is widely used in child mortality estimation, and isometric log-ratio (ILR), which is specifically designed for compositional data. We use publicly available household survey data on neonatal (NMR) and under-five (U5MR) mortality ratios in sub-Saharan Africa.
Results: Although both data transformations yield similar estimates, only the ILR transformation is consistent with the compositional properties of child mortality data. However, the ILR suffers from one key drawback: it requires complete data series, with pairs of observations for both NMR and U5MR. As a result, ILR entails excluding a large amount of available data from the regression analysis.
Conclusions: Complete data is needed to be able to undertake a compositional trend analysis of child mortality. This gap in data can be closed by employing imputation strategies that replace missing values in the existing datasets, and by developing new methods for the indirect estimation of NMR from summary birth history data, as it is currently done for U5MR.
Contribution: This paper extends the literature on child mortality estimation by examining the application of compositional data analysis to this field. It constitutes a first step towards building a Bayesian compositional regression approach for child mortality estimation.
2021-03-24T15:53:53ZEzbakhe, FatinePérez Foguet, AgustíBackground: Trend analysis of child mortality is vital to evaluate countries’ progress towards achieving the Sustainable Development Goal on health (SDG 3). However, strictly speaking, child mortality data are probabilities, and thus subject to non-negativity and constant-sum constraints.
Objective: Our objective is to assess the application of compositional data analysis for estimating levels and trends in child mortality.
Methods: We compare two data transformations: logit, which is widely used in child mortality estimation, and isometric log-ratio (ILR), which is specifically designed for compositional data. We use publicly available household survey data on neonatal (NMR) and under-five (U5MR) mortality ratios in sub-Saharan Africa.
Results: Although both data transformations yield similar estimates, only the ILR transformation is consistent with the compositional properties of child mortality data. However, the ILR suffers from one key drawback: it requires complete data series, with pairs of observations for both NMR and U5MR. As a result, ILR entails excluding a large amount of available data from the regression analysis.
Conclusions: Complete data is needed to be able to undertake a compositional trend analysis of child mortality. This gap in data can be closed by employing imputation strategies that replace missing values in the existing datasets, and by developing new methods for the indirect estimation of NMR from summary birth history data, as it is currently done for U5MR.
Contribution: This paper extends the literature on child mortality estimation by examining the application of compositional data analysis to this field. It constitutes a first step towards building a Bayesian compositional regression approach for child mortality estimation.Decision analysis for sustainable development: the case of renewable energy planning under uncertaintyEzbakhe, FatinePérez Foguet, Agustíhttp://hdl.handle.net/2117/3414882022-03-05T01:26:24Z2021-03-11T13:15:48ZDecision analysis for sustainable development: the case of renewable energy planning under uncertainty
Ezbakhe, Fatine; Pérez Foguet, Agustí
Multi-Criteria Decision Analysis (MCDA) methods are increasingly used to aid decision-making for sustainable development. However, although uncertainty is present in all decision environments, dealing with incomplete and vague information in decision analysis remains a challenge. Our objective is to simplify the incorporation of uncertainty in the scoring of alternatives in MCDA processes. We present a modified ELimination and Choice Translating REality (ELECTRE) III model, in which the uncertainty in the performance scores is expressed as lower/upper bounds and then added to the model’s discrimination thresholds. Unlike other uncertainty approaches developed in the literature (such as those based on fuzzy set theory), our approach does not require additional knowledge apart from understanding the ELECTRE III model. To test its validity and suitability, we apply it for the evaluation of renewable energy resources for Turkey – hydro, wind, geothermal, solar, and biomass – under five main criteria: technological, technical, economic, environmental, and socio-politic. Our results indicate that wind energy is the best alternative for Turkey, followed by solar energy, which is in line with country’s Vision 2023 energy targets.
2021-03-11T13:15:48ZEzbakhe, FatinePérez Foguet, AgustíMulti-Criteria Decision Analysis (MCDA) methods are increasingly used to aid decision-making for sustainable development. However, although uncertainty is present in all decision environments, dealing with incomplete and vague information in decision analysis remains a challenge. Our objective is to simplify the incorporation of uncertainty in the scoring of alternatives in MCDA processes. We present a modified ELimination and Choice Translating REality (ELECTRE) III model, in which the uncertainty in the performance scores is expressed as lower/upper bounds and then added to the model’s discrimination thresholds. Unlike other uncertainty approaches developed in the literature (such as those based on fuzzy set theory), our approach does not require additional knowledge apart from understanding the ELECTRE III model. To test its validity and suitability, we apply it for the evaluation of renewable energy resources for Turkey – hydro, wind, geothermal, solar, and biomass – under five main criteria: technological, technical, economic, environmental, and socio-politic. Our results indicate that wind energy is the best alternative for Turkey, followed by solar energy, which is in line with country’s Vision 2023 energy targets.A techno-economic optimization model of a biomass-based CCHP/heat pump system under evolving climate conditionsWegener, MoritzMalmquist, AndersIsalgué Buxeda, AntonioMartin, AndrewArranz Piera, PolCamara Moreno, OsarVelo García, Enriquehttp://hdl.handle.net/2117/3353522022-11-13T10:04:27Z2021-01-14T14:32:07ZA techno-economic optimization model of a biomass-based CCHP/heat pump system under evolving climate conditions
Wegener, Moritz; Malmquist, Anders; Isalgué Buxeda, Antonio; Martin, Andrew; Arranz Piera, Pol; Camara Moreno, Osar; Velo García, Enrique
An innovative modelling approach for the design of biomass-based, solar-assisted combined cooling, heating, and power (CCHP) and heat pump (HP) systems for various climate scenarios is proposed in this work. The modelling approach is comprised of three sub-models (a demand sub-model, a supply sub-model, an economic sub-model) allowing for cost-optimal sizing of the system components based on net present cost (NPC). Subsequently a transient optimization model has been developed, which computes the technical and economic performance for each component size and for each ambient temperature of the different climate scenarios. Additionally, the model provides data on energy efficiency, exergy efficiency, and CO2-emissions of a given CCHP/HP system. The model has then been employed in a case study in order to analyse the performance of a CCHP/HP system for a tourist, museum, and guest accommodation structure located at the Montjuïc castle in Barcelona, Spain. The results show that the smallest simulated biomass-based CCHP system using a 25 kWe syngas-fuelled engine would reduce lifetime costs by 7% compared to an only-HP system while operating with a high total energy efficiency of over 60%. The combined CCHP/HP system would operate with an exergy efficiency of 18%. However, larger CCHP systems cannot offset the much higher capital costs despite increasing electricity sales. The findings also reveal that for the high climate change scenario the overall project costs drop by up to 2.5%, however the effects have little impact on the optimal CCHP/HP system sizing. Even the smallest CCHP system would reduce emissions already by 75% with an increasing trend for larger systems. Although CCHP/HP systems would lead to lower NPC and emissions, the high investment costs and the complexity of the combined system remain considerable obstacles.
2021-01-14T14:32:07ZWegener, MoritzMalmquist, AndersIsalgué Buxeda, AntonioMartin, AndrewArranz Piera, PolCamara Moreno, OsarVelo García, EnriqueAn innovative modelling approach for the design of biomass-based, solar-assisted combined cooling, heating, and power (CCHP) and heat pump (HP) systems for various climate scenarios is proposed in this work. The modelling approach is comprised of three sub-models (a demand sub-model, a supply sub-model, an economic sub-model) allowing for cost-optimal sizing of the system components based on net present cost (NPC). Subsequently a transient optimization model has been developed, which computes the technical and economic performance for each component size and for each ambient temperature of the different climate scenarios. Additionally, the model provides data on energy efficiency, exergy efficiency, and CO2-emissions of a given CCHP/HP system. The model has then been employed in a case study in order to analyse the performance of a CCHP/HP system for a tourist, museum, and guest accommodation structure located at the Montjuïc castle in Barcelona, Spain. The results show that the smallest simulated biomass-based CCHP system using a 25 kWe syngas-fuelled engine would reduce lifetime costs by 7% compared to an only-HP system while operating with a high total energy efficiency of over 60%. The combined CCHP/HP system would operate with an exergy efficiency of 18%. However, larger CCHP systems cannot offset the much higher capital costs despite increasing electricity sales. The findings also reveal that for the high climate change scenario the overall project costs drop by up to 2.5%, however the effects have little impact on the optimal CCHP/HP system sizing. Even the smallest CCHP system would reduce emissions already by 75% with an increasing trend for larger systems. Although CCHP/HP systems would lead to lower NPC and emissions, the high investment costs and the complexity of the combined system remain considerable obstacles.Spatio-temporal air pollution modelling using a compositional approachSánchez Balseca, JosephPérez Foguet, Agustíhttp://hdl.handle.net/2117/3337802022-05-17T11:30:57Z2020-12-02T14:48:49ZSpatio-temporal air pollution modelling using a compositional approach
Sánchez Balseca, Joseph; Pérez Foguet, Agustí
Air pollutant data are compositional in character because they describe quantitatively the parts of a whole (atmospheric composition). However, it is common to use air pollutant concentrations in statistical models without considering this characteristic of the data and, therefore, without control of common statistical problems, such as spurious correlations and subcompositional incoherence. This paper now proposes a daily multivariate spatio-temporal model with a compositional approach. The air pollution spatio-temporal model is based on a dynamic linear modelling framework with Bayesian inference. The novel modelling methodology was applied in an urban area for carbon monoxide (CO, mg·m-3), sulfur dioxide (SO2, µg·m-3), ozone (O3, µg·m-3), nitrogen dioxide (NO2, µg·m-3), and particulate matter less than 2.5 µm in aerodynamic diameter (PM2.5, µg·m-3). The proposal complemented and improved the conventional approach in air pollution modelling. The main improvements come from a fast multivariate data description, high spatial-correlation, and adequate modelling of air pollutants with high variability.
2020-12-02T14:48:49ZSánchez Balseca, JosephPérez Foguet, AgustíAir pollutant data are compositional in character because they describe quantitatively the parts of a whole (atmospheric composition). However, it is common to use air pollutant concentrations in statistical models without considering this characteristic of the data and, therefore, without control of common statistical problems, such as spurious correlations and subcompositional incoherence. This paper now proposes a daily multivariate spatio-temporal model with a compositional approach. The air pollution spatio-temporal model is based on a dynamic linear modelling framework with Bayesian inference. The novel modelling methodology was applied in an urban area for carbon monoxide (CO, mg·m-3), sulfur dioxide (SO2, µg·m-3), ozone (O3, µg·m-3), nitrogen dioxide (NO2, µg·m-3), and particulate matter less than 2.5 µm in aerodynamic diameter (PM2.5, µg·m-3). The proposal complemented and improved the conventional approach in air pollution modelling. The main improvements come from a fast multivariate data description, high spatial-correlation, and adequate modelling of air pollutants with high variability.