Air pollution prediction models of particles, As, Cd, Ni and Pb in a highly industrialized area in Castellón (NE, Spain)

Vicente, A.B.; Jordán, M. M.; Sanfeliu, T.; Sánchez, Ángel; Esteban, Maria J.

doi:10.1007/s12665-011-1298-z

Cited by 10 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The team utilized multiple linear regression analysis and autoregressive integrated moving average (ARIMA) time series models to generate the alerting system [10]. Similarly, the University of Virginia developed a criminal analysis program to monitor anomalies in criminal data built around a zero modified Poisson linear model [11].…”

Section: Literature Reviewmentioning

confidence: 99%

Environmental surveillance modeling: A predictive respiratory alert model for the Shenandoah Valley, Virginia

Hovland

Wagner

Pierce

et al. 2013

2013 IEEE Systems and Information Engineering Design Symposium

View full text Add to dashboard Cite

Abstract²Chronic Obstructive Pulmonary Disease (COPD) is a serious respiratory ailment that affects millions of Americans. Several studies have shown that weather conditions and pollution can increase the occurrence of respiratory distress. The goal of the work described in this paper was to determine if the relationships between environmental variables and admissions rates for COPD were strong enough to enable the development of a surveillance system that could alert the population of potentially hazardous conditions. To conduct this study we obtained data on COPD admissions in the Shenandoah Valley of Virginia, an area of approximately 33,705 km 2 . The data were coded at the zip code level (approximately 250 km 2 ). We obtained data for weather variables from 6 monitoring stations and used Kriging to estimate their values at the zip code level. We controlled for the effects of influenza in admission rates, although this required smoothing methods to impute missing values. We also controlled for different types of land use. To predict COPD admissions we developed three types of models: generalized linear models (GLM), multivariate adaptive regression splines (MARS), and random forests. All models showed that temperature or season was a significant (p < 0.05) predictor for COPD admissions. In terms of predictive accuracy the random forest model provided the best performance measured by the receiver operations characteristic (ROC) and can provide the basis for strategic planning rather than tactical alerting.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Environmental surveillance modeling: A predictive respiratory alert model for the Shenandoah Valley, Virginia

Hovland

Wagner

Pierce

et al. 2013

2013 IEEE Systems and Information Engineering Design Symposium

View full text Add to dashboard Cite

show abstract

“…Existing studies involving time series analysis of O 3 and NO x have generally used univariate approaches (e.g., Kumar and Jain, 2010;Kumar et al, 2004;Slini et al, 2002;Robeson and Steyn, 1990), meaning that precursors relevant to formation chemistry are excluded from the analysis. Likewise, studies on time series analysis from particulate matter (PM) mass and/or it components (e.g., Jian et al, 2012;Vicente et al, 2012;Diaz-Robles, 69 2008;Vana et al, 1999) have focused on a single variable approach. For this study, we completed real-time measurements of gas-phase organic and inorganic species during a winter field campaign in Utah, then applied a vector autoregression to examine precursor species that are important to the formation of O 3 and NO x .…”

Section: Introductionmentioning

confidence: 99%

Time series analysis of wintertime O3 and NOx formation using vector autoregressions

Olson

Riedel

Long

et al. 2019

Atmospheric Environment

View full text Add to dashboard Cite

Concentrations of 11 species are reported from continuous measurements taken during a wintertime field study in Utah. Time series data for measured species generally displayed strong diurnal patterns. Six species show a diurnal pattern of daytime maximums (NO, NO y , O 3 , H 2 O 2 , CH 2 O 2 , and Cl 2), while five species show a diurnal pattern of night time maximums (NO 2 , HONO, ClNO 2 , HNO 3 , and N 2 O 5). Vector autoregression analyses were completed to better understand important species influencing the formation of O 3 and NO x. For the species studied, r 2 values of predicted versus measured concentrations ranged from 0.82-0.99. Fitting parameters for the autoregressive matrix, Π, indicated the importance of species precursors. In addition, values of fitting parameters for Π were relatively insensitive to data size, with variations generally <10%. Variable causation was quantified using the Granger causation method. Assuming O 3 and NO x behave as chemical products, reactants (in order of importance) are as follows:

show abstract

“…The state-space model performed better than the ARX model. On the other hand, Vicente et al (2012) developed predictive models based on multiple regression analysis together with time series (ARIMA) models to predict the concentration of total suspended particles (TSP), PM 10 , As, Cd, Ni and Pb in the ambient air of Castellón (Spain). Furthermore, in a previous study conducted by Arruti et al (2011), estimations of As, Cd, Ni and Pb levels in Cantabria (Spain) by means of statistical MLR and PCR models have been conducted.…”

Section: Introductionmentioning

confidence: 99%

Estimation of PM10-Bound As, Cd, Ni and Pb Levels by Means of Statistical Modelling: PLSR and ANN Approaches

Santos

Fernández-Olmo

Irabien

2015

Water Air Soil Pollut

View full text Add to dashboard Cite

Air quality assessment regarding metals and metalloids using experimental measurements is expensive and time consuming due to the cost and time required for the analytical determination of the levels of these pollutants. According to the European Union (EU) Air Quality Framework Directive (Directive 2008/50/EC), other alternatives, such as objective estimation techniques, can be considered for ambient air quality assessment in zones and agglomerations where the level of pollutants is below a certain concentration value known as the lower assessment threshold. These conditions occur in urban areas in Cantabria (northern Spain). This work aims to estimate the levels of As, Cd, Ni and Pb in airborne PM 10 at two urban sites in the Cantabria region (Castro Urdiales and Reinosa) using statistical models as objective estimation techniques. These models were developed based on three different approaches: partial least squares regression (PLSR), artificial neural networks (ANNs) and an alternative approach consisting of principal component analysis (PCA) coupled with ANNs (PCA-ANN). Additionally, these models were externally validated using previously unseen data. The results show that the models developed in this work based on PLSR and ANNs fulfil the EU uncertainty requirements for objective estimation techniques and provide an acceptable estimation of the mean values. As a consequence, they could be considered as an alternative to experimental measurements for air quality assessment regarding the aforementioned pollutants in the study areas while saving time and resources.

show abstract

Air pollution prediction models of particles, As, Cd, Ni and Pb in a highly industrialized area in Castellón (NE, Spain)

Cited by 10 publications

References 16 publications

Environmental surveillance modeling: A predictive respiratory alert model for the Shenandoah Valley, Virginia

Environmental surveillance modeling: A predictive respiratory alert model for the Shenandoah Valley, Virginia

Time series analysis of wintertime O3 and NOx formation using vector autoregressions

Estimation of PM10-Bound As, Cd, Ni and Pb Levels by Means of Statistical Modelling: PLSR and ANN Approaches

Contact Info

Product

Resources

About