A Bayesian kriged Kalman model for short-term forecasting of air pollution levels

Summary.  Short-term forecasts of air pollution levels in big cities are now reported in news-papers and other media outlets. Studies indicate that even short-term exposure to high levels of an air pollutant called atmospheric particulate matter can lead to long-term health effects. Data are typically observed at fixed monitoring stations throughout a study region of interest at different time points. Statistical spatiotemporal models are appropriate for modelling these data. We consider short-term forecasting of these spatiotemporal processes by using a Bayesian kriged Kalman filtering model. The spatial prediction surface of the model is built by using the well-known method of kriging for optimum spatial prediction and the temporal effects are analysed by using the models underlying the Kalman filtering method. The full Bayesian model is implemented by using Markov chain Monte Carlo techniques which enable us to obtain the optimal Bayesian forecasts in time and space. A new cross-validation method based on the Mahalanobis distance between the forecasts and observed data is also developed to assess the forecasting performance of the model implemented.     

Optimal design of air quality networks detecting warning and alert conditions

A statistical method is presented to determine the optima design of air quality networks detecting warning and alert levels. A simulation model is used to describe temporal and spatial variations of atmospheric pollutants; air quality patterns serve as the database of the procedure to design the network. Only the sites exceeding warning and alert levels, at different meteorological scenarios, are considered as potential monitoring stations. For the selection of the optima set, spatial and temporal representativity criteria are introduced; accordingly, the optima set provides a complete representativity of the space and time considered. The method is applied to the Mestre urban area, in Venice district, for the carbon monoxide pollutant.     

Prediction with Additive Models—Simulation and Application with Real Data

Abstract

In this paper we study the predictor behaviour of the additive model. The prediction equation is introduced as well as the computational considerations to select the smoothing parameters through cross-validation. The additive predictor is compared with a partially linear predictor in a broad simulation study and an application to a real case, prediction of the atmospheric concentration of SO₂ in sample stations.     

Venezuelan Rainfall Data Analysed by Using a Bayesian Space–time Model

We consider a set of data from 80 stations in the Venezuelan state of Guárico consisting of accumulated monthly rainfall in a time span of 16 years. The problem of modelling rainfall accumulated over fixed periods of time and recorded at meteorological stations at different sites is studied by using a model based on the assumption that the data follow a truncated and transformed multivariate normal distribution. The spatial correlation is modelled by using an exponentially decreasing correlation function and an interpolating surface for the means. Missing data and dry periods are handled within a Markov chain Monte Carlo framework using latent variables. We estimate the amount of rainfall as well as the probability of a dry period by using the predictive density of the data. We considered a model based on a full second-degree polynomial over the spatial co-ordinates as well as the first two Fourier harmonics to describe the variability during the year. Predictive inferences on the data show very realistic results, capturing the typical rainfall variability in time and space for that region. Important extensions of the model are also discussed.     

Functional principal component analysis of spatially correlated data

This paper focuses on the analysis of spatially correlated functional data. We propose a parametric model for spatial correlation and the between-curve correlation is modeled by correlating functional principal component scores of the functional data. Additionally, in the sparse observation framework, we propose a novel approach of spatial principal analysis by conditional expectation to explicitly estimate spatial correlations and reconstruct individual curves. Assuming spatial stationarity, empirical spatial correlations are calculated as the ratio of eigenvalues of the smoothed covariance surface Cov\((X_i(s),X_i(t))\) and cross-covariance surface Cov\((X_i(s), X_j(t))\) at locations indexed by i and j. Then a anisotropy Matérn spatial correlation model is fitted to empirical correlations. Finally, principal component scores are estimated to reconstruct the sparsely observed curves. This framework can naturally accommodate arbitrary covariance structures, but there is an enormous reduction in computation if one can assume the separability of temporal and spatial components. We demonstrate the consistency of our estimates and propose hypothesis tests to examine the separability as well as the isotropy effect of spatial correlation. Using simulation studies, we show that these methods have some clear advantages over existing methods of curve reconstruction and estimation of model parameters.     

Spatio-temporal modelling using B-spline for disease mapping: analysis of childhood cancer trends

To examine childhood cancer diagnoses in the province of Alberta, Canada during 1983–2004, we construct a generalized additive mixed model for the analysis of geographic and temporal variability of cancer ratios. In this model, spatially correlated random effects and temporal components are adopted. The interaction between space and time is also accommodated. Spatio-temporal models that use conditional autoregressive smoothing across the spatial dimension and B-spline over the temporal dimension are considered. We study the patterns of incidence ratios over time and identify areas with consistently high ratio estimates as areas for potential further investigation. We apply the method of penalized quasi-likelihood to estimate the model parameters. We illustrate this approach using a yearly data set of childhood cancer diagnoses in the province of Alberta, Canada during 1983–2004.     

Testing for interactions in generalized additive models: Application to SO<Subscript>2</Subscript> pollution data

In this paper we considered a generalized additive model with second-order interaction terms. A local scoring algorithm (with backfitting) based on local linear kernel smoothers was used to estimate the model. Our main aim was to obtain procedures for testing second-order interaction terms. Backfitting theory is difficult in this context, and a bootstrap procedure is therefore provided for estimating the distribution of the test statistics. Given the high computational cost involved, binning techniques were used to speed up the computation in the estimation and testing process. A simulation study was carried out in order to assess the validity of the bootstrap-based tests. Lastly, our method was applied to real data drawn from an SO₂ binary time series.     

Lessons From Quantile Panel Estimation of the Environmental Kuznets Curve

We employ quantile regression fixed effects models to estimate the income-pollution relationship on NO _x (nitrogen oxide) and SO ₂ (sulfur dioxide) using U.S. data. Conditional median results suggest that conditional mean methods provide too optimistic estimates about emissions reduction for NO _x , while the opposite is found for SO ₂. Deleting outlier states reverses the absence of a turning point for SO ₂ in the conditional mean model, while the conditional median model is robust to them. We also document the relationship's sensitivity to including additional covariates for NO _x , and undertake simulations to shed light on some estimation issues of the methods employed.     

Spatial–temporal model for wind speed in Lithuania

In this paper, we propose a spatial–temporal model for the wind speed (WS). We first estimate the model at the single spatial meteorological station independently on spatial correlations. The temporal model contains seasonality, a higher-order autoregressive component and a variance describing the remaining heteroskedesticity in residuals. We then model spatial dependencies by a Gaussian random field. The model is estimated on daily WS records from 18 meteorological stations in Lithuania. The validation procedure based on out-of-sample observations shows that the proposed model is reliable and can be used for various practical applications.     

Bayesian univariate space-time hierarchical model for mapping pollutant concentrations in the municipal area of Taranto

An analysis of air quality data is provided for the municipal area of Taranto (Italy) characterized by high environmental risks as decreed by the Italian government in the 1990s. In the context of an agreement between Dipartimento di Scienze Statistiche—Università degli Studi di Bari and the local regional environmental protection agency air quality, data were provided concerning six monitoring stations and covering years from 2005 to 2007. In this paper we analyze the daily concentrations of three pollutants highly relevant in such an industrial area, namely SO₂, NO₂ and PM₁₀, with the aim of reconstructing daily pollutants concentration surfaces for the town area. Taking into account the large amount of sparse missing data and the non normality affecting pollutants’ concentrations, we propose a full Bayesian separable space-time hierarchical model for each pollutant concentration series. The proposed model allows to embed missing data imputation and prediction of pollutant concentration. We critically discuss the results, highlighting advantages and disadvantages of the proposed methodology.     

A Case Study for Modelling Cancer Incidence Using Bayesian Spatio‐Temporal Models

Researchers familiar with spatial models are aware of the challenge of choosing the level of spatial aggregation. Few studies have been published on the investigation of temporal aggregation and its impact on inferences regarding disease outcome in space–time analyses. We perform a case study for modelling individual disease outcomes using several Bayesian hierarchical spatio‐temporal models, while taking into account the possible impact of spatial and temporal aggregation. Using longitudinal breast cancer data from South East Queensland, Australia, we consider both parametric and non‐parametric formulations for temporal effects at various levels of aggregation. Two temporal smoothness priors are considered separately; each is modelled with fixed effects for the covariates and an intrinsic conditional autoregressive prior for the spatial random effects. Our case study reveals that different model formulations produce considerably different model performances. For this particular dataset, a classical parametric formulation that assumes a linear time trend produces the best fit among the five models considered. Different aggregation levels of temporal random effects were found to have little impact on model goodness‐of‐fit and estimation of fixed effects.     

Relative risk analysis of dengue cases using convolution extended into spatio-temporal model

Dengue Hemmorage Fever (DHF) cases have become a serious problem every year in tropical countries such as Indonesia. Understanding the dynamic spread of the disease is essential in order to find an effective strategy in controlling its spread. In this study, a convolution (Poisson-lognormal) model that integrates both uncorrelated and correlated random effects was developed. A spatial–temporal convolution model to accomodate both spatial and temporal variations of the disease spread dynamics was considered. The model was applied to the DHF cases in the city of Kendari, Indonesia. DHF data for 10 districts during the period 2007–2010 were collected from the health services. The data of rainfall and population density were obtained from the local offices in Kendari. The numerical experiments indicated that both the rainfall and the population density played an important role in the increasing DHF cases in the city of Kendari. The result suggested that DHF cases mostly occured in January, the wet session with high rainfall, and in Kadia, the densest district in the city. As people in the city have high mobility while dengue mosquitoes tend to stay localized in their area, the best intervention is in January and in the district of Kadia.     

Physically constrained spatiotemporal modeling: generating clear-sky constructions of land surface temperature from sparse,remotely sensed satellite data

Satellite remote-sensing is used to collect important atmospheric and geophysical data at various spatial resolutions, providing insight into spatiotemporal surface and climate variability globally. These observations are often plagued with missing spatial and temporal information of Earth''s surface due to (1) cloud cover at the time of a satellite passing and (2) infrequent passing of polar-orbiting satellites. While many methods are available to model missing data in space and time, in the case of land surface temperature (LST) from thermal infrared remote sensing, these approaches generally ignore the temporal pattern called the ‘diurnal cycle’ which physically constrains temperatures to peak in the early afternoon and reach a minimum at sunrise. In order to infill an LST dataset, we parameterize the diurnal cycle into a functional form with unknown spatiotemporal parameters. Using multiresolution spatial basis functions, we estimate these parameters from sparse satellite observations to reconstruct an LST field with continuous spatial and temporal distributions. These estimations may then be used to better inform scientists of spatiotemporal thermal patterns over relatively complex domains. The methodology is demonstrated using data collected by MODIS on NASA''s Aqua and Terra satellites over both Houston, TX and Phoenix, AZ USA.     

Wavelet-based Bayesian nonlinear regression for the air pollution effects on clinic visits in small areas of Taiwan

We revisit the complete clinic visit records and environmental monitoring data at 50 townships and city districts of Taiwan. Extending the earlier analyses, here we consider a Bayesian analysis using Daubechies wavelet. Appropriate model selection is also considered using Bayesian model averaging. Temperature, dew point, and NO₂ and CO of the current day and the previous day are identified as the pollutants in different areas of the island following some spatial pattern.     

The variability of rainfall acidity

Two years of rainfall acidity data for the eastern United States were analyzed. The data consist of rainfall-event pH measurements from a nine station monitoring network. A spatio-temporal stochastic model, including deterministic components for seasonal variation and rainfall washout, and stochastic components for spatial, temporal, and measurement variation, was fitted to the data. The fitted autocorrelation structure from this model was used, in the process known as Kriging, to obtain BLUE contour maps of seasonal and rainfall adjusted yearly average pH over the monitoring region.     

A non-homogeneous skew-Gaussian Bayesian spatial model

In spatial statistics, models are often constructed based on some common, but possible restrictive assumptions for the underlying spatial process, including Gaussianity as well as stationarity and isotropy. However, these assumptions are frequently violated in applied problems. In order to simultaneously handle skewness and non-homogeneity (i.e., non-stationarity and anisotropy), we develop the fixed rank kriging model through the use of skew-normal distribution for its non-spatial latent variables. Our approach to spatial modeling is easy to implement and also provides a great flexibility in adjusting to skewed and large datasets with heterogeneous correlation structures. We adopt a Bayesian framework for our analysis, and describe a simple MCMC algorithm for sampling from the posterior distribution of the model parameters and performing spatial prediction. Through a simulation study, we demonstrate that the proposed model could detect departures from normality and, for illustration, we analyze a synthetic dataset of CO\(_2\) measurements. Finally, to deal with multivariate spatial data showing some degree of skewness, a multivariate extension of the model is also provided.     

Productivity indices and survival rate estimates from MAPS,a continent-wide programme of constant-effort mist-netting in North America

The Monitoring Avian Productivity and Survivorship (MAPS) programme is a cooperative effort to provide annual regional indices of adult population size and post-fledging productivity and estimates of adult survival rates from data pooled from a network of constant-effort mist-netting stations across North America. This paper provides an overview of the field and analytical methods currently employed by MAPS, a discussion of the assumptions underlying the use of these techniques, and a discussion of the validity of some of these assumptions based on data gathered during the first 5 years (1989-1993) of the programme, during which time it grew from 17 to 227 stations. Ageand species-specific differences in dispersal characteristics are important factors affecting the usefulness of the indices of adult population size and productivity derived from MAPS data. The presence of transients, heterogeneous capture probabilities among stations, and the large sample sizes required by models to deal effectively with these two considerations are important factors affecting the accuracy and precision of survival rate estimates derived from MAPS data. Important results from the first 5 years of MAPS are: (1) indices of adult population size derived from MAPS mist-netting data correlated well with analogous indices derived from point-count data collected at MAPS stations; (2) annual changes in productivity indices generated by MAPS were similar to analogous changes documented by direct nest monitoring and were generally as expected when compared to annual changes in weather during the breeding season; and (3) a model using between-year recaptures in Cormack-Jolly-Seber (CJS) mark-recapture analyses to estimate the proportion of residents among unmarked birds was found, for most tropical-wintering species sampled, to provide a better fit with the available data and more realistic and precise estimates of annual survival rates of resident birds than did standard CJS mark-recapture analyses. A detailed review of the statistical characteristics of MAPS data and a thorough evaluation of the field and analytical methods used in the MAPS programme are currently under way.     

Bayesian Nonlinear Regression for the Air Pollution Effects on Daily Clinic Visits in Small Areas of Taiwan

We consider the complete clinic visit records and environmental monitoring data at 50 townships and city districts where ambient air monitoring stations of Taiwan Air Quality Monitoring Stations are located. A Bayesian analysis is carried out using regression spline model on principal components obtained from several pollutant covariables. The appropriate model is selected using Bayesian model averaging. A brief account of our results is provided for the elderly patients group.     

Testing for Spatial Isotropy Under General Designs

Spatial modeling is typically composed of a specification of a mean function and a model for the correlation structure. A common assumption on the spatial correlation is that it is isotropic. This means that the correlation between any two observations depends only on the distance between those sites and not on their relative orientation. The assumption of isotropy is often made due to a simpler interpretation of correlation behavior and to an easier estimation problem under an assumed isotropy. The assumption of isotropy, however, can have serious deleterious effects when not appropriate. In this paper we formulate a test of isotropy for spatial observations located according to a general class of stochastic designs. Distribution theory of our test statistic is derived and we carry out extensive simulations which verify the efficacy of our approach. We apply our methodology to a data set on longleaf pine trees from an oldgrowth forest in the southern United States.     

A spatial model for the needle losses of pine-trees in the forests of Baden-Württemberg: an application of Bayesian structured additive regression

Summary.  The data that are analysed are from a monitoring survey which was carried out in 1994 in the forests of Baden-Württemberg, a federal state in the south-western region of Germany. The survey is part of a large monitoring scheme that has been carried out since the 1980s at different spatial and temporal resolutions to observe the increase in forest damage. One indicator for tree vitality is tree defoliation, which is mainly caused by intrinsic factors, age and stand conditions, but also by biotic (e.g. insects) and abiotic stresses (e.g. industrial emissions). In the survey, needle loss of pine-trees and many potential covariates are recorded at about 580 grid points of a 4 km × 4 km grid. The aim is to identify a set of predictors for needle loss and to investigate the relationships between the needle loss and the predictors. The response variable needle loss is recorded as a percentage in 5% steps estimated by eye using binoculars and categorized into healthy trees (10% or less), intermediate trees (10–25%) and damaged trees (25% or more). We use a Bayesian cumulative threshold model with non-linear functions of continuous variables and a random effect for spatial heterogeneity. For both the non-linear functions and the spatial random effect we use Bayesian versions of P -splines as priors. Our method is novel in that it deals with several non-standard data requirements: the ordinal response variable (the categorized version of needle loss), non-linear effects of covariates, spatial heterogeneity and prediction with missing covariates. The model is a special case of models with a geoadditive or more generally structured additive predictor. Inference can be based on Markov chain Monte Carlo techniques or mixed model technology.