Statistical assessment of geographic areas of compliance with air quality standards

Fuentes, Montserrat

doi:10.1029/2003jd003672

Cited by 12 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second model, referred to as the seasonal model, is a geostatistical model that predicts the FHDA field from the network values using standard best linear unbiased prediction, or kriging (see Cressie [1] or Stein [17] for more details on kriging). This seasonal model is similar to the model proposed by Fuentes [6], except that the region of interest here is much smaller and so can be assumed to be spatially and temporally stationary. A third approach that will be used as a benchmark estimates the FHDA field by way of a thin plate spline (see Green and Silverman [11] or Hastie and Tibshirani [12] for details on thin plate splines).…”

Section: Introductionmentioning

confidence: 92%

“…Stationarity for this field cannot be assumed (see, for example, Fuentes [6]) and, indeed, some heterogeneity might be modeled using additional covariates. Generally, meteorological data, such as temperature, is difficult to use for the daily model approach because at any time point the temperatures at two locations can vary greatly, and meteorological measurements are generally gathered only on a coarse spatial scale.…”

Section: Discussionmentioning

confidence: 99%

“…1 shows a region around the Research Triangle Park (RTP) in North Carolina in which the models will be interpolated onto a 15 × 15 grid. These data are a subset of the 513 stations covering the eastern United States used by Fuentes [6] and can be obtained from the web through http://www.cgd.ucar.edu/stats/Data.…”

Section: Ozone Monitoring Datamentioning

confidence: 99%

See 2 more Smart Citations

Statistical models for monitoring and regulating ground‐level ozone

Gilleland¹,

Nychka²

2005

Environmetrics

View full text Add to dashboard Cite

The U.S. Environmental Protection Agency's (EPA) National Ambient Air Quality Standard (NAAQS) for ground-level ozone is now based on the fourth-highest daily maximum 8-hour average ozone level (FHDA).Standard geostatistical models may not be appropriate for interpolating such a statistic off of a network of monitoring sites. In this paper we compare the performance of different statistical models in predicting this standard at locations where monitors are not located. We give special attention to two models: a daily model that uses an autoregression to account for spatial and temporal dependence, and a seasonal model that assumes the FHDA field is Gaussian and employs spatial statistical techniques. Based on five seasons of ozone data collected in and around North Carolina, we find that the daily model is superior enough to the seasonal model to warrant its added complexity.

show abstract

Section: Introductionmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Statistical models for monitoring and regulating ground‐level ozone

Gilleland¹,

Nychka²

2005

Environmetrics

View full text Add to dashboard Cite

show abstract

“…The proposed method is illustrated with daily maximum eight‐hour average data at a network of monitoring sites in the Eastern U.S. from April 1995 through October 1999. These data have been widely used in environmental statistics (see, e.g., Fuentes, ; Gilleland & Nychka, ; Zhang et al, ) and can be obtained from https://www.image.ucar.edu/Data/Ozmax. Following the preprocessing steps in Gilleland and Nychka (), the daily maximum eight‐hour ozone average with unit parts per billion (ppb) at station s and day u , denoted by O ( s , u ), is assumed to have the following structure:

O (s, u) = μ (s, u) + \tilde{O} (s, u),

where

μ false(bolds, u false) = a false(bolds false) + \sum_{j = 1}^{3} false{b_{j} \cos false(2 π j u false/ 184 false) + c_{j} \sin false(2 π j u false/ 184 false) false}

, which models the seasonal effect.…”

Section: Analysis Of Eastern Us Ozone Datamentioning

confidence: 99%

An additive approximate Gaussian process model for large spatio‐temporal data

Konomi

Kang

2019

Environmetrics

View full text Add to dashboard Cite

Motivated by a large ground‐level ozone data set, we propose a new computationally efficient additive approximate Gaussian process. The proposed method incorporates a computational‐complexity‐reduction method and a separable covariance function, which can flexibly capture various spatio‐temporal dependence structures. The first component is able to capture nonseparable spatio‐temporal variability, whereas the second component captures the separable variation. Based on a hierarchical formulation of the model, we are able to utilize the computational advantages of both components and perform efficient Bayesian inference. To demonstrate the inferential and computational benefits of the proposed method, we carry out extensive simulation studies assuming various scenarios of an underlying spatio‐temporal covariance structure. The proposed method is also applied to analyze large spatio‐temporal measurements of ground‐level ozone in the Eastern United States.

show abstract

“…Based on the work of Sahu, Yip, and Holland (2009), Fuentes (2003, 2005, Fuentes and Raftery (2005), and McMillan et al (2010), we define the process model as…”

Section: Process Modelmentioning

confidence: 99%

Development of a hierarchical Bayesian network algorithm for land surface data assimilation

Qin

Xuan-ji

2012

International Journal of Remote Sensing

View full text Add to dashboard Cite

A hierarchical Bayesian network (HBN) algorithm is developed for data assimilation (DA) and tested with an instance of soil moisture assimilation from a hydrological model and ground observations. In essence, the HBN is a framework that can statistically describe Bayesian models and capture the dependencies in the models more realistically than non-hierarchical Bayesian models. In this work, DA divided into three levelsdata, process, and parameter -and conditional probability models are defined for each level. The data model mainly deals with the scale differences of multi-source data in DA, while the process model is designed to take account of the non-stationary process. Moreover, both the temporal auto-correlation and the spatial correlation are considered in the process model. Soil moisture observations from the Soil Moisture Experiment in 2003 (SMEX03) and Variable Infiltration Capacity (VIC) model are sequentially assimilated with HBN. The result shows that the assimilation with HBN provides spatial and temporal distribution information of soil moisture and the assimilation result agrees well with the ground observations. IntroductionThe basic tenet of data assimilation (DA) is to combine complementary information from measurements and dynamic models into an optimal estimate of the geophysical fields of interest, generally defined as states (Reichle 2008). In doing so, DA systems interpolate and extrapolate observations and provide estimates at the scales required by the applicationboth in the temporal and spatial domains. Meanwhile, DA estimates the states when the unobserved physical parameters have a complicated functional dependence on the states estimated. These characteristics make DA one of the indispensable methods in Earth system science. DA has wide applications also across the range of the Earth sciences. One of the major applications is in the production of operational weather forecasts; other applications include oceanography, atmospheric chemistry, climate studies, and hydrology. Currently, DA is a key technique for obtaining spatial-temporal distribution and variation information of multiple Earth science parameters in the global, continental, and regional scales with the aid of a long time series of data records.The goal of DA is to effectively combine multi-source data with the associated uncertainty to estimate the state of interest. The theory of DA rests on the mathematical

show abstract

Statistical assessment of geographic areas of compliance with air quality standards

Cited by 12 publications

References 34 publications

Statistical models for monitoring and regulating ground‐level ozone

Statistical models for monitoring and regulating ground‐level ozone

An additive approximate Gaussian process model for large spatio‐temporal data

Development of a hierarchical Bayesian network algorithm for land surface data assimilation

Contact Info

Product

Resources

About