Bayesian Hot Spot Detection in the Presence of a Spatial Trend: Application to Total Nitrogen Concen

Extreme concentrations of water quality variables can cause serious adverse effects in an ecosystem, making their detection an important environmental issue. In Chesapeake Bay, a decreasing gradient of total nitrogen concentration extends from the highest values in the north at the mouth of the Susquehanna river to the lowest values in the south near the Atlantic ocean. We propose a general definition of ‘hot spot’ that includes previous definitions and is appealing for processes with a spatial trend. We model these data using the Bayesian Transformed Gaussian (BTG) random field model proposed by De Oliveira et al. (1997), which combines the Box–Cox family of power transformations and a spatial trend. The median function is used as the measure of spatial trend, which offers some advantages over the customarily used mean function. The BTG model is fitted by an enhanced Monte Carlo algorithm, and the methodology is applied to the nitrogen concentration data. Copyright © 2002 John Wiley & Sons, Ltd.

[1]  A. Gelfand,et al.  Bayesian Variogram Modeling for an Isotropic Spatial Process , 1997 .

[2]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[3]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[4]  Stephen L. Rathbun,et al.  Spatial modelling in irregularly shaped regions: Kriging estuaries , 1998 .

[5]  L. Canter,et al.  Nitrates in Groundwater , 1996 .

[6]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[7]  G. Fogg,et al.  Spatial Variation in Nitrogen Isotope Values Beneath Nitrate Contamination Sources , 1998 .

[8]  Robert M. Summers,et al.  The validity of a simple statistical model for estimating fluvial constituent loads: An Empirical study involving nutrient loads entering Chesapeake Bay , 1992 .

[9]  T. C. Haas,et al.  Model-based geostatistics. Discussion. Authors' reply , 1998 .

[10]  K. Moore,et al.  Chesapeake Bay: An Unprecedented Decline in Submerged Aquatic Vegetation , 1983, Science.

[11]  On the identification of toxic hot spots using measures of the sediment quality triad , 1997 .

[12]  P. L. Lietman,et al.  Synthesis of nutrient and sediment data for watersheds within the Chesapaeake Bay drainage basin , 1995 .

[13]  V. D. Oliveira,et al.  Bayesian prediction of clipped Gaussian random fields , 2000 .

[14]  M. Stein,et al.  A Bayesian analysis of kriging , 1993 .

[15]  “Green” Accounting for the Chesapeake Bay , 1997 .

[16]  Roman Viveros,et al.  Inference about the mean in log-regression with environmental applications , 1997 .

[17]  G. Brush.  History and Impact of Human Activities on Chesapeake Bay , 1997 .

[18]  B. Kedem,et al.  Bayesian Prediction of Transformed Gaussian Random Fields , 1997 .

[19]  Donald E. Myers,et al.  To be or not to be... stationary? That is the question , 1989 .