skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Empirical Bayes regionalization methods for spatial stochastic processes

Abstract

Many geophysical properties can be described as spatial stochastic processes, including spatially correlated hydraulic conductivity fields. Use of regional data can potentially improve estimation of such processes. The authors consider the case in which observations at each of several sites are described by a general linear model, while the parameters of these models arise from a common regional distribution. Parametric empirical Bayes methods enable the determination of the parameters of the regional distribution via maximum likelihood. However, such methods have not been utilized for spatial stochastic processes. They develop the application of a simple iterative technique for maximum likelihood estimation of the regional parameters, and demonstrate its use with a common parameterization of the spatial covariance structure. Synthetic data tests show the potential for substantial reduction in estimation risk through use of such techniques.

Authors:
 [1];  [2];  [3]
  1. Gradient Corp., Cambridge, MA (United States)
  2. Duke Univ., Durham, NC (United States)
  3. Ambiotec, Harlingen, TX (United States)
Publication Date:
OSTI Identifier:
5945814
Resource Type:
Journal Article
Journal Name:
Water Resources Research; (United States)
Additional Journal Information:
Journal Volume: 27:1; Journal ID: ISSN 0043-1397
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES; GROUND WATER; FLOW MODELS; ENVIRONMENTAL TRANSPORT; EXPECTATION VALUE; FLUID FLOW; HYDRAULIC CONDUCTIVITY; HYDROLOGY; PARAMETRIC ANALYSIS; RISK ASSESSMENT; STATISTICAL MODELS; STOCHASTIC PROCESSES; HYDROGEN COMPOUNDS; MASS TRANSFER; MATHEMATICAL MODELS; OXYGEN COMPOUNDS; WATER; 540310* - Environment, Aquatic- Basic Studies- (1990-); 580000 - Geosciences

Citation Formats

Butcher, J B, Medina, Jr, M A, and Marin, C M. Empirical Bayes regionalization methods for spatial stochastic processes. United States: N. p., 1991. Web. doi:10.1029/90WR01879.
Butcher, J B, Medina, Jr, M A, & Marin, C M. Empirical Bayes regionalization methods for spatial stochastic processes. United States. https://doi.org/10.1029/90WR01879
Butcher, J B, Medina, Jr, M A, and Marin, C M. 1991. "Empirical Bayes regionalization methods for spatial stochastic processes". United States. https://doi.org/10.1029/90WR01879.
@article{osti_5945814,
title = {Empirical Bayes regionalization methods for spatial stochastic processes},
author = {Butcher, J B and Medina, Jr, M A and Marin, C M},
abstractNote = {Many geophysical properties can be described as spatial stochastic processes, including spatially correlated hydraulic conductivity fields. Use of regional data can potentially improve estimation of such processes. The authors consider the case in which observations at each of several sites are described by a general linear model, while the parameters of these models arise from a common regional distribution. Parametric empirical Bayes methods enable the determination of the parameters of the regional distribution via maximum likelihood. However, such methods have not been utilized for spatial stochastic processes. They develop the application of a simple iterative technique for maximum likelihood estimation of the regional parameters, and demonstrate its use with a common parameterization of the spatial covariance structure. Synthetic data tests show the potential for substantial reduction in estimation risk through use of such techniques.},
doi = {10.1029/90WR01879},
url = {https://www.osti.gov/biblio/5945814}, journal = {Water Resources Research; (United States)},
issn = {0043-1397},
number = ,
volume = 27:1,
place = {United States},
year = {Tue Jan 01 00:00:00 EST 1991},
month = {Tue Jan 01 00:00:00 EST 1991}
}