Standard Article

Natural Resources Modeling

Environmental Policy and Regulation

  1. Stephen L. Rathbun

Published Online: 15 SEP 2006

DOI: 10.1002/9780470057339.van006

Encyclopedia of Environmetrics

Encyclopedia of Environmetrics

How to Cite

Rathbun, S. L. 2006. Natural Resources Modeling. Encyclopedia of Environmetrics. 4.

Author Information

  1. University of Athens Georgia, GA, USA

Publication History

  1. Published Online: 15 SEP 2006

Abstract

Environmental resources are biotic, including fish and game populations, timber, and grasslands, or abiotic, including water, air, and soil. Interest may focus on either the quantity of available resources (e.g. volume of available timber, or size of fish populations), or their quality (e.g. the concentration of contaminants in air, water, or soil samples). Environmental resource models can lead to a better understanding of environmental processes, and assist managers in making decisions regarding sustainable levels of resource exploitation, remediation of impaired habitats, and the maintenance of biodiversity. This article describes univariate and multivariate methods for predicting the data at unsampled sites from observations at sampled sites. Univariate models are used when the values of the explanatory variables are available at all sites for which predictions are desired. A multivariate approach is required when the explanatory variables are measured only at a sample of sites. For both approaches, models for the spatial correlation structure of the data are considered, including both parametric and nonparametric forms. Methods for model fitting and spatial prediction are described.