Introduction to Ordinary Least Squares (OLS) and Geographically Weighted Regression (GWR) Methods in Spatial Modeling of Land Use Effects on Water Quality

Authors
M. Erfanian
M. Hosseinkhah
A. Alijanpour
Abstract
Water quality is an important element in agriculture practices, drinking water, industry, etc. Different land use types on the watershed area have different effects on the river water in terms of quantity, quality, physico-chemical and biology. To the best of our knowledge, the spatial modeling of land use effects on water quality has not been investigated in Iran. By spatial modeling, it is possible to map the spatial variability of positive and/or negative effects of each land use type on water quality indicators. Based on spatial maps, it is easy to identify and manage non-point sources pollutants over the watershed area. The main objective of this paper is to introduce the Ordinary Least Squares (OLS) and the Geographically Weighted Regression (GWR) models for spatial modeling of land use effects on water quality. Most of recent researches show that the GWR model is more effective and efficient than the OLS method. So, its application for watershed management studies and researches is highly recommended.
Keywords
Water quality
Land use
OLS and GWR