The Ipswich watershed in northeastern Massachusetts, USA, is experiencing i
mportant land-use changes, which are contributing to severe environmental p
roblems such as eutrophication, ground water depletion and loss of wildlife
. The objective of this paper is to model deforestation between 1971, 1985
and 1991 in the watershed of the Ipswich River in Massachusetts, USA, where
most of the forest loss is attributable to new residential development. Th
e maps of suitability for deforestation are calibrated with maps of real ch
ange between 1971 and 1985 by using logistic regression, multi-criteria ana
lysis and spatial filters. The maps of 1971 and 1985 serve also as the basi
s to extrapolate the quantity of predicted future deforestation. Then, the
calibrated suitability maps and extrapolated quantities predict the locatio
n of deforestation between 1985 and 1991. The predicted deforestation maps
are validated with the map of real forest loss of 1985-1991. relative opera
ting characteristic (ROC) and variations of the Kappa index of agreement (K
no, Klocation and Kquantity) measure the validation. For most simulation ru
ns, Kno = 93%, Klocation = 8% and Kquantity = 100%. The best predictor of q
uantity of deforestation from 1985 to 1991 is linear extrapolation forward
in time of the deforestation that occurred from 1971 to 1985. It is difficu
lt to predict the exact locations of deforestation in the watershed because
only 2% of the watershed is deforested from 1971 to 1991, the patches of d
eforestation are scattered evenly across the landscape, and the some of the
most important variables are not readily available in digital form. Nevert
heless, the best predictor of location of deforestation (ROC = 70%) is a su
itability map that uses a spatial filter and multi-criteria evaluation of e
levation, slope, and proximity to existing residential areas. The locations
that are most threatened are those that are unprotected, near existing res
idential development and in towns where the demand for new residential deve
lopment is high. (C) 2001 Elsevier Science B.V. All rights reserved.