Rg. Pontius et Lc. Schneider, Land-cover change model validation by an ROC method for the Ipswich watershed, Massachusetts, USA, AGR ECO ENV, 85(1-3), 2001, pp. 239-248
Scientists need a better and larger set of tools to validate land-use chang
e models, because it is essential to know a model's prediction accuracy. Th
is paper describes how to use the relative operating characteristic (ROC) a
s a quantitative measurement to validate a land-cover change model. Typical
ly, a crucial component of a spatially explicit simulation model of land-co
ver change is a map of suitability for land-cover change, for example a map
of probability of deforestation. The model usually selects locations for n
ew land-cover change at locations that have relatively high suitability. Th
e ROC can compare a map of actual change to maps of modeled suitability for
land-cover change. ROC is a summary statistic derived from several two-by-
two contingency tables, where each contingency table corresponds to a diffe
rent simulated scenario of future land-cover change. The categories in each
contingency table are actual change and actual non-change versus simulated
change and simulated non-change. This paper applies the theoretical concep
ts to a model of deforestation in the Ipswich watershed, USA. (C) 2001 Else
vier Science B.V. All rights reserved.