Answers are grounded in this paper and cite their sources.
Continuous phenomena such as semi‐natural heathland vegetation cannot be adequately represented by conventional image classification routines. Measures of the probability of class membership derived as a by‐product of the widely used maximum likelihood classification were, however, found to be significantly correlated to heathland composition. Furthermore, ecological trends in the vegetation ground data revealed by an ordination were associated with systematic variations in the probabilities of class membership. Mapping the probabilities of class membership will therefore model the continuous character of such vegetation more appropriately than the class ificationfrom which the probabilities were dervied.
No takes yet. Share an insight, caveat, or question.
Foody et al. (1996) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: