Incorporating domain knowledge and spatial relationships into land cover classifications: a rule‐based approach

Abstract

For some tropical regions, remote sensing of land cover yields unacceptable results, particularly as the number of land cover classes increases. This research explores the utility of incorporating domain knowledge and multiple algorithms into land cover classifications via a rule‐based algorithm for a series of satellite images. The proposed technique integrates the fundamental, knowledge‐based interpretation elements of remote sensing without sacrificing the ease and consistency of automated, algorithm‐based processing. Compared with results from a traditional maximum likelihood algorithm, classification accuracy was improved substantially for each of the six land cover classes and all three years in the image series. Use of domain knowledge proved effective in accurately classifying problematic tropical land covers, such as tropical deciduous forest and seasonal wetlands. Results also suggest that ancillary data may be most useful in the classification of historic images, where the greatest improvement was observed relative to results from maximum likelihood. The cost of incorporating contextual knowledge and extensive spatial data sets may be justified, since results from the proposed technique suggest a considerable improvement in accuracy may be achieved.

Acknowledgements

This research was funded by a Fulbright Fellowship and a research grant from the Tropical Conservation and Development Program at the University of Florida (UF). Special thanks go to Dr Graeme Cumming, Dr Hugh Popenoe, and especially Dr Jane Southworth for their comments and input on the manuscript. The author would like to thank the staff at OTS' Palo Verde Research Station and UF's Land Use and Environmental Change Institute (LUECI) for logistical support.