An operational GIS expert system for mapping forest soils

Andrew K. Skidmore*, Fiona Watford, Paisan Luckananurug, P. J. Ryan

*Corresponding author for this work

Research output: Contribution to journalArticle

56 Citations (Scopus)


The successful integration of a Bayesian expert system with a commercially available geographic information system (GIS) (Genamap) is described. The package mapped forest soils into five soil landscape classes by utilizing a digital terrain model and vegetation map, as well as knowledge provided by a soil scientist. It is concluded that the map produced by the expert system was as accurate as the map drawn by the soil scientist, within a 95 percent confidence interval. An overall mapping accuracy of 69.8 percent was achieved for the soil maps produced by the expert system, while the conventionally derived map had an accuracy of 73.6 percent.

Original languageEnglish
Pages (from-to)501-511
Number of pages11
JournalPhotogrammetric Engineering and Remote Sensing
Issue number5
Publication statusPublished - May 1996
Externally publishedYes

Fingerprint Dive into the research topics of 'An operational GIS expert system for mapping forest soils'. Together they form a unique fingerprint.

Cite this