Numerical reproduction of traditional classifications and automatic vegetation identification

Questions Is it possible to develop an expert system to provide reliable automatic identifications of plant communities at the precision level of phytosociological associations? How can unreliable expert-based knowledge be discarded before applying supervised classification methods? Material We used 3677 releves from Catalonia (Spain), belonging to eight orders of terrestrial vegetation. These releves were classified by experts into 222 low-level units (associations or sub-associations). Methods We reproduced low-level, expert-defined vegetation units as independent fuzzy clusters using the Possibilistic C-means algorithm. Those releves detected as transitional between vegetation types were excluded in order to maximize the number of units numerically reproduced. Cluster centroids were then considered static and used to perform supervised classifications of vegetation data. Finally, we evaluated the classifier's ability to correctly identify the unit of both typical (i.e. training) and transitional releves. Results Only 166 out of 222 (75%) of the original units could be numerically reproduced. Almost all the unrecognized units were sub-associations. Among the original releves, 61% were deemed transitional or untypical. Typical releves were correctly identified 95% of the time, while the efficiency of the classifier for transitional data was only 64%. However, if the second classifier's choice was also considered, the rate of correct classification for transitional releves was 80%. Conclusions Our approach stresses the transitional nature of releve data obtained from vegetation databases. Releve selection is justified in order to adequately represent the vegetation concepts associated with expert-defined units.