Using spectral diversity and heterogeneity measures to map habitat mosaics: An example from the Classical Karst

Questions: Can we map complex habitat mosaics from remote-­sensing data? In doing this, are measures of spectral heterogeneity useful to improve image classification performance? Which measures are the most important? How can multitemporal data be integrated in a robust framework? Location: Classical Karst (NE Italy). Methods: First, a habitat map was produced from field surveys. Then, a collection of 12 monthly Sentinel-­2 images was retrieved. Vegetation and spectral heterogeneity (SH) indices were computed and aggregated in four combinations: (1) monthly layers of vegetation and SH indices; (2) seasonal layers of vegetation and SH indices; (3) yearly layers of SH indices computed across the months; and (4) yearly layers of SH indices computed across the seasons. For each combination, a Random Forest clas- sification was performed, first with the complete set of input layers and then with a subset obtained by recursive feature elimination. Training and validation points were independently extracted from field data. Results: The maximum overall accuracy (0.72) was achieved by using seasonally ag- gregated vegetation and SH indices, after the number of vegetation types was re- duced by aggregation from 26 to 11. The use of SH measures significantly increased the overall accuracy of the classification. The spectral β-­diversity was the most im- portant variable in most cases, while the spectral α-­diversity and Rao's Q had a low relative importance, possibly because some habitat patches were small compared to the window used to compute the indices. Conclusions: The results are promising and suggest that image classification frame- works could benefit from the inclusion of SH measures, rarely included before. Habitat mapping in complex landscapes can thus be improved in a cost-­and time-­effective way, suitable for monitoring applications.