Making objective forest stand maps of mixed managed forest with spatial interpolation and multi-criteria decision analysis

Spatial interpolation and multi-criteria decision analysis (MCDA) capabilities of geographic information systems have the potential to create new approaches to forest management. In this study, the regularized spline with tension (RST) interpolation method and ELECTRE TRI MCDA was used to predict forest stand volumes in an area characterized by even-aged stands with heterogeneous structures in Turkey. Sampling data (1050 circular sample plots) were obtained from the National forest inventory. For each species and diameter class, a map of the predicted volume per ha was obtained using the RST method. By repeating the same process for the eight species occurring in the study area, 31 volume maps were produced. The accuracy of these prediction maps was assessed at pixel (20 x 20 m) and area scale (per ha). An accuracy of more than 97% was achieved at the pixel level, whereas a minimum accuracy of 86% was achieved for the area-based estimations. In addition, predicted values from the above 31 volume maps were compared with the observed values from management plan reports obtained from the Government Institute responsinble for forest management plans. The comparisons showed an accuracy of predictions of 21, 14, 4, and 2% for Calabrian pine, Oriental beech, black pine and oak species, respectively. Following interpolation, volume prediction maps were geo-computed, and a volume-based stand map was produced. The 890 different combinations of species composition and diameter classes were classified according to expert knowledge by the use of ELECTRE TRI MCDA, obtaining a final stand type map representing 70 different profile categories based on species mixture rates and diameter classes for the area analyzed.