A spatial model for sporadic tree species distribution in support of tree oriented silviculture

Abstract

This technical note describes how a spatial model for sporadic tree species distribution in the territory of the Unione di Comuni Montana Colline Metallifere (UCMCM) was built using the Random Forest (RF) algorithm and 48 predictors, including reflectance values from ground cover - provided by satellite sensors - and ecological factors. The P.Pro.SPO.T. project - Policy and Protection of Sporadic tree species in Tuscany forest (LIFE 09 ENV/IT/000087) is currently carried out in this area with the purpose of initiating the implementation of tree oriented silviculture in the Tuscany forests. Tree oriented silviculture aims at obtaining both forest biodiversity protection and local production of valuable timber. After creating a map showing the probability of presence of sporadic tree species, it was possible to identify the most suitable areas for sporadic tree species which are under protection according to the regulation of the Tuscany Region.Using data and software provided free of charge, and applying the RF algorithm, distribution models could be developed in order to identify the most suitable areas for the application of tree oriented silviculture. This can provide a support to forestry planning that includes tree oriented silviculture, thus reducing its implementation cost.