Stone pine stand of Castel Fusano (Rome) burnt on July the 4th 2000 during a huge wildfire. As a consequence of the fire an intensive natural sexual and asexual regeneration began. In order to monitor such a regeneration field surveys were carried out in 2003 and 2006 in sample plots. Remotely sensed high resolution images from Ikonos and Quick Bird were acquired for the same years. The purpose of this work is to test different methodologies for modeling existing relationships between remotely sensed images and ground collected data in order to estimate and to map both sexual and asexual regeneration. For such a purpose different methodologies were tested: step-wise Muliple Linear Regression, Neural Networks (Relevance-Vector-Machine and the Multi-Layered-Perceptron) and the k-Nearest-Neighbors. These activities were carried out within the framework of the GRINFOMED- MEDIFIRE also developing a specific software named Spatial Forest Modeler (SFM) able to analyze existing relationships between remotely sensed variables and data collected in the field in order to identify the best available models to map and estimate the studied variables acquired on the basis of a field sampling design. The present paper presents data collected in the field, analysis and modeling methods and achieved results. The SFM software is also presented.

Forest ecosystems for their important multifunctional value, need a complex and increasing amount of descriptive information to support their management. Ecological and environmental related attributes have became nowadays important as traditional ones, such as wood growing stock and basal area. The correct application of Sustainable Forest Management criteria is boosted by spatial contiguous knowledge of such attributes. For such a reason in the last years a huge number of scientific experiences in the forest area have been concentrated to study the relationship between data acquired in the field and remotely sensed multispectral images. Models based on such relationships can be used to estimate and map forest attributes acquired in the field on the basis of a statistical sampling design. can be sucould not take in consideration spatially structured data. In last years many researches have focused on possible relationships between field data and remote sensed informations derived from multispectral imagery. Modeling these relationships allows to extend inventory data to not explored surfaces. In this paper were discussed results on spatializing forest biometrical attributes, tree heterogeneity and dimensional heterogeneity assessed during an inventory of Mountain Community "Alto Molise" (IS) throw Spot 5 and Lansat TM 7 imagery. For this purpose a multilinear regression and a k-Nearest Neighbor classifier were used.