http://http://dspace.unitus.it:80 The DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material. 2013-05-18T11:33:24Z http://hdl.handle.net/2067/2135 Title: Estimation of Mediterranean forest attributes by the application of k-NN procedures to multitemporal Landsat ETM+ images Authors: Maselli, Fabio; Chirici, Gherardo; Bottai, Lorenzo; Corona, Piermaria; Marchetti, Marco Abstract: Routinely, applications of nonparametric estimation methods to satellite data for assisting the creation of forest inventories in Northern European countries are stimulating interest in the possible extension of these methods to more complex Mediterranean areas. This is the subject of the current work, which presents an experiment based on the integration of remotely sensed images and sample field measurements aimed at producing forest attribute maps in central Italy. Testing was carried out in an area where 370 geocoded field plots, sampled on a singlestage cluster design, were collected to characterize wood and non-wood forest attributes. These ground data served to apply various k-Nearest Neighbour (k- NN) estimation procedures to multitemporal Landsat 7 ETM+ images in order to map major forest attributes (basal area and simulated leaf area index, LAI). More specifically, the investigation focused on evaluating the effects of using satellite images from different periods of the growing season and spectral metrics of increasing complexity. The results achieved by the examined methods are finally discussed in order to provide guidelines for possible operational utilization. Description: L'articolo è disponibile sul sito dell'editore http://www.tandf.co.uk/journals/ 2004-12-31T23:00:00Z http://hdl.handle.net/2067/2333 Title: K-NN FOREST: a software for the non-parametric prediction and mapping of environmental variables by the k-Nearest Neighbors algorithm Authors: Chirici, Gherardo; Corona, Piermaria; Marchetti, Marco; Mastronardi, Alessandro; Maselli, Fabio; Bottai, Lorenzo; Travaglini, Davide Abstract: In the last decades researchers investigated the possibility of extending the information collected in sampling units during a field survey to wider geographical areas through the use of remotely sensed images. One of the most widely adopted approaches is based on the non-parametric k-Nearest Neighbors (k-NN) algorithm. This contribution describes the software K-NN FOREST we developed to provide a complete tool for the implementation of the k-NN technique to generate spatially explicit estimations (maps) of a response variable acquired in the field by sampling units through the use of remotely sensed data or other ancillary variables. K-NN FOREST is designed to guide the user through a graphic user interface in the different phases of the process. K-NN FOREST is freely available for download and it is designed to run under Windows environment in conjunction with the GIS software IDRISI. 2011-12-31T23:00:00Z