Cel To develop an expert system to be used as a decision tool towardsprotecting forest land.The proposed expert system will bebased on remotely sensed Multi-date Satellite Imagery,Geographical Information Systems, Global Positioning Signals,Mathematical Modeling and Advanced Visualization Techniques.The system will consist of the following mainparts: (i) an electronic database within a GeographicalInformation System to provide information on forest areas, (ii) amathematical model to process the database information andclassify forested areas according to their potentiality for fireeruption, (iii) a visualization system to provide an on-linepixmap representation of the potential of fire eruption on adigital map of the area of interest. To construct the expertsystem, representative forest-fire affected areas from twoMediterranean countries, will be studied.The electronic database will be incorporated, structured andlayered in a Geographical Information System (EASI/PACE) and willinclude: multi-date satellite data, digitized geophysical data,land-use data and socio-economic parameters pertaining to factorsthat affect intentional fire eruption.Image processing and photo-interpretation techniques will beapplied on geophysical maps and multi-date satellite imagery(LANDSAT TM, LANDSAT TM+ERS-1 SAR, LANDSAT TM+SPOT PAN) todetermine geophysical parameters such as: (I) biomass, (II) soilmoisture, and land use data such as: (I) illegal residentialdevelopment across forest roads and at the outskirts of theexisting forest areas, and (II) intensity of illegal housingconstruction. Change detection techniques such as: PostClassification Comparison, Principal Component Analysis (PCA) andImage Rationing/Differencing will be applied on multi-datesatellite data of fire-affected areas, to determine land-usechange data.Critical parameters will be determined, by cross-correlatinggeophysical, land-use change, and socio-economic data pertainingto areas that have been affected by fire eruption. Theseparameters will serve as input to the mathematical model. Adeductive neural network classification algorithm will bedeveloped to classify forested areas according to theirpotentiality for fire eruption.The mathematical model will be integrated with the GIS system(EASI/PACE) to provide automatic access to the input parametersresiding at the GIS database. Also, a visualization softwarepackage (AVS) will be used to integrate the mathematical modelwith advanced visualization techniques. Dziedzina nauki natural sciencescomputer and information sciencesdatabasesnatural sciencesearth and related environmental sciencesphysical geographycartographygeographic information systemsengineering and technologymechanical engineeringvehicle engineeringaerospace engineeringsatellite technologynatural sciencescomputer and information sciencesartificial intelligenceexpert systemsnatural sciencesmathematicsapplied mathematicsmathematical model Program(-y) FP3-ENV 1C - Specific research and technological development programme (EEC) in the field of the environment, 1990-1994 Temat(-y) 040103 - Wildfires Zaproszenie do składania wniosków Data not available System finansowania CSC - Cost-sharing contracts Koordynator INTEGRATED INFORMATION SYSTEMS SA Wkład UE Brak danych Adres 72-74,SALAMINOS STREET 17675 KALLITHEA Grecja Zobacz na mapie Koszt całkowity Brak danych Uczestnicy (4) Sortuj alfabetycznie Sortuj według wkładu UE Rozwiń wszystko Zwiń wszystko Advanced Technology Information Systems Grecja Wkład UE Brak danych Adres 5,Agiou Nikolaou 15772 Athens Zobacz na mapie Koszt całkowity Brak danych CENTRO NACIONAL DE INFORMACAO GEOGRAFICA Portugalia Wkład UE Brak danych Adres 82,Tagus Park, Nucleo Central Sala 301 2780-920 OEIRAS Zobacz na mapie Koszt całkowity Brak danych Centro di Ricerche e Servizi Avanzati per la Formazione Scienter Włochy Wkład UE Brak danych Adres Via Val d'Aposa 3 40123 Bologna Zobacz na mapie Koszt całkowity Brak danych National Technical University of Athens Grecja Wkład UE Brak danych Adres 9,Iroon Polytechniou Avenue 15780 Athens Zobacz na mapie Koszt całkowity Brak danych