Embedding a geographic information system in a decision support system for landslide hazard monitoring

In this paper we present an application that exploits a geographic information system as a front-end of a complex information system supporting the management of landslide hazard in Valtellina, an alpine valley in Northern Italy. A decision support system (EYDENET, operational since October 1996), incorporating a geographic information system and a data interpreter based on artificial intelligence techniques, processes the readings of the 250 most significant instruments of a monitoring net of about 1000 sensors installed on different landslides in several alpine valleys. Data gathered by extensometers, clinometers and pluviometers, to check both movements of rocks and climatic conditions which could affect them, are processed by EYDENET, that provides on-line interpretation of data, helps the users analyse them, and generates natural language explanations and alarm messages for the people responsible for the environmental management and the civil protection.