Abstract :
Due to the particular geographical location and geological condition, Taiwan suffers from many natural hazards which often cause series property damages and life losses. To reduce the damages and casualty, an effective real-time system for hazard prediction and mitigation is necessary. In this study, a case study for landslide hotspots and hazard factors investigation are analyzed in accordance with spatial data mining technology from massive spatial database. Many different kinds of geospatial data, such as the terrain elevation, land cover types, the distance to roads and rivers, geology maps, and monitoring rainfall data etc., are collected into the database for spatial autocorrelation and spatial regression analysis. In order to guarantee the data quality, the spatial data cleaning is essential to remove the noises, errors, outliers, and inconsistency hiding in the input spatial data sets. The experiment results show that the hot spot analysis exactly has the ability to indicate the hazards locations. In addition, the spatial relationship can be built using the geographically weight regression (GWR) model.
Keywords :
data mining; geology; geomorphology; geophysics computing; hazards; regression analysis; rivers; terrain mapping; visual databases; Taiwan; data quality; effective real-time system; geographical location; geographically weight regression model; geological condition; geology maps; geospatial data mining technology; geospatial database; hazard factors; hazard locations; hazard mitigation; hazard prediction; hot spot analysis; input spatial data sets; land cover types; landslide hotspots; life losses; natural hazards; property damages; rainfall data monitoring; rivers; roads; spatial autocorrelation; spatial data cleaning; spatial regression analysis; terrain elevation; Correlation; Data mining; Geospatial analysis; Hazards; Spatial databases; Terrain factors; geographically weighted regression; hot spots analysis; spatial autocorrelation; spatial data mining;
