Improvement of an intelligent system to aid in lithostratigraphic and geochemical correlation, Mono and Inyo Tephras, California

We are developing an intelligent system for tephra correlation to aid geologists in interpreting eruption patterns in volcanic chains and fields. The intelligent system is used to define groups of tephra source vents and to correlate tephra layers based on combination of geochemical data and lithostratigraphic characteristics (Bursik and Rogova, 2006). Understanding the eruption history of volcanic fields from stratigraphic studies is important for forecasting future eruptive behavior and hazards.;The data processing is performed by a suite of both unsupervised and supervised classifiers, built and combined within the framework of the Belief Theories (Shafer, 1976, Smets and Kennes, 1994, Smets and Ristic, 2004). The spatial distribution of eruption deposits is important to determining eruption patterns and the correlation of tephra layers. I have developed algorithms to calculate isopleth maps of thickness, lithic and pumice size, which are used in the processing of the lithostratigraphic data. Geochemical data for defining groups of tephra sources are processed by a suit of fuzzy k-means classifiers. Improved clustering results of geochemical data are achieved by the fusion of individual clustering results with an evidential combination method (Rogova et al., 2008).;The intelligent system aids correlation by showing matches and disparities between data patterns from different outcrops that may have been overlooked. The intelligent system produces a useful recognition result, while dealing with the uncertainty from sparse data and imprecise description of layer characteristics.