摘要：This study tests novel methods for automatically identifying annual layers in a shallow Antarctic ice core (WDC05Q) using images that were collected with an optical scanner at the US National Ice Core Laboratory. A new method of optimized variance maximization (OVM) modeled the density-related changes in annual layer thickness directly from image variance. This was done by using multi-objective complex (MOCOM) parameter optimization to drive a low-pass filtering scheme. The OVM-derived changes in annual layer thickness corresponded well with the results of an independent glaciochemical interpretation of the core. Individual annual cycles in image brightness were then identified by using OVM results to apply a depth-varying low-pass filter and fitting a second-order polynomial to a locally detrended neighborhood. The resulting map of annual cycles agreed to within 1% of the overall annual count of the glaciochemical interpretation. Agreement on the presence of specific annual layer features was 96%. It was also shown that the MOCOM parameter optimization could calibrate the image-based results to match directly the date of a specific volcanic marker.
