High-resolution stratigraphy of the northernmost concentric raised bog in Europe: Sellevollmyra, Andoya, northern Norway

From the Sellevollmyra bog at Andoya, northern Norway, a 440-cm long peat core covering the last c. 7000 calendar years was examined for humification, loss-on-ignition, microfossils, macrofossils and tephra. The age model was based on a Bayesian wiggle-match of 35 C-14 dates and two historically anchored tephra layers. Based on changes in lithology and biostratigraphical climate proxies, several climatic changes were identified ( periods of the most fundamental changes in italics): 6410-6380, 6230-6050, 5730-5640, 5470-5430, 5340-5310, 5270-5100, 4790-4710, 4890-4820, 4380-4320, 4220-4120, 4000-3810, 3610-3580, 3370-3340 ( regionally 2850-2750; in Sellevollmyra a hiatus between 2960-2520), 2330-2220, 1950, 1530-1450, 1150-840, 730? and c. 600? cal. yr BP. Most of these climate changes are known from other investigations of different palaeoclimate proxies in northern and middle Europe. Some volcanic eruptions seemingly coincide with vegetation changes recorded in the peat, e.g. about 5760 cal. yr BP; however, the known climatic deterioration at the time of the Hekla-4 tephra layer started some decades before the eruption event.

Averaged Extended Tree Augmented Naive Classifier

This work presents a new general purpose classifier named Averaged Extended Tree Augmented Naive Bayes (AETAN), which is based on combining the advantageous characteristics of Extended Tree Augmented Naive Bayes (ETAN) and Averaged One-Dependence Estimator (AODE) classifiers. We describe the main properties of the approach and algorithms for learning it, along with an analysis of its computational time complexity. Empirical results with numerous data sets indicate that the new approach is superior to ETAN and AODE in terms of both zero-one classification accuracy and log loss. It also compares favourably against weighted AODE and hidden Naive Bayes. The learning phase of the new approach is slower than that of its competitors, while the time complexity for the testing phase is similar. Such characteristics suggest that the new classifier is ideal in scenarios where online learning is not required.