Clustering misaligned dependent curves applied to varved lake sediment for climate reconstruction

Abstract

In this paper we introduce a novel functional clustering method, the Bagging Voronoi K-Medoid Aligment (BVKMA) algorithm, which simultaneously clusters and aligns spatially dependent curves. It is a nonparametric statistical method that does not rely on distributional or dependency structure assumptions. The method is motivated by and applied to varved (annually laminated) sediment data from lake Kassjön in northern Sweden, aiming to infer on past environmental and climate changes. The resulting clusters and their time dynamics show great potential for seasonal climate interpretation, in particular for winter climate changes

Multiresolution clustering of dependent functional data with application to climate reconstruction

“…The properties of each varve reflect to a large extent weather conditions and internal biological processes in the lake the year that varve was deposited. The seasonal patterns have previously been analysed by Arnqvist et al (), Arnqvist and de Luna (), and Abramowicz et al ().…”

“…More recently, a growing interest in clustering spatially dependent functional data has emerged. Examples of spatial functional clustering methods are given in Giraldo, Delicado, and Mateu (), Secchi, Vantini, and Vitelli (), and Abramowicz et al (). Giraldo et al () present a hierarchical method that incorporates the spatial information in the clustering procedure by weighting the dissimilarity matrix (based on the functional shapes) with the spatial dependence expressed through variograms.…”

“…The local representatives are then clustered, and the resulting cluster labels bagged together over the random tessellations to form a final clustering. Abramowicz et al () propose a clustering method for misaligned spatially dependent functional data, the bagging Voronoi K ‐medoid alignment (BVKMA) method. BVKMA jointly handles clustering, misalignment, and spatial dependency using the bagging Voronoi strategy.…”

Advances in spatial functional statistics

“…Abramowicz et al (2016) propose a functional non-parametric clustering method which simultaneously clusters and aligns spatially dependent curves. Balzanella et al (2016) address the problem of getting order statistics for georeferenced functional data by means of depth functions for spatially dependent functional data.…”

“…Abramowicz et al (2016) propose a novel method, the Bagging Voronoi K-medoid Alignment algorithm (BVKMA), that jointly handles clustering, misalignment, and spatial dependence of functional data. As claimed by the authors, this method is the first proposal in the literature that jointly deals with these three sources of variability.…”