<abstract xmlns="http://www.w3.org/1999/xhtml"><p> We applied two widely-used methods for data partitioning - constrained incremental sum-of-squares (CONISS) and Optimal Partitioning (OP) along with two supplementary methods, a Kohonen artificial neural network (self-organising map, SOM) and the indicator value (IndVal) index, for the quantitative analysis of subfossil chironomid assemblages from a palaeolake in Central Poland. The samples, taken from 79 core depths, were divided into 5-11 groups (five by SOM, seven by CONISS, 11 by OP), for which different numbers of indicator taxa were determined with the use of the IndVal index (18 for CONISS, 15 for SOM, 11 for OP). Only six indicator taxa were common to all three methods. The number of highly specific (p &lt; 0.001) taxa was highest for SOM. Only the SOM analysis clearly reflected the rate of the changes in chironomid assemblages, which occurred rapidly in the Late Glacial (as a result of greater climate variability) and slowly in the Holocene (as a reflection of slow long-term changes in the local habitat, such as paludification). In summary, we recommend using SOM and the IndVal index in combination with CONISS and/or OP in order to detect different aspects of temporal variability in complex multivariate palaeoecological data. </p></abstract>

We applied two widely-used methods for data partitioning - constrained incremental sum-of-squares (CONISS) and Optimal Partitioning (OP) along with two supplementary methods, a Kohonen artificial neural network (self-organising map, SOM) and the indicator value (IndVal) index, for the quantitative analysis of subfossil chironomid assemblages from a palaeolake in Central Poland. The samples, taken from 79 core depths, were divided into 5-11 groups (five by SOM, seven by CONISS, 11 by OP), for which different numbers of indicator taxa were determined with the use of the IndVal index (18 for CONISS, 15 for SOM, 11 for OP). Only six indicator taxa were common to all three methods. The number of highly specific (p < 0.001) taxa was highest for SOM. Only the SOM analysis clearly reflected the rate of the changes in chironomid assemblages, which occurred rapidly in the Late Glacial (as a result of greater climate variability) and slowly in the Holocene (as a reflection of slow long-term changes in the local habitat, such as paludification). In summary, we recommend using SOM and the IndVal index in combination with CONISS and/or OP in order to detect different aspects of temporal variability in complex multivariate palaeoecological data.

Kohonen Artificial Neural Networks and the IndVal Index as Supplementary Tools for the Quantitative Analysis of Palaeoecological Data

Department of Invertebrate Zoology and Hydrobiology, Faculty of Biology and Environmental Protection, University of Łódź, 12/16 Banacha Str., 90-237 Łódź, Poland

Department of Ecology and Vertebrate Zoology, Faculty of Biology and Environmental Protection, University of Łódź, 12/16 Banacha Str., 90-237 Łódź, Poland

GADAM Centre of Excellence, Institute of Physics – CSE, Silesian University of Technology, Konarskiego 22B, 44-100 Gliwice, Poland

Department of Biology, University of Bergen, PO Box 7803, N-5020 Bergen, Norway; and Environmental Change Research Centre, University College London, London, WC1E 6BT, UK

Geochronometria

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

We applied two widely-used methods for data partitioning - constrained incremental sum-of-squares (CONISS) and Optimal Partitioning (OP) along with two...

Kohonen Artificial Neural Networks and the IndVal Index as Supplementary Tools for the Quantitative Analysis of Palaeoecological Data

Publié en ligne: 03 déc. 2015

Pages: -

Reçu: 06 août 2014

Accepté: 26 oct. 2015

DOI: https://doi.org/10.1515/geochr-2015-0021

Mots clés
Late Quaternary, Chironomidae, self-organising map (SOM), CONISS, Optimal Parti-tioning

© 2015

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Kohonen Artificial Neural Networks and the IndVal Index as Supplementary Tools for the Quantitative Analysis of Palaeoecological Data

Publié en ligne: 03 déc. 2015

Pages: -

Reçu: 06 août 2014

Accepté: 26 oct. 2015

DOI: https://doi.org/10.1515/geochr-2015-0021

Mots clésLate Quaternary, Chironomidae, self-organising map (SOM), CONISS, Optimal Parti-tioning

© 2015

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Late Quaternary, Chironomidae, self-organising map (SOM), CONISS, Optimal Parti-tioning