Please use this identifier to cite or link to this item:
Authors: Kuhl, Eileen
Zang, Christian
Esper, Jan
Riechelmann, Dana F. C.
Büntgen, Ulf
Briesch, Martin
Reinig, Frederick
Römer, Philipp
Konter, Oliver
Schmidhalter, Martin
Hartl, Claudia
Title: Using machine learning on tree-ring data to determine the geographical provenance of historical construction timbers
Online publication date: 9-Jun-2023
Year of first publication: 2023
Language: english
Abstract: Dendroclimatology offers the unique opportunity to reconstruct past climate at annual resolution and wood from historical buildings can be used to extend such information back in time up to several millennia. However, the varying and often unclear origin of timbers affects the climate sensitivity of individual tree-ring samples. Here, we compare tree-ring width and density of 143 living larch (Larix decidua Mill.) trees at seven sites along an elevational transect from 1400 to 2200 m asl and 99 historical tree-ring series to parametrize state-of-the-art classification models for the European Alps. To achieve geographical provenance of the historical series, nine different supervised machine learning algorithms are trained and tested in their capability to solve our classification problem. Based on this assessment, we consider a tree-ring density-based and a tree-ring width-based dataset for model building. For each of these datasets, a general not species-related model and a larch-specific model including the cyclic larch budmoth influence are built. From the nine tested machine learning algorithms, Extreme Gradient Boosting showed the best performance. The density-based models outperform the ring-width models with the larch-specific density model reaching the highest skill (f1 score = 0.8). The performance metrics reveal that the larch-specific density model also performs best within individual sites and particularly in sites above 2000 m asl, which show the highest temperature sensitivities. The application of the specific density model for larch allows the historical series to be assigned with high confidence to a particular elevation within the valley. The procedure can be applied to other provenance studies using multiple tree growth characteristics. The novel approach of building machine learning models based on tree-ring density features allows to omit a common period between reference and historical data for finding the provenance of relict wood and will therefore help to improve millennium-length climate reconstructions.
DDC: 550 Geowissenschaften
550 Earth sciences
910 Geografie
910 Geography and travel
Institution: Johannes Gutenberg-Universität Mainz
Department: FB 09 Chemie, Pharmazie u. Geowissensch.
Place: Mainz
Version: Published version
Publication type: Zeitschriftenaufsatz
Document type specification: Scientific article
License: CC BY
Information on rights of use:
Journal: Ecosphere
Pages or article number: e4453
Publisher: Wiley
Publisher place: Weinheim
Issue date: 2023
Publisher DOI: 10.1002/ecs2.4453
Appears in collections:DFG-491381577-G

Files in This Item:
  File Description SizeFormat
using_machine_learning_on_tre-20230609085557154.pdf2.15 MBAdobe PDFView/Open