PRINCIPAL COMPONENTS ANALYSIS APPLIED TO DENDROCHRONOLOGY
DOI:
https://doi.org/10.21680/2447-3359.2022v8n1ID24096Abstract
This work uses samples of the species Imbuia, (Ocotea porosa (Nees & Mart) Barroso), collected in the city of General Carneiro, southeastern region of the State of Paraná (26º24'01 25 "S 51º24'03 91" W), Brazil, for generate the dendrochronological series of this region. The samples selected for this study were obtained through Cluster Analysis, which classifies objects (samples) based on their similarities. In order to obtain the dendrochronological series, the Principal Component Analysis (PCA) statistical method was applied. After obtaining the Principal Components (PCs), the series were reconstructed without the 1st PC, which is an estimate of the trend that best represents the natural growth of all trees in the place. The average of the series without the 1st PC is the dendrochronological series. The PCA method has several advantages over the traditional method of obtaining the time series, such as rapid data processing, an automated way to remove the natural growth trend in all samples at the same time, and also the fact of integrating a tool Alternating Least Squares (ALS) method to estimate or recover data failures.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Revista de Geociências do Nordeste
This work is licensed under a Creative Commons Attribution 4.0 International License.