Predicting the vessel lumen area tree-ring parameter of Quercus robur with linear and nonlinear machine learning algorithms
Authors:
Open Access
- 5 November 2018
- journal article
- research article
- Published by Silesian University of Technology in Geochronometria
- Vol. 45 (1) , 211-222
Abstract
Climate-growth relationships in Quercus robur chronologies for vessel lumen area (VLA) from two oak stands (QURO-1 and QURO-2) showed a consistent temperature signal: VLA is highly correlated with mean April temperature and the temperature at the end of the previous growing season. QURO-1 showed significant negative correlations with winter sums of precipitation. Selected climate variables were used as predictors of VLA in a comparison of various linear and nonlinear machine learning methods: Artificial Neural Networks (ANN), Multiple Linear Regression (MLR), Model Trees (MT), Bagging of Model Trees (BMT) and Random Forests of Regression Trees (RF). ANN outperformed all the other regression algorithms at both sites. Good performance also characterised RF and BMT, while MLR, and especially MT, displayed weaker performance. Based on our results, advanced machine learning algorithms should be seriously considered in future climate reconstructions. Climate-growth relationships in Quercus robur chronologies for vessel lumen area (VLA) from two oak stands (QURO-1 and QURO-2) showed a consistent temperature signal: VLA is highly correlated with mean April temperature and the temperature at the end of the previous growing season. QURO-1 showed significant negative correlations with winter sums of precipitation. Selected climate variables were used as predictors of VLA in a comparison of various linear and nonlinear machine learning methods: Artificial Neural Networks (ANN), Multiple Linear Regression (MLR), Model Trees (MT), Bagging of Model Trees (BMT) and Random Forests of Regression Trees (RF). ANN outperformed all the other regression algorithms at both sites. Good performance also characterised RF and BMT, while MLR, and especially MT, displayed weaker performance. Based on our results, advanced machine learning algorithms should be seriously considered in future climate reconstructions.Keywords
This publication has 48 references indexed in Scilit:
- Fiji: an open-source platform for biological-image analysisNature Methods, 2012
- Using Tree Rings to Predict the Response of Tree Growth to Climate Change in the Continental United States during the Twenty-First CenturyEarth Interactions, 2010
- Flash-flood impacts cause changes in wood anatomy of Alnus glutinosa, Fraxinus angustifolia and Quercus pyrenaicaTree Physiology, 2010
- Vessel features of Quercus ilex L. growing under Mediterranean climate have a better climatic signal than tree-ring widthTrees, 2010
- Studying global change through investigation of the plastic responses of xylem anatomy in tree ringsNew Phytologist, 2009
- Earlywood vessel size of oak as a potential proxy for spring precipitation in mesic sitesJournal of Biogeography, 2008
- Ensuring a representative sample of earlywood vessels for dendroecological studies: an example from two ring-porous speciesTrees, 2007
- Cool‐season precipitation in the southwestern USA sinceAD1000: comparison of linear and nonlinear techniques for reconstructionInternational Journal of Climatology, 2002
- On the use of neural networks for dendroclimatic reconstructionsGeophysical Research Letters, 2000
- Reconstructing Summer Temperatures in Northern Fennoscandinavia Back to A.D. 1700 Using Tree-Ring Data from Scots PineArctic and Alpine Research, 1988