Predicting the vessel lumen area tree-ring parameter of &lt;i&gt;Quercus robur&lt;/i&gt; with linear and nonlinear machine learning algorithms

Jevšenak, Jernej; Džeroski, Sašo; Levanič, Tom

doi:10.1515/geochr-2015-0097

Cited by 9 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, given that our study occurred in a subtropical area, our focus turned to using machine learning methods. Artificial neural network (ANN) was considered as a better choice for careful assessment of complex climate-growth relationships [20,[36][37][38][39][40][41][42][43][44][45][46][47][48][49][50]. However, the learning method process of an ANN is a "black box operation" [51][52][53], meaning that it is sensitive to overfitting and ANNs have difficulty evaluating the contribution of each variable to the results, from a statistical point of view [53,54].…”

Section: Introductionmentioning

confidence: 99%

Insights into the BRT (Boosted Regression Trees) Method in the Study of the Climate-Growth Relationship of Masson Pine in Subtropical China

Wang

Shang

et al. 2019

Forests

View full text Add to dashboard Cite

Dendroclimatology and dendroecology have entered mainstream dendrochronology research in subtropical and tropical areas. Our study focused on the use of the chronology series of Masson pine (Pinus massoniana Lamb.), the most widely distributed tree species in the subtropical wet monsoon climate regions in China, to understand the tree growth response to ecological and hydroclimatic variability. The boosted regression trees (BRT) model, a nonlinear machine learning method, was used to explore the complex relationship between tree-ring growth and climate factors on a larger spatial scale. The common pattern of an asymptotic growth response to the climate indicated that the climate-growth relationship may be linear until a certain threshold. Once beyond this threshold, tree growth will be insensitive to some climate factors, after which a nonlinear relationship may occur. Spring and autumn climate factors are important controls of tree growth in most study areas. General circulation model (GCM) projections of future climates suggest that warming climates, especially temperatures in excess of those of the optimum growth threshold (as estimated by BRT), will be particularly threatening to the adaptation of Masson pine.

show abstract

Section: Introductionmentioning

confidence: 99%

Insights into the BRT (Boosted Regression Trees) Method in the Study of the Climate-Growth Relationship of Masson Pine in Subtropical China

Wang

Shang

et al. 2019

Forests

View full text Add to dashboard Cite

show abstract

“…In our study, we did not evaluate the influence of climate metrics on VLAs or specific hydraulic conductivity. Even though many studies have reported tree height as a dominant factor of basipetal widening ( Fajardo et al, 2020 ), some recent studies have highlighted the influence of temperature ( Jevšenak et al, 2018a ) and precipitation ( Castagneri et al, 2017 ; Jevšenak et al, 2018b ) on VLAs and hydraulic conductivity. In addition, climate has an undeniable influence on the tree ring widths of both the studied tree species ( Rybníček et al, 2016 ; Roibu et al, 2020 ), and specifically influences the growth of trees of different dimensions ( Trouillier et al, 2019 ).…”

Section: Discussionmentioning

confidence: 99%

“…The size of the conduit elements of trees increases ontogenetically with the increasing distance from the stem base to the apex ( Olson et al, 2014 ; Kašpar et al, 2019 ; Fajardo et al, 2020 ). This general pattern is partly influenced by climate (e.g., Fonti et al, 2013 ; Castagneri et al, 2017 ; Jevšenak et al, 2018a , b ) and partly by the formation of reaction wood ( Jourez et al, 2001 ). This reaction wood generally has vessels with smaller lumens ( Tumajer et al, 2015 ) and different density ( Heinrich et al, 2007 ).…”

Section: Introductionmentioning

confidence: 99%

Hillslope Processes Affect Vessel Lumen Area and Tree Dimensions

et al. 2021

View full text Add to dashboard Cite

The height growth of the trees depends on sufficient mechanical support given by the stem and an effective hydraulic system. On unstable slopes, tree growth is affected by soil pressure from above and potential soil erosion from below the position of tree. The necessary stabilization is then provided by the production of mechanically stronger wood of reduced hydraulic conductivity. Unfortunately, the interaction between tree growth (both radial and axial) and stabilization in the soil is still insufficiently understood. Therefore, in this study, we aimed to quantify the impact of hillslope dynamics on the degree of tree growth and hydraulic limitation, and the potential effect on tree height growth and growth plasticity. To evaluate this effect, we took four cores from 80 individuals of Quercus robur and Fraxinus excelsior and measured tree-ring widths (TRWs) and vessel lumen areas (VLAs). The tree heights were evaluated using a terrestrial laser scanner, and local soil depth was measured by a soil auger. Our data showed a significant limitation of the tree hydraulic system related with the formation of eccentric tree-rings. The stem eccentricity decreased with increasing stem diameter, but at the same time, the negative effect of stem eccentricity on conduit size increased with the increasing stem diameter. Even though this anatomical adaptation associated with the effect of stem eccentricity differed between the tree species (mainly in the different degree of limitations in conduit size), the trees showed an increase in the proportion of hydraulically inactive wood elements and a lowered effectiveness of their hydraulic system. In addition, we observed a larger negative effect of stem eccentricity on VLA in Quercus. We conclude that the stabilization of a tree in unstable soil is accompanied by an inability to create sufficiently effective hydraulic system, resulting in severe height-growth limitation. This affects the accumulation of aboveground biomass and carbon sequestration.

show abstract

“…Such a situation might lead to non‐linear and temporarily unstable relationships between tree growth and climatic factors (Wilmking et al, 2020). Consequently, calibrated climate–growth response functions might not accurately reflect growth variability outside the calibration period, which might reduce the validity of both climate reconstructions and forecast models of forest growth (Jevšenak et al, 2018). This phenomenon, referred to as the “divergence problem” (D'Arrigo et al, 2008) or “non‐stationarity” (Wilmking et al, 2020), is likely widespread and might affect most forest biomes across the globe (Buchwal et al, 2020; Büntgen et al, 2006; Kirdyanov et al, 2020; Wilmking et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, non‐linear process‐based models should be less prone to divergence bias (Kirdyanov et al, 2020; Tolwinski‐Ward et al, 2011). However, a systematic comparison of the predisposition to non‐stationarity of linear versus non‐linear models has so far not been presented (but see Jevšenak et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Ecological and methodological drivers of non‐stationarity in tree growth response to climate

Tumajer

Begović

Čada

et al. 2022

Global Change Biology

View full text Add to dashboard Cite

Radial tree growth is sensitive to environmental conditions, making observed growth increments an important indicator of climate change effects on forest growth. However, unprecedented climate variability could lead to non‐stationarity, that is, a decoupling of tree growth responses from climate over time, potentially inducing biases in climate reconstructions and forest growth projections. Little is known about whether and to what extent environmental conditions, species, and model type and resolution affect the occurrence and magnitude of non‐stationarity. To systematically assess potential drivers of non‐stationarity, we compiled tree‐ring width chronologies of two conifer species, Picea abies and Pinus sylvestris, distributed across cold, dry, and mixed climates. We analyzed 147 sites across the Europe including the distribution margins of these species as well as moderate sites. We calibrated four numerical models (linear vs. non‐linear, daily vs. monthly resolution) to simulate growth chronologies based on temperature and soil moisture data. Climate–growth models were tested in independent verification periods to quantify their non‐stationarity, which was assessed based on bootstrapped transfer function stability tests. The degree of non‐stationarity varied between species, site climatic conditions, and models. Chronologies of P. sylvestris showed stronger non‐stationarity compared with Picea abies stands with a high degree of stationarity. Sites with mixed climatic signals were most affected by non‐stationarity compared with sites sampled at cold and dry species distribution margins. Moreover, linear models with daily resolution exhibited greater non‐stationarity compared with monthly‐resolved non‐linear models. We conclude that non‐stationarity in climate–growth responses is a multifactorial phenomenon driven by the interaction of site climatic conditions, tree species, and methodological features of the modeling approach. Given the existence of multiple drivers and the frequent occurrence of non‐stationarity, we recommend that temporal non‐stationarity rather than stationarity should be considered as the baseline model of climate–growth response for temperate forests.

show abstract

Predicting the vessel lumen area tree-ring parameter of <i>Quercus robur</i> with linear and nonlinear machine learning algorithms

Cited by 9 publications

References 47 publications

Insights into the BRT (Boosted Regression Trees) Method in the Study of the Climate-Growth Relationship of Masson Pine in Subtropical China

Insights into the BRT (Boosted Regression Trees) Method in the Study of the Climate-Growth Relationship of Masson Pine in Subtropical China

Hillslope Processes Affect Vessel Lumen Area and Tree Dimensions

Ecological and methodological drivers of non‐stationarity in tree growth response to climate

Contact Info

Product

Resources

About