Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- - (2)
- F1 score (1)
- ROXAS (1)
- alder carr (1)
- artificial intelligence (1)
- deep learning (1)
- hydraulic traits (1)
- lumen area (1)
- peatland restoration (1)
- waterlogging (1)
Publisher
Human-driven peatland drainage has occurred in Europe for centuries, causing habitat degradation and leading to the emission of greenhouse gases. As such, in the last decades, there has been an increase in policies aiming at restoring these habitats through rewetting. Alder (Alnus glutinosa L.) is a widespread species in temperate forest peatlands with a seemingly high waterlogging tolerance. Yet, little is known about its specific response in growth and wood traits relevant for tree functioning when dealing with changing water table levels. In this study, we investigated the effects of rewetting and extreme flooding on alder growth and wood traits in a peatland forest in northern Germany. We took increment cores from several trees at a drained and a rewetted stand and analyzed changes in ring width, wood density, and xylem anatomical traits related to the hydraulic functioning, growth, and mechanical support for the period 1994–2018. This period included both the rewetting action and an extreme flooding event. We additionally used climate-growth and climate-density correlations to identify the stand-specific responses to climatic conditions. Our results showed that alder growth declined after an extreme flooding in the rewetted stand, whereas the opposite occurred in the drained stand. These changes were accompanied by changes in wood traits related to growth (i.e., number of vessels), but not in wood density and hydraulic-related traits. We found poor climate-growth and climate-density correlations, indicating that water table fluctuations have a stronger effect than climate on alder growth. Our results show detrimental effects on the growth of sudden water table changes leading to permanent waterlogging, but little implications for its wood density and hydraulic architecture. Rewetting actions should thus account for the loss of carbon allocation into wood and ensure suitable conditions for alder growth in temperate peatland forests.
The recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood anatomical (QWA) analyses, where the main challenges reside in the detection of a high number of cells, in the intrinsic variability of wood anatomical features, and in the sample quality. To properly classify and interpret features within the images, DCNNs need to undergo a training stage. We performed the training with images from transversal wood anatomical sections, together with manually created optimal outputs of the target cell areas. The target species included an example for the most common wood anatomical structures: four conifer species; a diffuse-porous species, black alder (Alnus glutinosa L.); a diffuse to semi-diffuse-porous species, European beech (Fagus sylvatica L.); and a ring-porous species, sessile oak (Quercus petraea Liebl.). The DCNN was created in Python with Pytorch, and relies on a Mask-RCNN architecture. The developed algorithm detects and segments cells, and provides information on the measurement accuracy. To evaluate the performance of this tool we compared our Mask-RCNN outputs with U-Net, a model architecture employed in a similar study, and with ROXAS, a program based on traditional image analysis techniques. First, we evaluated how many target cells were correctly recognized. Next, we assessed the cell measurement accuracy by evaluating the number of pixels that were correctly assigned to each target cell. Overall, the “learning process” defining artificial intelligence plays a key role in overcoming the issues that are usually manually solved in QWA analyses. Mask-RCNN is the model that better detects which are the features characterizing a target cell when these issues occur. In general, U-Net did not attain the other algorithms’ performance, while ROXAS performed best for conifers, and Mask-RCNN showed the highest accuracy in detecting target cells and segmenting lumen areas of angiosperms. Our research demonstrates that future software tools for QWA analyses would greatly benefit from using DCNNs, saving time during the analysis phase, and providing a flexible approach that allows model retraining.