Refine
Year of publication
- 2021 (2) (remove)
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)
- artificial intelligence (1)
- boreal forest (1)
- conduit reinforcement (1)
- deep learning (1)
- drought limitation (1)
- hydraulic stability (1)
- lumen area (1)
- temperature limitation (1)
- tree allometry (1)
- tree height (1)
- wood anatomy (1)
Publisher
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.
Direct and Indirect Effects of Environmental Limitations on White Spruce Xylem Anatomy at Treeline
(2021)
Treeline ecosystems are of great scientific interest to study the effects of limiting environmental conditions on tree growth. However, tree growth is multidimensional, with complex interactions between height and radial growth. In this study, we aimed to disentangle effects of height and climate on xylem anatomy of white spruce [Picea glauca (Moench) Voss] at three treeline sites in Alaska; i.e., one warm and drought-limited, and two cold, temperature-limited. To analyze general growth differences between trees from different sites, we used data on annual ring width, diameter at breast height (DBH), and tree height. A representative subset of the samples was used to investigate xylem anatomical traits. We then used linear mixed-effects models to estimate the effects of height and climatic variables on our study traits. Our study showed that xylem anatomical traits in white spruce can be directly and indirectly controlled by environmental conditions: hydraulic-related traits seem to be mainly influenced by tree height, especially in the earlywood. Thus, they are indirectly driven by environmental conditions, through the environment’s effects on tree height. Traits related to mechanical support show a direct response to environmental conditions, mainly temperature, especially in the latewood. These results highlight the importance of assessing tree growth in a multidimensional way by considering both direct and indirect effects of environmental forcing to better understand the complexity of tree growth responses to the environment.