Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- wood anatomy (2) (remove)
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.
Determining the effect of a changing climate on tree growth will ultimately depend on our understanding of wood formation processes and how they can be affected by environmental conditions. In this context, monitoring intra-annual radial growth with high temporal resolution through point dendrometers has often been used. Another widespread approach is the microcoring method to follow xylem and phloem formation at the cellular level. Although both register the same biological process (secondary growth), given the limitations of each method, each delivers specific insights that can be combined to obtain a better picture of the process as a whole. To explore the potential of visualizing combined dendrometer and histological monitoring data and scrutinize intra-annual growth data on both dimensions (dendrometer → continuous; microcoring → discrete), we developed DevX (Dendrometer vs. Xylogenesis), a visualization application using the “Shiny” package in the R programming language. The interactive visualization allows the display of dendrometer curves and the overlay of commonly used growth model fits (Gompertz and Weibull) as well as the calculation of wood phenology estimates based on these fits (growth onset, growth cessation, and duration). Furthermore, the growth curves have interactive points to show the corresponding histological section, where the amount and development stage of the tissues at that particular time point can be observed. This allows to see the agreement of dendrometer derived phenology and the development status at the cellular level, and by this help disentangle shrinkage and swelling due to water uptake from actual radial growth. We present a case study with monitoring data for Acer pseudoplatanus L., Fagus sylvatica L., and Quercus robur L. trees growing in a mixed stand in northeastern Germany. The presented application is an example of the innovative and easy to access use of programming languages as basis for data visualization, and can be further used as a learning tool in the topic of wood formation and its ecology. Combining continuous dendrometer data with the discrete information from histological-sections provides a tool to identify active periods of wood formation from dendrometer series (calibrate) and explore monitoring datasets.