Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy

An open-source machine-learning approach for obtaining high-quality quantitative wood anatomy data from E. grandis and P. radiata xylem

Quantitative wood anatomy is a subfield in dendrochronology that requires effective open-source image analysis tools. In this research, the bioimage analysis software QuPath (v0.4.4) is introduced as a candidate for accurately quantifying the cellular properties of the xylem in an automated manner. Additionally, the potential of QuPath to detect the transition of early- to latewood tracheids over the growing season was evaluated to assess a potential application in dendroecological studies. Various algorithms in QuPath were optimized to quantify different xylem cell types in Eucalyptus grandis and the transition of early- to latewood tracheids in Pinus radiata. These algorithms were coded into cell detection scripts for automatic quantification of stem microsections and compared to a manually curated method to assess the accuracy of the cell detections. The automatic cell detection approach, using QuPath, has been validated to be reproducible with an acceptable error when assessing fibers, vessels, early- and latewood tracheids. However, further optimization for parenchyma is still required. This proposed method developed in QuPath provides a scalable and accurate approach for quantifying anatomical features in stem microsections. With minor amendments to the detection and classification algorithms, this strategy is likely to be viable in other plant species.

Tree ring segmentation using UNEt TRansformer neural network on stained microsections for quantitative wood anatomy

Forests are critical in the terrestrial carbon cycle, and the knowledge of their response to ongoing climate change will be crucial for determining future carbon fluxes and climate trajectories. In areas with contrasting seasons, trees form discrete annual rings that can be assigned to calendar years, allowing to extract valuable information about how trees respond to the environment. The anatomical structure of wood provides highly-resolved information about the reaction and adaptation of trees to climate. Quantitative wood anatomy helps to retrieve this information by measuring wood at the cellular level using high-resolution images of wood micro-sections. However, whereas large advances have been made in identifying cellular structures, obtaining meaningful cellular information is still hampered by the correct annual tree ring delimitation on the images. This is a time-consuming task that requires experienced operators to manually delimit ring boundaries. Classic methods of automatic segmentation based on pixel values are being replaced by new approaches using neural networks which are capable of distinguishing structures, even when demarcations require a high level of expertise. Although neural networks have been used for tree ring segmentation on macroscopic images of wood, the complexity of cell patterns in stained microsections of broadleaved species requires adaptive models to accurately accomplish this task. We present an automatic tree ring boundary delineation using neural networks on stained cross-sectional microsection images from beech cores. We trained a UNETR, a combined neural network of UNET and the attention mechanisms of Visual Transformers, to automatically segment annual ring boundaries. Its accuracy was evaluated considering discrepancies with manual segmentation and the consequences of disparity for the goals of quantitative wood anatomy analyses. In most cases (91.8%), automatic segmentation matched or improved manual segmentation, and the rate of vessels assignment to annual rings was similar between the two categories, even when manual segmentation was considered better. The application of convolutional neural networks-based models outperforms human operator segmentations when confronting ring boundary delimitation using specific parameters for quantitative wood anatomy analysis. Current advances on segmentation models may reduce the cost of massive and accurate data collection for quantitative wood anatomy.

A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey

Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. This primer is accompanied by an interactive online tutorial.

Improving ecological insights from dendroecological studies of Arctic shrub dynamics: Research gaps and potential solutions

Rapid climate change has been driving changes in Arctic vegetation in recent decades, with increased shrub dominance in many tundra ecosystems. Dendroecological observations of tundra shrubs can provide insight into current and past growth and recruitment patterns, both key components for understanding and predicting ongoing and future Arctic shrub dynamics. However, generalizing these dynamics is challenging as they are highly scale-dependent and vary among sites, species, and individuals. Here, we provide a perspective on how some of these challenges can be overcome. Based on a targeted literature search of dendrochronological studies from 2005 to 2022, we highlight five research gaps that currently limit dendro-based studies from revealing cross-scale ecological insight into shrub dynamics across the Arctic biome. We further discuss the related research priorities, suggesting that future studies could consider: 1) increasing focus on intra- and interspecific variation, 2) including demographic responses other than radial growth, 3) incorporating drivers, in addition to warming, at different spatial and temporal scales, 4) implementing systematic and unbiased sampling approaches, and 5) investigating the cellular mechanisms behind the observed responses. Focusing on these aspects in dendroecological studies could improve the value of the field for addressing cross-scale and plant community-framed ecological questions. We outline how this could be facilitated through the integration of community-based dendroecology and dendroanatomy with remote sensing approaches. Integrating new technologies and a more multidisciplinary approach in dendroecological research could provide key opportunities to close important knowledge gaps in our understanding of scale-dependencies, as well as intra- and inter-specific variation, in vegetation community dynamics across the Arctic tundra.