An official website of the United States government
Summary Leaf vein network geometry can predict levels of resource transport, defence and mechanical support that operate at different spatial scales. However, it is challenging to quantify network architecture across scales due to the difficulties both in segmenting networks from images and in extracting multiscale statistics from subsequent network graph representations.Here we developed deep learning algorithms using convolutional neural networks (CNNs) to automatically segment leaf vein networks. Thirty‐eight CNNs were trained on subsets of manually defined ground‐truth regions from >700 leaves representing 50 southeast Asian plant families. Ensembles of six independently trained CNNs were used to segment networks from larger leaf regions (c. 100 mm2). Segmented networks were analysed using hierarchical loop decomposition to extract a range of statistics describing scale transitions in vein and areole geometry.The CNN approach gave a precision‐recall harmonic mean of 94.5% ± 6%, outperforming other current network extraction methods, and accurately described the widths, angles and connectivity of veins. Multiscale statistics then enabled the identification of previously undescribed variation in network architecture across species.We provide aLeafVeinCNNsoftware package to enable multiscale quantification of leaf vein networks, facilitating the comparison across species and the exploration of the functional significance of different leaf vein architectures.
more »
« less
Editorial: Bridging Scales and Levels
Network neuroscience strives to understand the networks of the brain on all spatiotemporal scales and levels of observation. Current experimental and theoretical capabilities are beginning to facilitate a more holistic perspective, uniting these networks. This focus feature, “Bridging Scales and Levels,” aims to document current research and looks to future progress towards this vision.
more »
« less
- Award ID(s):
- 1734870
- PAR ID:
- 10137007
- Date Published:
- Journal Name:
- Network Neuroscience
- Volume:
- 2
- Issue:
- 3
- ISSN:
- 2472-1751
- Page Range / eLocation ID:
- 303 to 305
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Understanding how resource limitation and biotic interactions interact across spatial scales is fundamental to explaining the structure of ecological communities. However, empirical studies addressing this issue are often hindered by logistical constraints, especially at local scales. Here, we use a highly tractable arboreal ant study system to explore the interactive effects of resource availability and competition on community structure across three local scales: an individual tree, the nest network created by each colony and the individual ant nest. On individual trees, the ant assemblages are primarily shaped by availability of dead wood, a critical nesting resource. The nest networks within a tree are constrained by the availability of nesting resources but also influenced by the co-occurring species. Within individual nests, the distribution of adult ants is only affected by distance to interspecific competitors. These findings demonstrate that resource limitation exerts the strongest effects on diversity at higher levels of local ecological organization, transitioning to a stronger effect of species interactions at finer scales. Collectively, these results highlight that the process exerting the strongest influence on community structure is highly dependent on the scale at which we examine the community, with shifts occurring even across fine-grained local scales.more » « less
-
In the current data-centered era, there are many highly diverse data sources that provide information about movement on networks, such as GPS trajectories, traffic flow measurements, farecard data, pedestrian cameras, bike-share data and even geo-social movement trajectories. The challenge identified in this vision paper is to create a unified framework for aggregating and analyzing such diverse and uncertain movement data on networks. This requires probabilistic models to capture flow/volume and movement probabilities on a network over time. Novel algorithms are required to train these models from datasets with varying levels of uncertainty. By combining information from different networks, immediate applications of such a unifying movement model include optimal site planning, map construction, traffic management, and emergency management.more » « less
-
Grant, William (Ed.)Abstract The euphausiid genus Stylocheiron includes species with biogeographical distributions spanning multiple ocean basins. Despite their circumglobal distributions, the species show low levels of genetic diversity and little or no evidence of population structure based on the mitochondrial cytochrome oxidase I (COI) barcode region, with the exception of a possible cryptic species within Stylocheiron affine. Stylocheiron elongatum showed < 1% variation of the COI barcode region among populations in different ocean basins, but analysis of samples collected from the Florida Current (February, 1993) and Gulf Stream Meander Region (April, 1993) in the Northwest Atlantic Ocean revealed small-but-significant genetic differentiation between samples based on a different section of COI and mitochondrial cytochrome b (CYB). Both COI and CYB showed large haplotype and small nucleotide diversities, departures from neutral expectations, and haplotype networks consistent with persistent genetic structuring of the species population. These patterns of diversity indicate the presence of selection driving population divergence. We hypothesize that position-keeping by this deep-living, non-migrating euphausiid species may prevent genetic homogenization (panmixia) in the dynamic Gulf Stream System. This study demonstrates the importance of analyzing patterns of genetic diversity and structure at regional and global scales to understand the ecological and evolutionary processes impacting marine zooplankton.more » « less
-
Moura, Mario R. (Ed.)Projecting ecological and evolutionary responses to variable and changing environments is central to anticipating and managing impacts to biodiversity and ecosystems. Current modeling approaches are largely phenomenological and often fail to accurately project responses due to numerous biological processes at multiple levels of biological organization responding to environmental variation at varied spatial and temporal scales. Limited mechanistic understanding of organismal responses to environmental variability and extremes also restricts predictive capacity. We outline a strategy for identifying and modeling the key organismal mechanisms across levels of biological organization that mediate ecological and evolutionary responses to environmental variation. A central component of this strategy is quantifying timescales and magnitudes of climatic variability and how organisms experience them. We highlight recent empirical research that builds this information and suggest how to design future experiments that can produce more generalizable principles. We discuss how to create biologically informed projections in a feasible way by combining statistical and mechanistic approaches. Predictions will inform both fundamental and practical questions at the interface of ecology, evolution, and Earth science such as how organisms experience, adapt to, and respond to environmental variation at multiple hierarchical spatial and temporal scales.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1162/netn_e_00059
