Branching principles of animal and plant networks identified by combining extensive data, machine learning and modelling

Abstract

Branching in vascular networks and in overall organismic form is one of the most common and ancient features of multicellular plants, fungi and animals. By combining machine-learning techniques with new theory that relates vascular form to metabolic function, we enable novel classification of diverse branching networks—mouse lung, human head and torso, angiosperm and gymnosperm plants. We find that ratios of limb radii—which dictate essential biologic functions related to resource transport and supply—are best at distinguishing branching networks. We also show how variation in vascular and branching geometry persists despite observing a convergent relationship across organisms for how metabolic rate depends on body mass.

Variable metabolic scaling breaks the law: from ‘Newtonian’ to ‘Darwinian’ approaches

“…Each of several possible mechanisms may, by itself, potentially explain some variation in b , but clearly not all of the systematic effects of various intrinsic and extrinsic factors that have been observed [13,30]. For example, proponents of RTN theory suggest that simply altering the geometry or physics of transport networks can explain much of the existing diversity of b [16,18,126,145]. However, this explanation has several limitations, including that no direct causal relationship between variation in the geometry of RTNs and whole-body metabolic scaling has yet been empirically demonstrated [13,30], most species lack the closed vascular systems required by RTN theory [13,20,36], evidence is accumulating that metabolic scaling is not a simple result of body size-related limits in oxygen and nutrient supply to metabolizing cells [27,29,30,98,146], and RTN theory is incapable of explaining the systematic effects of many kinds of intrinsic biological factors (e.g.…”

The shape of trees: Reimagining forest ecology in three dimensions with remote sensing

“…For example, neural network approaches have been used to automate tree crown detection from both RGB aerial imagery (Bosch, 2020; Weinstein et al, 2019), and from aerial LiDAR (Windrim & Bryson, 2020), and to identify species based on whole tree point clouds (Seidel et al, 2021), stem and bark properties (Mizoguchi et al, 2019) and processed, interpretable features (Terryn et al, 2020). The additional inclusion of ecologically realistic information to constrain processing algorithms, including through the use of scaling rules, can further improve performance (Brummer et al, 2021; Tao et al, 2015); however, the need for training data to build these models means that increased data sharing across the community may be needed, as well as adoption of approaches such as transfer learning and data augmentation.…”

Spatial and Texture Analysis of Root System Distribution with Earth Mover’s Distance (STARSEED)

“…3 College of Natural Sciences, Forestry, and Agriculture, University of Maine, 04469 Orono, USA. 4 Tropical Research and Education Center, University of Florida, 33031 Gainesville, USA.…”