imageseg: an R package for deep learning-based image segmentation

Convolutional neural networks (CNNs) and deep learning are powerful and robust tools for ecological applications. CNNs can perform very well in various tasks, especially for visual tasks and image data. Image segmentation (the classification of all pixels in images) is one such task and can for example be used to assess forest vertical and horizontal structure. While such methods have been suggested, widespread adoption in ecological research has been slow, likely due to technical difficulties in implementation of CNNs and lack of toolboxes for ecologists. Here, we present R package imageseg which implements a workflow for general-purpose image segmentation using CNNs and the U-Net architecture in R. The workflow covers data (pre)processing, model training, and predictions. We illustrate the utility of the package with two models for forest structural metrics: tree canopy density and understory vegetation density. We trained the models using large and diverse training data sets from a variety of forest types and biomes, consisting of 3288 canopy images (both canopy cover and hemispherical canopy closure photographs) and 1468 understory vegetation images. Overall classification accuracy of the models was high with a Dice score of 0.91 for the canopy model and 0.89 for the understory vegetation model (assessed with 821 and 367 images, respectively), indicating robustness to variation in input images and good generalization strength across forest types and biomes. The package and its workflow allow simple yet powerful assessments of forest structural metrics using pre-trained models. Furthermore, the package facilitates custom image segmentation with multiple classes and based on color or grayscale images, e.g. in cell biology or for medical images. Our package is free, open source, and available from CRAN. It will enable easier and faster implementation of deep learning-based image segmentation within R for ecological applications and beyond.

Quantifying the Spatial Variability of Annual and Seasonal Changes in Riverscape Vegetation Using Drone Laser Scanning

Riverscapes are complex ecosystems consisting of dynamic processes influenced by spatially heterogeneous physical features. A critical component of riverscapes is vegetation in the stream channel and floodplain, which influences flooding and provides habitat. Riverscape vegetation can be highly variable in size and structure, including wetland plants, grasses, shrubs, and trees. This vegetation variability is difficult to precisely measure over large extents with traditional surveying tools. Drone laser scanning (DLS), or UAV-based lidar, has shown potential for measuring topography and vegetation over large extents at a high resolution but has yet to be used to quantify both the temporal and spatial variability of riverscape vegetation. Scans were performed on a reach of Stroubles Creek in Blacksburg, VA, USA six times between 2017 and 2019. Change was calculated both annually and seasonally over the two-year period. Metrics were derived from the lidar scans to represent different aspects of riverscape vegetation: height, roughness, and density. Vegetation was classified as scrub or tree based on the height above ground and 604 trees were manually identified in the riverscape, which grew on average by 0.74 m annually. Trees had greater annual growth and scrub had greater seasonal variability. Height and roughness were better measures of annual growth and density was a better measure of seasonal variability. The results demonstrate the advantage of repeat surveys with high-resolution DLS for detecting seasonal variability in the riverscape environment, including the growth and decay of floodplain vegetation, which is critical information for various hydraulic and ecological applications.

Straightforward Synthesis of Mn3O4/ZnO/Eu2O3-Based Ternary Heterostructure Nano-Photocatalyst and Its Application for the Photodegradation of Methyl Orange and Methylene Blue Dyes

Zinc oxide-ternary heterostructure Mn3O4/ZnO/Eu2O3 nanocomposites were successfully prepared via waste curd as fuel by a facile one-pot combustion procedure. The fabricated heterostructures were characterized utilizing XRD, UV–Visible, FT-IR, FE-SEM, HRTEM and EDX analysis. The photocatalytic degradation efficacy of the synthesized ternary nanocomposite was evaluated utilizing model organic pollutants of methylene blue (MB) and methyl orange (MO) in water as examples of cationic dyes and anionic dyes, respectively, under natural solar irradiation. The effect of various experimental factors, viz. the effect of a light source, catalyst dosage, irradiation time, pH of dye solution and dye concentration on the photodegradation activity, was systematically studied. The ternary Mn3O4/ZnO/Eu2O3 photocatalyst exhibited excellent MB and MO degradation activity of 98% and 96%, respectively, at 150 min under natural sunlight irradiation. Experiments further conclude that the fabricated nanocomposite exhibits pH-dependent photocatalytic efficacy, and for best results, concentrations of dye and catalysts have to be maintained in a specific range. The prepared photocatalysts are exemplary and could be employed for wastewater handling and several ecological applications.

A natural constant predicts survival to maximum age

Information about the survival of species is important in many ecological applications. Yet, the estimation of a species’ natural mortality rate M remains a major problem in the management and conservation of wild populations, often circumvented by applying empirical equations that relate mortality to other traits that are more easily observed. We show that mean adult M can be approximated from the general law of decay if the average maximum age reached by individuals in a cohort is known. This is possible because the proportion P of individuals surviving to the average maximum age in a cohort is surprisingly similar across a wide range of examined species at 1.5%. The likely reason for the narrow range of P is a universal increase in the rate of mortality near the end of life, providing strong evidence that the evolutionary theories of ageing are the norm in natural populations.

DNA metabarcoding quantifies relative abundances of arthropod taxa in songbird diets: validation with camera-recorded diets

Ecological research is often hampered by the inability to quantify animal diets. Diet composition can be tracked through DNA metabarcoding of faecal samples, but whether (complex) diets can be quantitatively determined with metabarcoding is still debated and needs validation using free-living animals. This study validates that DNA metabarcoding of faeces can retrieve actual ingested taxa, and most importantly, that read numbers retrieved from sequencing can also be used to quantify relative abundances of dietary taxa. Validation was done with the hole-nesting insectivorous Pied Flycatcher whose diet was quantified using camera footage. Size-adjusted counts of food items delivered to nestlings were used to approximate provided biomass of prey orders and families and subsequently nestling faeces were assessed through DNA metabarcoding. To explore potential effects of digestion, stomach and lower intestine samples of freshly collected birds were subjected to DNA metabarcoding. For metabarcoding with Cytochrome Oxidase subunit I (COI), we modified published invertebrate COI primers LCO1490 and HCO1777, which reduced host reads to 0.03%, and amplified Arachnida DNA without significant changing the recovery of other arthropod taxa. DNA metabarcoding retrieved all commonly camera-recorded taxa. Overall, and in each replicate year (N = 3), the relative abundances of size-adjusted prey counts and COI read numbers correlated at R=0.85 (CI:0.68-0.94) at order level and at R=0.75 (CI:0.67-0.82) at family level. Similarity in arthropod community composition between stomach and intestines suggested limited digestive bias. This DNA metabarcoding validation demonstrates that quantitative analyses of arthropod diet is possible. We discuss the ecological applications for insectivorous birds.