Biology subjects

Hoeye, T. T.

Publications and source records attributed to Hoeye, T. T..

2 recordsLinked to original sources

bioRxiv2025

A General Method for Detection and Segmentation of Terrestrial Arthropods in Images

To better understand the status and trends of insects and other arthropods, emerging technologies like image recognition are developing rapidly. This is creating a strong demand for efficient and accurate algorithms for detection and localization of arthropods in images. Existing models have modest performance and do not generalise well to variation in scale, appearance and density of specimens, or imaging conditions. Consequently, each new application often requires manual labeling of training data and model training, which limits the uptake of image-based tools and technologies. Here, we introduce flatbug, which is a powerful and general model to count and outline insects and other terrestrial arthropods in images. The training dataset is large and diverse and represent 23 different lab- and field-based imaging systems. The best flatbug model achieves an average F 1 = 94.2% on our validation dataset. Crucially, we show that flatbug has great out-of-the-box performance and generalises well to novel contexts. When images from a given dataset are left out of model training, the performance of flatbug is only reduced by on average 7.1% for the dataset in question. By using truly stratified cross-validation, we set a precedent for robust evaluation of deep learning model performance and generalization. We also take steps towards scale- and size-agnostic arthropod detection, by developing an integrated tiling framework for inference and training. Additionally, flatbug s implementation of YOLOv8 for instance segmentation enables downstream background removal and body size estimation. The generaliseability of flatbug stems from the diversity of contexts represented in the flatbug dataset, including 113550 arthropods annotated across 6131 images. Alongside a fully documented Python package with tutorials for integration and analysis via https://github.com/darsa-group/flat-bug/, the flatbug dataset is available from https://www.doi.org/10.5281/zenodo.14761447. By providing performant models and the accompanying dataset, flatbug offers both a ready-to-use tool and a benchmark for the future. Overall, flatbug represents a significant methodological advance within arthropod image detection, with user-friendly integration for monitoring and research. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=134 SRC="FIGDIR/small/647223v1_ufig1.gif" ALT="Figure 1"> View larger version (80K): org.highwire.dtl.DTLVardef@2d25c0org.highwire.dtl.DTLVardef@9929borg.highwire.dtl.DTLVardef@77ff28org.highwire.dtl.DTLVardef@10bd2f_HPS_FORMAT_FIGEXP M_FIG C_FIG

ecology↗

bioRxiv2017

A systematic survey of regional multitaxon biodiversity: evaluating strategies and coverage

BackgroundIn light of the biodiversity crisis and our limited ability to explain variation in biodiversity, tools to quantify spatial and temporal variation in biodiversity and its underlying drivers are critically needed. Inspired by the recently published ecospace framework, we developed and tested a sampling design for environmental and biotic mapping. We selected 130 study sites (40 x 40 m) across Denmark using stratified random sampling along the major environmental gradients underlying biotic variation. Using standardized methods, we collected site species data on vascular plants, bryophytes, macrofungi, lichens, gastropods and arthropods. To evaluate sampling efficiency, we calculated regional coverage (relative to the known species number per taxonomic group), and site scale coverage (i.e., sample completeness per taxonomic group at each site). To extend taxonomic coverage to organisms that are difficult to sample by classical inventories (e.g., nematodes and non-fruiting fungi), we collected soil for metabarcoding. Finally, to assess site conditions, we mapped abiotic conditions, biotic resources and habitat continuity.\n\nResultsDespite the 130 study sites only covering a minute fraction (0.0005 %) of the total Danish terrestrial area, we found 1774 species of macrofungi (54 % of the Danish fungal species pool), 663 vascular plant species (42 %), 254 bryophyte species (41 %) and 200 lichen species (19 %). For arthropods, we observed 330 spider species (58 %), 123 carabid beetle species (37 %) and 99 hoverfly species (33 %). Correlations among species richness for taxonomic groups were predominantly positive. Overall, sample coverage was remarkably high across taxonomic groups and sufficient to capture substantial spatial variation in biodiversity across Denmark. This inventory is nationally unprecedented in detail and resulted in the discovery of 143 species with no previous record for Denmark. Comparison between plant OTUs detected in soil DNA and observed plant species confirmed the usefulness of carefully curated environmental DNA-data. Species richness did not correlate well among taxa suggesting differential and complex biotic responses to environmental variation.\n\nConclusionsWe successfully and adequately sampled a wide range of diverse taxa along key environmental gradients across Denmark using an approach that includes multi-taxon biodiversity assessment and ecospace mapping. Our approach is applicable to assessments of biodiversity in other regions and biomes where species are structured along environmental gradient.

ecology↗