T. T. Hoye

A deep learning pipeline for time-lapse camera monitoring of insects and their floral environments

This paper presents a deep learning pipeline to monitor arthropod abundance and floral cover using time-lapse camera data, showing a correlation between flower cover and arthropod activity.

Deep learning to extract the meteorological by-catch of wildlife cameras

This paper develops deep learning models to extract micrometeorological data from wildlife camera images, showing improved accuracy and revealing ecological insights.

Hierarchical Classification of Insects with Multitask Learning and Anomaly Detection

This paper presents an algorithm for hierarchical insect classification using multitask learning and anomaly detection, improving accuracy at higher taxonomic ranks while identifying classification uncertainty.

Accurate detection and identification of insects from camera trap images with deep learning

This paper presents a large insect image dataset and evaluates YOLO models for accurate detection and identification of insects in camera trap images.

Simple attributes predict the importance of plants as hosts to the richness of fungi and arthropods

The paper investigates how plant attributes predict the richness of associated fungi and arthropods using link scores derived from plant-consumer interaction databases.

Deep learning and computer vision will transform entomology

This paper discusses how deep learning and computer vision can improve insect monitoring by enabling non-invasive, continuous data collection and analysis of insect abundance, diversity, and phenotypic traits.

Earlier springs enable High-Arctic wolf spiders to produce a second clutch

The paper shows Arctic wolf spiders are producing a second clutch due to earlier snowmelt, with later first clutches and larger second clutch proportions in warmer years.

An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning

This paper introduces an automated moth trap with computer vision and deep learning to monitor moths, achieving high image capture and classification performance.

Multi-taxon inventory reveals highly consistent biodiversity responses to ecospace variation

The paper uses an ecospace framework to analyze multi-taxon biodiversity across 130 sites in Denmark, finding consistent responses to environmental variation and highlighting the role of organic matter for fungi and insects.

Vascular plants are strong predictors of multi-taxon species richness

The paper tests if vascular plants predict multi-taxon species richness and finds they explain 48% of total species richness variation when combined with bioindicators.