Quentin Geissmann

ALANizer is a low-cost tool for introducing and monitoring artificial light at night to study its effects on ecosystems, with a feasibility study showing its effectiveness in tracking arthropod activity.

This paper improves insect classification by integrating body size information into deep learning models, showing it enhances accuracy, especially in low-data and taxonomic misclassification scenarios.

flatbug, a YOLOv8 instance-segmentation model with multi-scale tile-pyramid inference and polygon-based deduplication, segments terrestrial arthropods across 23 image subdatasets and transfers to held-out subdatasets with a modest F1 penalty.

This study uses MYCroplanters to identify how host, microbiota, and pathogen factors interact to influence host health in an Arabidopsis-Pseudomonas system.

This study investigates sleep function in Drosophila melanogaster, finding that sleep restriction is not lethal and that circadian drive, not homeostasis, primarily drives sleep pressure.

Rethomics provides an R framework for analyzing high-throughput behavioral data, offering tools for storage, manipulation, and visualization to bridge behavioral biology and data science.