Biology subjects

Geissmann, Q.

Publications and source records attributed to Geissmann, Q..

10 recordsLinked to original sources

bioRxiv2025

ALANizer: Design and validation of experimental lighting rig for studying artificial light at night in ecosystems

1Over the past few centuries, human activity has introduced astoundingly bright light to the environment at a rapidly accelerating pace. Artificial light at night (ALAN) has detrimental effects on a wide range of organisms, including arthropods. To minimise impact, we must understand how different organisms are affected and whether certain lights are less perturbing. We designed a novel tool for introducing and monitoring different types of ALAN, called ALANizer, composed of open-source software and inexpensive, widely-available hardware. We describe the design and assembly of ALANizer as well as a feasibility study where we installed 12 ALANizers in hedgerows and monitored arthropod activity using pitfall traps. Understanding ALANs impacts on ecosystems only grows more pressing as LED technology proliferates. As an effective, low-cost, and scalable tool for introducing and monitoring ALAN in ecosystems, ALANizer can help advance this key area of research.

ecology↗

bioRxiv2025

Insect Size Matters: Using Image and Dimensions Together Improves Image Classification

Although visual features have been the cornerstone of insect recognition, morphological traits are often overlooked by modern "scale-invariant" deep learning-based methods. One such trait is absolute body size, which is commonly used by entomologists to describe species. We propose a novel approach that integrates explicit size information into computer vision models. Our method improves predictions of a Convolutional Neural Network (ResNet) by incorporating the likelihood of an insect belonging to each class based on its size and the size distribution of the training data. We compare the performance of the proposed size-aware approach against a standard ResNet and a feature-fused ResNet model, demonstrating that incorporating explicit dimensional traits, such as body size, can enhance classification accuracy across both balanced and imbalanced dataset scenarios. Our results also show that incorporating size reduces classification error, especially in low-data scenarios and for hierarchically coarse, taxonomic misclassifications (e.g., errors at the family level). Despite being readily available and computationally inexpensive, size has, to our knowledge, not been used in this context before. We show that explicitly including size is both computationally efficient and practical, as it requires no specialized sensors and can be derived from standard image segmentation. This makes our approach highly scalable for automated monitoring of insects with camera traps. By acknowledging the importance of size, our approach also contributes to more robust and interpretable ecological modeling. This work opens new avenues for biologically informed AI applications in entomology and beyond.

ecology↗

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↗

bioRxiv2024

Order among chaos: high throughput MYCroplanters can distinguish interacting drivers of host infection in a highly stochastic system

While microbiomes provide diverse benefits for their host, they are notoriously variable in structure and function. As a result, substantial experimental replication and scalability are required to identify the contributions of and interactions between microbiota, the host and the environment. Here, we describe a novel high throughput plant growth system (MYCroplanters) to test how multiple host, microbiota, and pathogen variables predict host health. Using an Arabidopsis-Pseudomonas host-microbiome-pathogen model, we found that host genotype and order of arrival predict competition outcome between strains in the rhizosphere, but pathogen and microbiota dose can overwhelm these effects. Regardless of host or inoculation conditions, final microbial community structure emerged as a consistent predictor of host health. We demonstrate that high-throughput tools like MYCroplanters can isolate interacting drivers of host health. Increasing the scale at which we can screen components of microbiome-mediated host benefits will facilitate building microbiome engineering solutions for medicine and agricultural applications.

ecology↗

bioRxiv2023

Hierarchical Classification of Insects with Multitask Learning and Anomaly Detection

Cameras and computer vision are revolutionising the study of insects, creating new research opportunities within agriculture, epidemiology, evolution, ecology and monitoring of biodiversity. However, a major challenge is the diversity of insects and close resemblances of many species combined with computer vision are often not sufficient to classify large numbers of insect species, which sometimes cannot be identified at the species level. Here, we present an algorithm to hierarchically classify insects from images, leveraging a simple taxonomy to (1) classify specimens across multiple taxonomic ranks simultaneously, and (2) highlight the lowest rank at which a reliable classification can be reached. Specifically, we propose multitask learning, a loss function incorporating class dependency at each taxonomic rank, and anomaly detection based on outlier analysis for quantification of uncertainty. First, we compile a dataset of 41,731 images of insects, combining images from time-lapse monitoring of floral scenes with images from the Global Biodiversity Information Facility (GBIF). Second, we adapt state-of-the-art convolutional neural networks, ResNet and EfficientNet, for the hierarchical classification of insects belonging to three orders, five families and nine species. Third, we assess model generalization for 11 species unseen by the trained models. Here, anomaly detection is used to predict the higher rank of the species not present in the training set. We found that incorporating a simple taxonomy into our model increased accuracy at higher taxonomic ranks. As expected, our algorithm correctly classified new insect species at higher taxonomic ranks, while classification was uncertain at lower taxonomic ranks. Anomaly detection can effectively flag novel taxa that are visually distinct from species in the training data. However, five novel taxa were consistently mistaken for visually similar species in the training data. Above all, we have demonstrated a practical approach to hierarchical classification based on species taxonomy and uncertainty during automated in situ monitoring of live insects. Our method is simple and versatile and could be implemented to classify a wide range of insects as well as other organisms.

ecology↗

bioRxiv2021

Sticky Pi, an AI-powered smart insect trap for community chronoecology

In the face of severe environmental crises that threaten insect biodiversity, new technologies are imperative to monitor both the identity and ecology of insect species. Traditionally, insect surveys rely on manual collection of traps, which provide abundance data but mask the large intra- and inter-day variations in insect activity, an important facet of their ecology. Although laboratory studies have shown that circadian processes are central to insects biological functions, from feeding to reproduction, we lack the high-frequency monitoring tools to study insect circadian biology in the field. To address these issues, we developed the Sticky Pi, a novel, autonomous, open-source, insect trap that acquires images of sticky cards every twenty minutes. Using custom deep-learning algorithms, we automatically and accurately scored where, when and which insects were captured. First, we validated our device in controlled laboratory conditions with a classic chronobiological model organism, Drosophila melanogaster. Then, we deployed an array of Sticky Pis to the field to characterise the daily activity of an agricultural pest, Drosophila suzukii, and its parasitoid wasps. Finally, we demonstrate the wide scope of our smart trap by describing the sympatric arrangement of insect temporal niches in a community, without targeting particular taxa a priori. Together, the automatic identification and high sampling rate of our tool provide biologists with unique data that impacts research far beyond chronobiology; with applications to biodiversity monitoring and pest control as well as fundamental implications for phenology, behavioural ecology, and ecophysiology. We released the Sticky Pi project as an open community resource on https://doc.sticky-pi.com.

ecology↗

bioRxiv2020

Loss of a plant receptor kinase recruits beneficial rhizosphere-associated Pseudomonas

Maintaining microbiome structure is critical for the health of both plants1 and animals2. In plants, enrichment of beneficial bacteria is associated with advantageous outcomes including protection from biotic and abiotic stress3,4. However, the genetic and molecular mechanisms by which plants enrich for specific beneficial microbes without general dysbiosis have remained elusive. Here we show that through regulation of NADPH oxidase, FERONIA kinase negatively regulates beneficial Pseudomonas fluorescens in the Arabidopsis rhizosphere microbiome. By rescreening a collection of Arabidopsis mutants that affect root immunity under gnotobiotic conditions, followed by microbiome sequencing in natural soil, we identified a FERONIA mutant (fer-8) with a rhizosphere microbiome enriched in P. fluorescens without phylum-level dysbiosis. Using microbiome transplant experiments, we found that the fer-8 microbiome was beneficial and promoted plant growth. The effect of FER on rhizosphere Pseudomonads was independent of its immune coreceptor function, role in development, and jasmonic acid autoimmunity. We found that the fer-8 mutant has reduced basal levels of reactive oxygen species (ROS) in roots and that mutants deficient in NADPH oxidase showed elevated rhizosphere Pseudomonad levels. Overexpression of the ROP2 gene (encoding a client of FER and positive regulator of NADPH oxidase5) in fer-8 plants suppressed Pseudomonad overgrowth. This work shows that FER-mediated ROS production regulates levels of beneficial Pseudomonads in the rhizosphere microbiome.

plant biology↗

bioRxiv2018

Most sleep does not serve a vital function. Evidence from Drosophila melanogaster

Sleep appears to be a universally conserved phenomenon among the animal kingdom but whether this striking evolutionary conservation underlies a basic vital function is still an open question. Using novel technologies, we conducted an unprecedentedly detailed high-throughput analysis of sleep in the fruit fly Drosophila melanogaster, coupled with a life-long chronic and specific sleep restriction. Our results show that some wild-type flies are virtually sleepless in baseline conditions and that complete, forced sleep restriction is not necessarily a lethal treatment in wild-type Drosophila melanogaster. We also show that circadian drive, and not homeostatic regulation, is the main contributor to sleep pressure in flies. We propose a three-partite model framework of sleep function, according to which, total sleep accounts for three components: a vital component, a useful component, and an accessory component.

neuroscience↗

bioRxiv2018

Rethomics: an R framework to analyse high-throughput behavioural data

The recent development of automatised methods to score various behaviours on a large number of animals provides biologists with an unprecedented set of tools to decipher these complex phenotypes. Analysing such data comes with several challenges that are largely shared across acquisition platform and paradigms. Here, we present rethomics, a set of R packages that unifies the analysis of behavioural datasets in an efficient and flexible manner. rethomics offers a computational solution to storing, manipulating and visualising large amounts of behavioural data. We propose it as a tool to bridge the gap between behavioural biology and data sciences, thus connecting computational and behavioural scientists. rethomics comes with a extensive documentation as well as a set of both practical and theoretical tutorials (available at https://rethomics.github.io).

bioinformatics↗

bioRxiv2017

Ethoscopes: An Open Platform For High-Throughput Ethomics

We present ethoscopes, machines for high-throughput analysis of behaviour in Drosophila and other animals. Ethoscopes provide a software and hardware solution that is reproducible and easily scalable; they perform, in real-time, tracking and profiling of behaviour using a supervised machine learning algorithm; they can deliver behaviourally-triggered stimuli to flies in a feedback-loop mode; and they are highly customisable and open source. Ethoscopes can be built easily using 3D printing technology and rely on Raspberry Pi microcomputers and Arduino boards to provide affordable and flexible hardware. All software and construction specifications are available at http://lab.gilest.ro/ethoscope.

animal behavior and cognition↗