Quentin Geissmann

Over 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 the intensity and spectral character of 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 ALAN's 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.

Data shortages fuel controversy about an ongoing insect biodiversity crisis. Insects are immensely diverse and functionally critical for ecosystems, yet data on their trends remain patchy and biased. Sensors, ranging from camera traps and acoustic recorders to weather radar stations, are set to transform data collection in entomology. Meanwhile, AI models that extract biological information from sensors are improving at a startling rate. Realising the potential of automated monitoring means progressing from proof‐of‐concept studies to scalable insect sensing systems. However, stakeholders face severe operational challenges when adopting a growing suite of sensors, models and protocols for insect surveillance. Deployment of devices is not well co‐ordinated, while the risks of relying on AI are overlooked or understated. To achieve monitoring goals, common pitfalls related to sensors and AI need to be exposed and avoided. We trace a seven‐step path towards an effective transnational rollout of insect sensing systems. Step (1) reviews strengths, weaknesses and synergies across visual, acoustic, radar and photonic sensors; (2) confronts species determination—a key challenge for sensors and AI—suggesting how to improve identification and make use of uncertain data; (3) promotes creating and sharing standardised, labelled data, offering ecological insights and opportunities to train and evaluate AI. Focussing on data processing and scalability, step (4) proposes using AI to complement other resources, both human and digital, given it is not always the best tool for the job; (5) highlights how and why AI models fail, calling for routine evaluations and shrewdness during model training; (6) aims to break barriers to wider uptake of technologies through knowledge sharing, affordable design principles and equitable computing infrastructures, and finally, (7) emphasises that any revolution in insect monitoring must be grounded in good sampling design, with established monitoring schemes at its core. We set a trajectory for coordinated development of insect sensing systems, focussing not only on technical performance but also on integration with human expertise, case‐based evaluation and harmonisation with historical long‐term datasets. We address fundamental challenges of sensors and AI for biodiversity monitoring, producing recommendations that apply to all branches of the tree of life.

Members of the genus Pseudomonas synthesize diverse natural products that contribute to their versatility in free-living and host-associated lifestyles. Here, we characterized the in vivo functions of the nitroimidazole antibiotic azomycin in the genus Pseudomonas . We found that genes with similarity to azomycin biosynthesis genes rohPQRST are prevalent within the Pseudomonas syringae species complex and rarely present in the Pseudomonas fluorescens species complex. Azomycin production was detectable in culture by biocontrol strains Pseudomonas spp. DF41 and CMR5a. Pseudomonas sp. DF41 exhibited anti-oomycete activity that was lost in a ∆rohPQRST mutant. Purified azomycin was sufficient to kill the oomycete pathogens Aphanomyces and Phytophthora . Although DF41 has been studied for its role in biocontrol of plant pathogens, we found that azomycin exhibited phytotoxicity against Pisum sativum (pea) plants at similar concentrations to those that inhibited oomycetes. However, consistent with its use as a biocontrol agent, Pseudomonas sp. DF41 only produced azomycin in planta when pea plants were infected with the oomycete pathogen Aphanomyces euteiches . Our findings suggest dual roles for azomycin in Pseudomonas, functioning both as a biocontrol agent of oomycete pathogens, as well as a phytotoxic molecule with a potential role in plant virulence. IMPORTANCE: While many natural products are studied for their roles in the treatment of plant or human disease, the ecological functions of natural products are understudied. We found that an antibiotic, azomycin, is produced by Pseudomonas species and has toxicity against both plants and oomycete pathogens. Our findings suggest a complex ecological role of azomycin production by Pseudomonas in both the amelioration and exacerbation of plant disease.

1 Over 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 ALAN’s 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.

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.

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 F1=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.

The likelihood that a host will be susceptible to infection is influenced by the interaction of diverse biotic and abiotic factors. As a result, substantial experimental replication and scalability are required to identify the contributions of and interactions between the host, the environment, and biotic factors such as the microbiome. For example, pathogen infection success is known to vary by host genotype, bacterial strain identity and dose, and pathogen dose. Elucidating the interactions between these factors in vivo has been challenging because testing combinations of these variables quickly becomes experimentally intractable. Here, we describe a novel high throughput plant growth system (MYCroplanters) to test how multiple host, non-pathogenic bacteria, and pathogen variables predict host health. Using an Arabidopsis-Pseudomonas host-microbe model, we found that host genotype and bacterial strain order of arrival predict host susceptibility to infection, but pathogen and non-pathogenic bacterial dose can overwhelm these effects. Host susceptibility to infection is therefore driven by complex interactions between multiple factors that can both mask and compensate for each other. However, regardless of host or inoculation conditions, the ratio of pathogen to non-pathogen emerged as a consistent correlate of disease. Our results demonstrate that high-throughput tools like MYCroplanters can isolate interacting drivers of host susceptibility to disease. Increasing the scale at which we can screen drivers of disease, such as microbiome community structure, will facilitate both disease predictions and treatments for medicine and agricultural applications.

Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and fastest developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects—from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue ‘Towards a toolkit for global insect biodiversity monitoring’.

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.