Deep learning and computer vision will transform entomology

Automated identification of aquatic insects: A case study using deep learning and computer vision techniques

Deep learning techniques have recently found application in biodiversity research. Mayflies (Ephemeroptera), stoneflies (Plecoptera) and caddisflies (Trichoptera), often abbreviated as EPT, are frequently used for freshwater biomonitoring due to their large numbers and sensitivity to environmental changes. However, the morphological identification of EPT species is a challenging but fundamental task. Morphological identification of these freshwater insects is therefore not only extremely time-consuming and costly, but also often leads to misjudgments or generates datasets with low taxonomic resolution. Here, we investigated the application of deep learning to increase the efficiency and taxonomic resolution of biomonitoring programs. Our database contains 90 EPT taxa (genus or species level), with the number of images per category ranging from 21 to 300 (16,650 in total). Upon completion of training, a CNN (Convolutional Neural Network) model was created, capable of automatically classifying these taxa into their appropriate taxonomic categories with an accuracy of 98.7 %. Our model achieved a perfect classification rate of 100 % for 68 of the taxa in our dataset. We achieved noteworthy classification accuracy with morphologically closely related taxa within the training data (e.g., species of the genus Baetis, Hydropsyche, Perla). Gradient-weighted Class Activation Mapping (Grad-CAM) visualized the morphological features responsible for the classification of the treated species in the CNN models. Within Ephemeroptera, the head was the most important feature, while the thorax and abdomen were equally important for the classification of Plecoptera taxa. For the order Trichoptera, the head and thorax were almost equally important. Our database is recognized as the most extensive aquatic insect database, notably distinguished by its wealth of included categories (taxa). Our approach can help solve long-standing challenges in biodiversity research and address pressing issues in monitoring programs by saving time in sample identification.

Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects

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'.

Emerging technologies in citizen science and potential for insect monitoring

Emerging technologies are increasingly employed in environmental citizen science projects. This integration offers benefits and opportunities for scientists and participants alike. Citizen science can support large-scale, long-term monitoring of species occurrences, behaviour and interactions. At the same time, technologies can foster participant engagement, regardless of pre-existing taxonomic expertise or experience, and permit new types of data to be collected. Yet, technologies may also create challenges by potentially increasing financial costs, necessitating technological expertise or demanding training of participants. Technology could also reduce people's direct involvement and engagement with nature. In this perspective, we discuss how current technologies have spurred an increase in citizen science projects and how the implementation of emerging technologies in citizen science may enhance scientific impact and public engagement. We show how technology can act as (i) a facilitator of current citizen science and monitoring efforts, (ii) an enabler of new research opportunities, and (iii) a transformer of science, policy and public participation, but could also become (iv) an inhibitor of participation, equity and scientific rigour. Technology is developing fast and promises to provide many exciting opportunities for citizen science and insect monitoring, but while we seize these opportunities, we must remain vigilant against potential risks. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Sharing insect data through GBIF: novel monitoring methods, opportunities and standards

Technological advancements in biological monitoring have facilitated the study of insect communities at unprecedented spatial scales. The progress allows more comprehensive coverage of the diversity within a given area while minimizing disturbance and reducing the need for extensive human labour. Compared with traditional methods, these novel technologies offer the opportunity to examine biological patterns that were previously beyond our reach. However, to address the pressing scientific inquiries of the future, data must be easily accessible, interoperable and reusable for the global research community. Biodiversity information standards and platforms provide the necessary infrastructure to standardize and share biodiversity data. This paper explores the possibilities and prerequisites of publishing insect data obtained through novel monitoring methods through GBIF, the most comprehensive global biodiversity data infrastructure. We describe the essential components of metadata standards and existing data standards for occurrence data on insects, including data extensions. By addressing the current opportunities, limitations, and future development of GBIF's publishing framework, we hope to encourage researchers to both share data and contribute to the further development of biodiversity data standards and publishing models. Wider commitments to open data initiatives will promote data interoperability and support cross-disciplinary scientific research and key policy indicators. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Delivering on a promise: futureproofing automated insect monitoring methods

Due to rapid technological innovations, the automated monitoring of insect assemblages comes within reach. However, this continuous innovation endangers the methodological continuity needed for calculating reliable biodiversity trends in the future. Maintaining methodological continuity over prolonged periods of time is not trivial, since technology improves, reference libraries grow and both the hard- and software used now may no longer be available in the future. Moreover, because data on many species are collected at the same time, there will be no simple way of calibrating the outputs of old and new devices. To ensure that reliable long-term biodiversity trends can be calculated using the collected data, I make four recommendations: (1) Construct devices to last for decades, and have a five-year overlap period when devices are replaced. (2) Construct new devices to resemble the old ones, especially when some kind of attractant (e.g. light) is used. Keep extremely detailed metadata on collection, detection and identification methods, including attractants, to enable this. (3) Store the raw data (sounds, images, DNA extracts, radar/lidar detections) for future reprocessing with updated classification systems. (4) Enable forward and backward compatibility of the processed data, for example by in-silico data 'degradation' to match the older data quality. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Towards a toolkit for global insect biodiversity monitoring

Insects are the most diverse group of animals on Earth, yet our knowledge of their diversity, ecology and population trends remains abysmally poor. Four major technological approaches are coming to fruition for use in insect monitoring and ecological research-molecular methods, computer vision, autonomous acoustic monitoring and radar-based remote sensing-each of which has seen major advances over the past years. Together, they have the potential to revolutionize insect ecology, and to make all-taxa, fine-grained insect monitoring feasible across the globe. So far, advances within and among technologies have largely taken place in isolation, and parallel efforts among projects have led to redundancy and a methodological sprawl; yet, given the commonalities in their goals and approaches, increased collaboration among projects and integration across technologies could provide unprecedented improvements in taxonomic and spatio-temporal resolution and coverage. This theme issue showcases recent developments and state-of-the-art applications of these technologies, and outlines the way forward regarding data processing, cost-effectiveness, meaningful trend analysis, technological integration and open data requirements. Together, these papers set the stage for the future of automated insect monitoring. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Towards acoustic monitoring of bees: wingbeat sounds are related to species and individual traits

Global pollinator decline urgently requires effective methods to assess their trends, distribution and behaviour. Passive acoustics is a non-invasive and cost-efficient monitoring tool increasingly employed for monitoring animal communities. However, insect sounds remain highly unexplored, hindering the application of this technique for pollinators. To overcome this shortfall and support future developments, we recorded and characterized wingbeat sounds of a variety of Iberian domestic and wild bees and tested their relationship with taxonomic, morphological, behavioural and environmental traits at inter- and intra-specific levels. Using directional microphones and machine learning, we shed light on the acoustic signature of bee wingbeat sounds and their potential to be used for species identification and monitoring. Our results revealed that frequency of wingbeat sounds is negatively related with body size and environmental temperature (between-species analysis), while it is positively related with experimentally induced stress conditions (within-individual analysis). We also found a characteristic acoustic signature in the European honeybee that supported automated classification of this bee from a pool of wild bees, paving the way for passive acoustic monitoring of pollinators. Overall, these findings confirm that insect sounds during flight activity can provide insights on individual and species traits, and hence suggest novel and promising applications for this endangered animal group. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

GranoScan: an AI-powered mobile app for in-field identification of biotic threats of wheat

Capitalizing on the widespread adoption of smartphones among farmers and the application of artificial intelligence in computer vision, a variety of mobile applications have recently emerged in the agricultural domain. This paper introduces GranoScan, a freely available mobile app accessible on major online platforms, specifically designed for the real-time detection and identification of over 80 threats affecting wheat in the Mediterranean region. Developed through a co-design methodology involving direct collaboration with Italian farmers, this participatory approach resulted in an app featuring: (i) a graphical interface optimized for diverse in-field lighting conditions, (ii) a user-friendly interface allowing swift selection from a predefined menu, (iii) operability even in low or no connectivity, (iv) a straightforward operational guide, and (v) the ability to specify an area of interest in the photo for targeted threat identification. Underpinning GranoScan is a deep learning architecture named efficient minimal adaptive ensembling that was used to obtain accurate and robust artificial intelligence models. The method is based on an ensembling strategy that uses as core models two instances of the EfficientNet-b0 architecture, selected through the weighted F1-score. In this phase a very good precision is reached with peaks of 100% for pests, as well as in leaf damage and root disease tasks, and in some classes of spike and stem disease tasks. For weeds in the post-germination phase, the precision values range between 80% and 100%, while 100% is reached in all the classes for pre-flowering weeds, except one. Regarding recognition accuracy towards end-users in-field photos, GranoScan achieved good performances, with a mean accuracy of 77% and 95% for leaf diseases and for spike, stem and root diseases, respectively. Pests gained an accuracy of up to 94%, while for weeds the app shows a great ability (100% accuracy) in recognizing whether the target weed is a dicot or monocot and 60% accuracy for distinguishing species in both the post-germination and pre-flowering stage. Our precision and accuracy results conform to or outperform those of other studies deploying artificial intelligence models on mobile devices, confirming that GranoScan is a valuable tool also in challenging outdoor conditions.

Out-of-Distribution Detection Algorithms for Robust Insect Classification

Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.

Insect detect: An open-source DIY camera trap for automated insect monitoring

Insect monitoring is essential to design effective conservation strategies, which are indispensable to mitigate worldwide declines and biodiversity loss. For this purpose, traditional monitoring methods are widely established and can provide data with a high taxonomic resolution. However, processing of captured insect samples is often time-consuming and expensive, which limits the number of potential replicates. Automated monitoring methods can facilitate data collection at a higher spatiotemporal resolution with a comparatively lower effort and cost. Here, we present the Insect Detect DIY (do-it-yourself) camera trap for non-invasive automated monitoring of flower-visiting insects, which is based on low-cost off-the-shelf hardware components combined with open-source software. Custom trained deep learning models detect and track insects landing on an artificial flower platform in real time on-device and subsequently classify the cropped detections on a local computer. Field deployment of the solar-powered camera trap confirmed its resistance to high temperatures and humidity, which enables autonomous deployment during a whole season. On-device detection and tracking can estimate insect activity/abundance after metadata post-processing. Our insect classification model achieved a high top-1 accuracy on the test dataset and generalized well on a real-world dataset with captured insect images. The camera trap design and open-source software are highly customizable and can be adapted to different use cases. With custom trained detection and classification models, as well as accessible software programming, many possible applications surpassing our proposed deployment method can be realized.

VespAI: a deep learning-based system for the detection of invasive hornets

The invasive hornet Vespa velutina nigrithorax is a rapidly proliferating threat to pollinators in Europe and East Asia. To effectively limit its spread, colonies must be detected and destroyed early in the invasion curve, however the current reliance upon visual alerts by the public yields low accuracy. Advances in deep learning offer a potential solution to this, but the application of such technology remains challenging. Here we present VespAI, an automated system for the rapid detection of V. velutina. We leverage a hardware-assisted AI approach, combining a standardised monitoring station with deep YOLOv5s architecture and a ResNet backbone, trained on a bespoke end-to-end pipeline. This enables the system to detect hornets in real-time-achieving a mean precision-recall score of ≥0.99-and send associated image alerts via a compact remote processor. We demonstrate the successful operation of a prototype system in the field, and confirm its suitability for large-scale deployment in future use cases. As such, VespAI has the potential to transform the way that invasive hornets are managed, providing a robust early warning system to prevent ingressions into new regions.

A gentle introduction to computer vision-based specimen classification in ecological datasets

Classifying specimens is a critical component of ecological research, biodiversity monitoring and conservation. However, manual classification can be prohibitively time-consuming and expensive, limiting how much data a project can afford to process. Computer vision, a form of machine learning, can help overcome these problems by rapidly, automatically and accurately classifying images of specimens. Given the diversity of animal species and contexts in which images are captured, there is no universal classifier for all species and use cases. As such, ecologists often need to train their own models. While numerous software programs exist to support this process, ecologists need a fundamental understanding of how computer vision works to select appropriate model workflows based on their specific use case, data types, computing resources and desired performance capabilities. Ecologists may also face characteristic quirks of ecological datasets, such as long-tail distributions, 'unknown' species, similarity between species and polymorphism within species, which impact the efficacy of computer vision. Despite growing interest in computer vision for ecology, there are few resources available to help ecologists face the challenges they are likely to encounter. Here, we present a gentle introduction for species classification using computer vision. In this manuscript and associated GitHub repository, we demonstrate how to prepare training data, basic model training procedures, and methods for model evaluation and selection. Throughout, we explore specific considerations ecologists should make when training classification models, such as data domains, feature extractors and class imbalances. With these basics, ecologists can adjust their workflows to achieve research goals and/or account for uncertainty in downstream analysis. Our goal is to provide guidance for ecologists for getting started in or improving their use of machine learning for visual classification tasks.

The Use and Prospects of Nonlethal Methods in Entomology

Arthropods are declining globally, and entomologists ought to be in the forefront of protecting them. However, entomological study methods are typically lethal, and we argue that this makes the ethical status of the profession precarious. Lethal methods are used in most studies, even those that aim to support arthropod conservation. Additionally, almost all collecting methods result in bycatch, and a first step toward less destructive research practices is to minimize bycatch and/or ensure its proper storage and use. In this review, we describe the available suite of nonlethal methods with the aim of promoting their use. We classify nonlethal methods into (a) reuse of already collected material, (b) methods that are damaging but not lethal, (c) methods that modify behavior, and (d) true nonlethal methods. Artificial intelligence and miniaturization will help to extend the nonlethal methodological toolkit, but the need for further method development and testing remains.

Using individual-based trait frequency distributions to forecast plant-pollinator network responses to environmental change

Determining how and why organisms interact is fundamental to understanding ecosystem responses to future environmental change. To assess the impact on plant-pollinator interactions, recent studies have examined how the effects of environmental change on individual interactions accumulate to generate species-level responses. Here, we review recent developments in using plant-pollinator networks of interacting individuals along with their functional traits, where individuals are nested within species nodes. We highlight how these individual-level, trait-based networks connect intraspecific trait variation (as frequency distributions of multiple traits) with dynamic responses within plant-pollinator communities. This approach can better explain interaction plasticity, and changes to interaction probabilities and network structure over spatiotemporal or other environmental gradients. We argue that only through appreciating such trait-based interaction plasticity can we accurately forecast the potential vulnerability of interactions to future environmental change. We follow this with general guidance on how future studies can collect and analyse high-resolution interaction and trait data, with the hope of improving predictions of future plant-pollinator network responses for targeted and effective conservation.

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

Microclimate-proximal climatic variation at scales of metres and minutes-can exacerbate or mitigate the impacts of climate change on biodiversity. However, most microclimate studies are temperature centric, and do not consider meteorological factors such as sunshine, hail and snow. Meanwhile, remote cameras have become a primary tool to monitor wild plants and animals, even at micro-scales, and deep learning tools rapidly convert images into ecological data. However, deep learning applications for wildlife imagery have focused exclusively on living subjects. Here, we identify an overlooked opportunity to extract latent, ecologically relevant meteorological information. We produce an annotated image dataset of micrometeorological conditions across 49 wildlife cameras in South Africa's Maloti-Drakensberg and the Swiss Alps. We train ensemble deep learning models to classify conditions as overcast, sunshine, hail or snow. We achieve 91.7% accuracy on test cameras not seen during training. Furthermore, we show how effective accuracy is raised to 96% by disregarding 14.1% of classifications where ensemble member models did not reach a consensus. For two-class weather classification (overcast vs. sunshine) in a novel location in Svalbard, Norway, we achieve 79.3% accuracy (93.9% consensus accuracy), outperforming a benchmark model from the computer vision literature (75.5% accuracy). Our model rapidly classifies sunshine, snow and hail in almost 2 million unlabelled images. Resulting micrometeorological data illustrated common seasonal patterns of summer hailstorms and autumn snowfalls across mountains in the northern and southern hemispheres. However, daily patterns of sunshine and shade diverged between sites, impacting daily temperature cycles. Crucially, we leverage micrometeorological data to demonstrate that (1) experimental warming using open-top chambers shortens early snow events in autumn, and (2) image-derived sunshine marginally outperforms sensor-derived temperature when predicting bumblebee foraging. These methods generate novel micrometeorological variables in synchrony with biological recordings, enabling new insights from an increasingly global network of wildlife cameras.

Mitigating the impacts of street lighting on biodiversity and ecosystem functioning

Street lights are not only a major source of direct light pollution emissions, but stock has been transitioning to light-emitting diode (LED) technology in many parts of the world, resulting in increases in the blue part of the visible spectrum that is more harmful to biodiversity and human health. But LEDs can be modified more easily than conventional sodium lamps by adjusting their intensity, spectral output and other features of street light systems. In this Opinion piece, I provide an updated overview of street light mitigation strategies and contend that research in this area has been slow. I show how experimental lighting rigs that mimic real street lights can be used for mitigation testing, since invertebrate behaviour, abundances and interactions can respond quickly and measurably. I demonstrate how advances in network ecology that use species interaction data can provide much-needed assessments of the impacts of street lights on biodiversity and ecosystem functioning, and ultimately provide new tools and metrics for biomonitoring. I acknowledge the limitations of measuring local, short-term responses of biodiversity and identify promising avenues for collaborating with industry and government agencies in new or existing road lighting schemes, to minimize the negative long-term impacts at marginal cost. This article is part of the theme issue 'Light pollution in complex ecological systems'.

Learning algorithms estimate pose and detect motor anomalies in flies exposed to minimal doses of a toxicant

Pesticide exposure, even at low doses, can have detrimental effects on ecosystems. This study aimed at validating the use of machine learning for recognizing motor anomalies, produced by minimal insecticide exposure on a model insect species. The Mediterranean fruit fly, Ceratitis capitata (Diptera: Tephritidae), was exposed to food contaminated with low concentrations of Carlina acaulis essential oil (EO). A deep learning approach enabled fly pose estimation on video recordings in a custom-built arena. Five machine learning algorithms were trained on handcrafted features, extracted from the predicted pose, to distinguish treated individuals. Random Forest and K-Nearest Neighbor algorithms best performed, with an area under the receiver operating characteristic (ROC) curve of 0.75 and 0.73, respectively. Both algorithms achieved an accuracy of 0.71. Results show the machine learning potential for detecting sublethal effects arising from insecticide exposure on fly motor behavior, which could also affect other organisms and environmental health.

Bioacoustic IoT Sensors as Next-Generation Tools for Monitoring: Counting Flying Insects through Buzz

The global loss of biodiversity is an urgent concern requiring the implementation of effective monitoring. Flying insects, such as pollinators, are vital for ecosystems, and establishing their population dynamics has become essential in conservation biology. Traditional monitoring methods are labour-intensive and show time constraints. In this work, we explore the use of bioacoustic sensors for monitoring flying insects. Data collected at four Italian farms using traditional monitoring methods, such as hand netting and pan traps, and bioacoustic sensors were compared. The results showed a positive correlation between the average number of buzzes per hour and insect abundance measured by traditional methods, primarily by pan traps. Intraday and long-term analysis performed on buzzes revealed temperature-related patterns of insect activity. Passive acoustic monitoring proved to be effective in estimating flying insect abundance, while further development of the algorithm is required to correctly identify insect taxa. Overall, innovative technologies, such as bioacoustic sensors, do not replace the expertise and data quality provided by professionals, but they offer unprecedented opportunities to ease insect monitoring to support conservation biodiversity efforts.

Collective and harmonized high throughput barcoding of insular arthropod biodiversity: Toward a Genomic Observatories Network for islands

Current understanding of ecological and evolutionary processes underlying island biodiversity is heavily shaped by empirical data from plants and birds, although arthropods comprise the overwhelming majority of known animal species, and as such can provide key insights into processes governing biodiversity. Novel high throughput sequencing (HTS) approaches are now emerging as powerful tools to overcome limitations in the availability of arthropod biodiversity data, and hence provide insights into these processes. Here, we explored how these tools might be most effectively exploited for comprehensive and comparable inventory and monitoring of insular arthropod biodiversity. We first reviewed the strengths, limitations and potential synergies among existing approaches of high throughput barcode sequencing. We considered how this could be complemented with deep learning approaches applied to image analysis to study arthropod biodiversity. We then explored how these approaches could be implemented within the framework of an island Genomic Observatories Network (iGON) for the advancement of fundamental and applied understanding of island biodiversity. To this end, we identified seven island biology themes at the interface of ecology, evolution and conservation biology, within which collective and harmonized efforts in HTS arthropod inventory could yield significant advances in island biodiversity research.

Machine learning analysis of wing venation patterns accurately identifies Sarcophagidae, Calliphoridae and Muscidae fly species

In medical, veterinary and forensic entomology, the ease and affordability of image data acquisition have resulted in whole-image analysis becoming an invaluable approach for species identification. Krawtchouk moment invariants are a classical mathematical transformation that can extract local features from an image, thus allowing subtle species-specific biological variations to be accentuated for subsequent analyses. We extracted Krawtchouk moment invariant features from binarised wing images of 759 male fly specimens from the Calliphoridae, Sarcophagidae and Muscidae families (13 species and a species variant). Subsequently, we trained the Generalized, Unbiased, Interaction Detection and Estimation random forests classifier using linear discriminants derived from these features and inferred the species identity of specimens from the test samples. Fivefold cross-validation results show a 98.56 ± 0.38% (standard error) mean identification accuracy at the family level and a 91.04 ± 1.33% mean identification accuracy at the species level. The mean F1-score of 0.89 ± 0.02 reflects good balance of precision and recall properties of the model. The present study consolidates findings from previous small pilot studies of the usefulness of wing venation patterns for inferring species identities. Thus, the stage is set for the development of a mature data analytic ecosystem for routine computer image-based identification of fly species that are of medical, veterinary and forensic importance.

Discrimination of Hover Fly Species and Sexes by Wing Interference Signals

Remote automated surveillance of insect abundance and diversity is poised to revolutionize insect decline studies. The study reveals spectral analysis of thin-film wing interference signals (WISs) can discriminate free-flying insects beyond what can be accomplished by machine vision. Detectable by photonic sensors, WISs are robust indicators enabling species and sex identification. The first quantitative survey of insect wing thickness and modulation through shortwave-infrared hyperspectral imaging of 600 wings from 30 hover fly species is presented. Fringy spectral reflectance of WIS can be explained by four optical parameters, including membrane thickness. Using a Naïve Bayes Classifier with five parameters that can be retrieved remotely, 91% is achieved accuracy in identification of species and sexes. WIS-based surveillance is therefore a potent tool for remote insect identification and surveillance.

From beasts to bytes: Revolutionizing zoological research with artificial intelligence

Since the late 2010s, Artificial Intelligence (AI) including machine learning, boosted through deep learning, has boomed as a vital tool to leverage computer vision, natural language processing and speech recognition in revolutionizing zoological research. This review provides an overview of the primary tasks, core models, datasets, and applications of AI in zoological research, including animal classification, resource conservation, behavior, development, genetics and evolution, breeding and health, disease models, and paleontology. Additionally, we explore the challenges and future directions of integrating AI into this field. Based on numerous case studies, this review outlines various avenues for incorporating AI into zoological research and underscores its potential to enhance our understanding of the intricate relationships that exist within the animal kingdom. As we build a bridge between beast and byte realms, this review serves as a resource for envisioning novel AI applications in zoological research that have not yet been explored.

replicAnt: a pipeline for generating annotated images of animals in complex environments using Unreal Engine

Deep learning-based computer vision methods are transforming animal behavioural research. Transfer learning has enabled work in non-model species, but still requires hand-annotation of example footage, and is only performant in well-defined conditions. To help overcome these limitations, we developed replicAnt, a configurable pipeline implemented in Unreal Engine 5 and Python, designed to generate large and variable training datasets on consumer-grade hardware. replicAnt places 3D animal models into complex, procedurally generated environments, from which automatically annotated images can be exported. We demonstrate that synthetic data generated with replicAnt can significantly reduce the hand-annotation required to achieve benchmark performance in common applications such as animal detection, tracking, pose-estimation, and semantic segmentation. We also show that it increases the subject-specificity and domain-invariance of the trained networks, thereby conferring robustness. In some applications, replicAnt may even remove the need for hand-annotation altogether. It thus represents a significant step towards porting deep learning-based computer vision tools to the field.

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

Develoment of image recognition AI algorithms for flower-visiting arthropods has the potential to revolutionize the way we monitor pollinators. Ecologists need light-weight models that can be deployed in a field setting and can classify with high accuracy. We tested the performance of three deep learning light-weight models, YOLOv5nano, YOLOv5small, and YOLOv7tiny, at object recognition and classification in real time on eight groups of flower-visiting arthropods using open-source image data. These eight groups contained four orders of insects that are known to perform the majority of pollination services in Europe (Hymenoptera, Diptera, Coleoptera, Lepidoptera) as well as other arthropod groups that can be seen on flowers but are not typically considered pollinators (e.g., spiders-Araneae). All three models had high accuracy, ranging from 93 to 97%. Intersection over union (IoU) depended on the relative area of the bounding box, and the models performed best when a single arthropod comprised a large portion of the image and worst when multiple small arthropods were together in a single image. The model could accurately distinguish flies in the family Syrphidae from the Hymenoptera that they are known to mimic. These results reveal the capability of existing YOLO models to contribute to pollination monitoring.

Object Detection of Small Insects in Time-Lapse Camera Recordings

As pollinators, insects play a crucial role in ecosystem management and world food production. However, insect populations are declining, necessitating efficient insect monitoring methods. Existing methods analyze video or time-lapse images of insects in nature, but analysis is challenging as insects are small objects in complex and dynamic natural vegetation scenes. In this work, we provide a dataset of primarily honeybees visiting three different plant species during two months of the summer. The dataset consists of 107,387 annotated time-lapse images from multiple cameras, including 9423 annotated insects. We present a method for detecting insects in time-lapse RGB images, which consists of a two-step process. Firstly, the time-lapse RGB images are preprocessed to enhance insects in the images. This motion-informed enhancement technique uses motion and colors to enhance insects in images. Secondly, the enhanced images are subsequently fed into a convolutional neural network (CNN) object detector. The method improves on the deep learning object detectors You Only Look Once (YOLO) and faster region-based CNN (Faster R-CNN). Using motion-informed enhancement, the YOLO detector improves the average micro F1-score from 0.49 to 0.71, and the Faster R-CNN detector improves the average micro F1-score from 0.32 to 0.56. Our dataset and proposed method provide a step forward for automating the time-lapse camera monitoring of flying insects.

The future of tropical insect diversity: strategies to fill data and knowledge gaps

The decline of insect diversity is a much-discussed, yet understudied phenomenon, particularly in the tropics, where the majority of insect abundance, diversity and biomass is found. Integrated approaches involving traditional taxonomic methods, new molecular approaches, and novel monitoring and identification tools and applications are needed to address related and challenging questions regarding how many species of tropical insects exist, their distributions and natural history, the relative impacts of global change drivers on insect diversity across complex tropical landscapes, and the effects of insect declines on ecosystem functions and services. The main barriers to addressing these challenges are a lack of capacity and funding for research on insects in tropical countries and a lack of recognition of their importance for ecosystem functioning and human wellbeing. Insects must be brought into policy agendas, local capacity and funding through cross-boundary collaborations and equitable scientific practices increased, and their importance emphasized.

Richer than Gold: the fungal biodiversity of Reserva Los Cedros, a threatened Andean cloud forest

BACKGROUND

Globally, many undescribed fungal taxa reside in the hyperdiverse, yet undersampled, tropics. These species are under increasing threat from habitat destruction by expanding extractive industry, in addition to global climate change and other threats. Reserva Los Cedros is a primary cloud forest reserve of ~ 5256 ha, and is among the last unlogged watersheds on the western slope of the Ecuadorian Andes. No major fungal survey has been done there, presenting an opportunity to document fungi in primary forest in an underrepresented habitat and location. Above-ground surveys from 2008 to 2019 resulted in 1760 vouchered collections, cataloged and deposited at QCNE in Ecuador, mostly Agaricales sensu lato and Xylariales. We document diversity using a combination of ITS barcode sequencing and digital photography, and share the information via public repositories (GenBank & iNaturalist).

RESULTS

Preliminary identifications indicate the presence of at least 727 unique fungal species within the Reserve, representing 4 phyla, 17 classes, 40 orders, 101 families, and 229 genera. Two taxa at Los Cedros have recently been recommended to the IUCN Fungal Red List Initiative (Thamnomyces chocöensis Læssøe and "Lactocollybia" aurantiaca Singer), and we add occurrence data for two others already under consideration (Hygrocybe aphylla Læssøe & Boertm. and Lamelloporus americanus Ryvarden).

CONCLUSIONS

Plants and animals are known to exhibit exceptionally high diversity and endemism in the Chocó bioregion, as the fungi do as well. Our collections contribute to understanding this important driver of biodiversity in the Neotropics, as well as illustrating the importance and utility of such data to conservation efforts.

RESUMEN

Antecedentes: A nivel mundial muchos taxones fúngicos no descritos residen en los trópicos hiper diversos aunque continúan submuestreados. Estas especies están cada vez más amenazadas por la destrucción del hábitat debido a la expansión de la industria extractivista además del cambio climático global y otras amenazas. Los Cedros es una reserva de bosque nublado primario de ~ 5256 ha y se encuentra entre las últimas cuencas hidrográficas no explotadas en la vertiente occidental de los Andes ecuatorianos. Nunca antes se ha realizado un estudio de diversidad micológica en el sitio, lo que significa una oportunidad para documentar hongos en el bosque primario, en hábitat y ubicación subrepresentatadas. El presente estudio recopila información entre el 2008 y 2019 muestreando material sobre todos los sustratos, reportando 1760 colecciones catalogadas y depositadas en el Fungario del QCNE de Ecuador, en su mayoría Agaricales sensu lato y Xylariales; además se documenta la diversidad mediante secuenciación de códigos de barras ITS y fotografía digital, la información está disponible en repositorios públicos digitales (GenBank e iNaturalist).

RESULTADOS

La identificación preliminar indica la presencia de al menos 727 especies únicas de hongos dentro de la Reserva, que representan 4 filos, 17 clases, 40 órdenes, 101 familias y 229 géneros. Recientemente dos taxones en Los Cedros se recomendaron a la Iniciativa de Lista Roja de Hongos de la UICN (Thamnomyces chocöensis Læssøe y "Lactocollybia" aurantiaca Singer) y agregamos datos de presencia de otros dos que ya estaban bajo consideración (Hygrocybe aphylla Læssøe & Boertm. y Lamelloporus americanus Ryvarden).

CONCLUSIONES

Se sabe que plantas y animales exhiben una diversidad y endemismo excepcionalmente altos en la bioregión del Chocó y los hongos no son la excepción. Nuestras colecciones contribuyen a comprender este importante promotor de la biodiversidad en el Neotrópico además de ilustrar la importancia y utilidad de dichos datos para los esfuerzos de conservación.

Taxonomic Delineation of the Old World Species Stomphastis thraustica (Lepidoptera: Gracillariidae) Feeding on Jatropha gossypiifolia (Euphorbiaceae) that Was Collected in the New World and Imported as a Biocontrol Agent to Australia

We provide the identification and species delineation of this biocontrol agent as Stomphastis thraustica (Meyrick in Trans Ent Soc Lond 80(1):107-120, 1908) belonging to the family Gracillariidae. We clarify the distribution pattern of S. thraustica, its host plant preferences, and present taxonomic and molecular diagnoses based on original morphological and genetic data as well as data retrieved from historic literature and genetic databases. Following our own collecting efforts in three continents Africa, South America, and Australia as well as our study of historic museum collection material, we present many new distribution records of S. thraustica for countries and territories in the world including the new discovery of this species in the Neotropical region and we report its introduction in Australia as a biocontrol agent. Using mitogenomic and COI gene data, we clarified that the closest relative of S. thraustica is Stomphastis sp. that occurs in Madagascar and Australia and feeds on the same host plant as S. thraustica - Jatropha gossypiifolia L. (Euphorbiaceae). The molecular sequence divergence in the mitochondrial DNA barcode fragment between these two closely related species S. thraustica and Stomphastis sp. is over 5.7% supporting that they are different species.

Increasing biodiversity knowledge through social media: A case study from tropical Bangladesh

Citizen science programs are becoming increasingly popular among naturalists but remain heavily biased taxonomically and geographically. However, with the explosive popularity of social media and the near-ubiquitous availability of smartphones, many post wildlife photographs on social media. Here, we illustrate the potential of harvesting these data to enhance our biodiversity understanding using Bangladesh, a tropical biodiverse country, as a case study. We compared biodiversity records extracted from Facebook with those from the Global Biodiversity Information Facility (GBIF), collating geospatial records for 1013 unique species, including 970 species from Facebook and 712 species from GBIF. Although most observation records were biased toward major cities, the Facebook records were more evenly spatially distributed. About 86% of the Threatened species records were from Facebook, whereas the GBIF records were almost entirely Of Least Concern species. To reduce the global biodiversity data shortfall, a key research priority now is the development of mechanisms for extracting and interpreting social media biodiversity data.

Getting the bugs out of AI: Advancing ecological research on arthropods through computer vision

Deep learning for computer vision has shown promising results in the field of entomology, however, there still remains untapped potential. Deep learning performance is enabled primarily by large quantities of annotated data which, outside of rare circumstances, are limited in ecological studies. Currently, to utilize deep learning systems, ecologists undergo extensive data collection efforts, or limit their problem to niche tasks. These solutions do not scale to region agnostic models. However, there are solutions that employ data augmentation, simulators, generative models, and self-supervised learning that can supplement limited labelled data. Here, we highlight the success of deep learning for computer vision within entomology, discuss data collection efforts, provide methodologies for optimizing learning from limited annotations, and conclude with practical guidelines for how to achieve a foundation model for entomology capable of accessible automated ecological monitoring on a global scale.

Remote Nanoscopy with Infrared Elastic Hyperspectral Lidar

Monitoring insects of different species to understand the factors affecting their diversity and decline is a major challenge. Laser remote sensing and spectroscopy offer promising novel solutions to this. Coherent scattering from thin wing membranes also known as wing interference patterns (WIPs) have recently been demonstrated to be species specific. The colors of WIPs arise due to unique fringy spectra, which can be retrieved over long distances. To demonstrate this, a new concept of infrared (950-1650 nm) hyperspectral lidar with 64 spectral bands based on a supercontinuum light source using ray-tracing and 3D printing is developed. A lidar with an unprecedented number of spectral channels, high signal-to-noise ratio, and spatio-temporal resolution enabling detection of free-flying insects and their wingbeats. As proof of principle, coherent scatter from a damselfly wing at 87 m distance without averaging (4 ms recording) is retrieved. The fringed signal properties are used to determine an effective wing membrane thickness of 1412 nm with ±4 nm precision matching laboratory recordings of the same wing. Similar signals from free flying insects (2 ms recording) are later recorded. The accuracy and the method's potential are discussed to discriminate species by capturing coherent features from free-flying insects.

Dual-Band Infrared Scheimpflug Lidar Reveals Insect Activity in a Tropical Cloud Forest

We describe an entomological dual-band 808 and 980 nm lidar system which has been implemented in a tropical cloud forest (Ecuador). The system was successfully tested at a sample rate of 5 kHz in a cloud forest during challenging foggy conditions (extinction coefficients up to 20 km^-1). At times, the backscattered signal could be retrieved from a distance of 2.929 km. We present insect and bat observations up to 200 m during a single night with an emphasis on fog aspects, potentials, and benefits of such dual-band systems. We demonstrate that the modulation contrast between insects and fog is high in the frequency domain compared to intensity in the time domain, thus allowing for better identification and quantification in misty forests. Oscillatory lidar extinction effects are shown in this work for the first time, caused by the combination of dense fog and large moths partially obstructing the beam. We demonstrate here an interesting case of a moth where left- and right-wing movements induced oscillations in both intensity and pixel spread. In addition, we were able to identify the dorsal and ventral sides of the wings by estimating the corresponding melanization with the dual-band lidar. We demonstrate that the wing beat trajectories in the dual-band parameter space are complementary rather than covarying or redundant, thus a dual-band entomological lidar approach to biodiversity studies is feasible in situ and endows species specificity differentiation. Future improvements are discussed. The introduction of these methodologies opens the door to a wealth of possible experiments to monitor, understand, and safeguard the biological resources of one of the most biodiverse countries on Earth.

Progress in understanding the vulnerability of freshwater ecosystems

The ability to collect and synthesize long-term environmental monitoring data is essential for the effective management of freshwater ecosystems. Progress has been made in assessment and monitoring approaches that have integrated routine monitoring programs into more holistic watershed-scale vulnerability assessments. While the concept of vulnerability assessment is well-defined for ecosystems, complementary and sometimes competing concepts of adaptive management, ecological integrity, and ecological condition complicate the communication of results to a broader audience. Here, we identify progress in freshwater assessments that can contribute to the identification and communication of freshwater vulnerability. We review novel methods that address common challenges associated with: 1) a lack of baseline information, 2) variability associated with a spatial context, and 3) the taxonomic sufficiency of biological indicators used to make inferences about ecological conditions. Innovation in methods and communication are discussed as a means to highlight meaningful cost-effective results that target policy towards heuristic ecosystem-management.

Future of DNA-based insect monitoring

Insects are crucial for ecosystem health but climate change and pesticide use are driving massive insect decline. To mitigate this loss, we need new and effective monitoring techniques. Over the past decade there has been a shift to DNA-based techniques. We describe key emerging techniques for sample collection. We suggest that the selection of tools should be broadened, and that DNA-based insect monitoring data need to be integrated more rapidly into policymaking. We argue that there are four key areas for advancement, including the generation of more complete DNA barcode databases to interpret molecular data, standardisation of molecular methods, scaling up of monitoring efforts, and integrating molecular tools with other technologies that allow continuous, passive monitoring based on images and/or laser imaging, detection, and ranging (LIDAR).

Untargeted Metabolomics for Integrative Taxonomy: Metabolomics, DNA Marker-Based Sequencing, and Phenotype Bioimaging

Integrative taxonomy is a fundamental part of biodiversity and combines traditional morphology with additional methods such as DNA sequencing or biochemistry. Here, we aim to establish untargeted metabolomics for use in chemotaxonomy. We used three thallose liverwort species Riccia glauca, R. sorocarpa, and R. warnstorfii (order Marchantiales, Ricciaceae) with Lunularia cruciata (order Marchantiales, Lunulariacea) as an outgroup. Liquid chromatography high-resolution mass-spectrometry (UPLC/ESI-QTOF-MS) with data-dependent acquisition (DDA-MS) were integrated with DNA marker-based sequencing of the trnL-trnF region and high-resolution bioimaging. Our untargeted chemotaxonomy methodology enables us to distinguish taxa based on chemophenetic markers at different levels of complexity: (1) molecules, (2) compound classes, (3) compound superclasses, and (4) molecular descriptors. For the investigated Riccia species, we identified 71 chemophenetic markers at the molecular level, a characteristic composition in 21 compound classes, and 21 molecular descriptors largely indicating electron state, presence of chemical motifs, and hydrogen bonds. Our untargeted approach revealed many chemophenetic markers at different complexity levels that can provide more mechanistic insight into phylogenetic delimitation of species within a clade than genetic-based methods coupled with traditional morphology-based information. However, analytical and bioinformatics analysis methods still need to be better integrated to link the chemophenetic information at multiple scales.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Are digital services the right solution for empowering smallholder farmers? A perspective enlightened by COVID-19 experiences to inform smart IPM

The COVID-19 pandemic, surprised many through its impact on the food systems, resulting in collapses in the food production value chains and in the integrated pest disease management sector with fatal outcomes in many places. However, the impact of COVID-19 and the digital experience perspective on Integrating Pest Management (IPM) is still yet to be understood. In Africa, the impact was devastating, mostly for the vulnerable smallholder farm households, who were rendered unable to access markets to purchase inputs and sell their produce during the lockdown period. By using a holistic approach the paper reviews different Information and Communications Technologies (ICTs), digitalization, and how this enhanced the capacity of smallholder farmers resilient, and inform their smart-IPM practices in order to improve food systems' amidst climate change during and in the post-COVID-19 period. Different digital modalities were adopted to ensure continuous food production, access to inputs and finances, and selling surplus production among others. This was largely possible by using ICTs to deliver these needed services digitally. The study shares contributions and capacity perspectives of ICTs for empowering smallholder farmers to boost the resilience of their food systems based on COVID-19 successful experiences. Thus digital solutions must be embraced in the delivery of extension service on pest management and good agronomic practices, money transfers for purchasing inputs, receiving payment for sold farm produce, and markets information exchange. These are key avenues through which digital solutions strategically supported smallholder-based food systems through the pandemic.

Artificial intelligence (AI): a new window to revamp the vector-borne disease control

Artificial intelligence (AI) facilitates scientists to devise intelligent machines that work and behave like humans to resolve difficulties and problems by utilizing minimal resources. The Healthcare sector has benefited due to this. Mosquito-transmitted diseases pose a significant health risk. Despite all advances, present strategies for curbing these diseases still depend largely on controlling the mosquito vectors. This strategy demands an army of entomology experts for thorough monitoring, determining, and finally eradicating the targeted mosquito population. Deep learning (DL) algorithms may substitute such unmanageable processes. The current review focuses on how AI, with particular emphasis on deep learning, demonstrates effectiveness in quick detection, identification, monitoring, and finally controlling the target mosquito populations with minimal resources. It accelerates the pace of operation and data exploration on ongoing evolutionary status, tendency to feed blood, and age grading of mosquitoes. The successful combination of computer and biological sciences will provide practical insight and generate a new research niche in this study area.

A roadmap for ladybird conservation and recovery

Ladybirds (Coleoptera: Coccinellidae) provide services that are critical to food production, and they fulfill an ecological role as a food source for predators. The richness, abundance, and distribution of ladybirds, however, are compromised by many anthropogenic threats. Meanwhile, a lack of knowledge of the conservation status of most species and the factors driving their population dynamics hinders the development and implementation of conservation strategies for ladybirds. We conducted a review of the literature on the ecology, diversity, and conservation of ladybirds to identify their key ecological threats. Ladybird populations are most affected by climate factors, landscape composition, and biological invasions. We suggest mitigating actions for ladybird conservation and recovery. Short-term actions include citizen science programs and education, protective measures for habitat recovery and threatened species, prevention of the introduction of non-native species, and the maintenance and restoration of natural areas and landscape heterogeneity. Mid-term actions involve the analysis of data from monitoring programs and insect collections to disentangle the effect of different threats to ladybird populations, understand habitat use by taxa on which there is limited knowledge, and quantify temporal trends of abundance, diversity, and biomass along a management-intensity gradient. Long-term actions include the development of a worldwide monitoring program based on standardized sampling to fill data gaps, increase explanatory power, streamline analyses, and facilitate global collaborations.

Micro-CT and deep learning: Modern techniques and applications in insect morphology and neuroscience

Advances in modern imaging and computer technologies have led to a steady rise in the use of micro-computed tomography (µCT) in many biological areas. In zoological research, this fast and non-destructive method for producing high-resolution, two- and three-dimensional images is increasingly being used for the functional analysis of the external and internal anatomy of animals. µCT is hereby no longer limited to the analysis of specific biological tissues in a medical or preclinical context but can be combined with a variety of contrast agents to study form and function of all kinds of tissues and species, from mammals and reptiles to fish and microscopic invertebrates. Concurrently, advances in the field of artificial intelligence, especially in deep learning, have revolutionised computer vision and facilitated the automatic, fast and ever more accurate analysis of two- and three-dimensional image datasets. Here, I want to give a brief overview of both micro-computed tomography and deep learning and present their recent applications, especially within the field of insect science. Furthermore, the combination of both approaches to investigate neural tissues and the resulting potential for the analysis of insect sensory systems, from receptor structures via neuronal pathways to the brain, are discussed.

Protected areas and the future of insect conservation

Anthropogenic pressures are driving insect declines across the world. Although protected areas (PAs) play a prominent role in safeguarding many vertebrate species from human-induced threats, insects are not widely considered when designing PA systems or building strategies for PA management. We review the effectiveness of PAs for insect conservation and find substantial taxonomic and geographic gaps in knowledge. Most research focuses on the representation of species, and few studies assess threats to insects or the role that effective PA management can play in insect conservation. We propose a four-step research agenda to help ensure that insects are central in efforts to expand the global PA network under the Post-2020 Global Biodiversity Framework.

Silbido profundo: An open source package for the use of deep learning to detect odontocete whistles

This work presents an open-source matlab software package for exploiting recent advances in extracting tonal signals from large acoustic data sets. A whistle extraction algorithm published by Li, Liu, Palmer, Fleishman, Gillespie, Nosal, Shiu, Klinck, Cholewiak, Helble, and Roch [(2020). Proceedings of the International Joint Conference on Neural Networks, July 19-24, Glasgow, Scotland, p. 10] is incorporated into silbido, an established software package for extraction of cetacean tonal calls. The precision and recall of the new system were over 96% and nearly 80%, respectively, when applied to a whistle extraction task on a challenging two-species subset of a conference-benchmark data set. A second data set was examined to assess whether the algorithm generalized to data that were collected across different recording devices and locations. These data included 487 h of weakly labeled, towed array data collected in the Pacific Ocean on two National Oceanographic and Atmospheric Administration (NOAA) cruises. Labels for these data consisted of regions of toothed whale presence for at least 15 species that were based on visual and acoustic observations and not limited to whistles. Although the lack of per whistle-level annotations prevented measurement of precision and recall, there was strong concurrence of automatic detections and the NOAA annotations, suggesting that the algorithm generalizes well to new data.

Using deep learning to study emotional behavior in rodent models

Quantifying emotional aspects of animal behavior (e.g., anxiety, social interactions, reward, and stress responses) is a major focus of neuroscience research. Because manual scoring of emotion-related behaviors is time-consuming and subjective, classical methods rely on easily quantified measures such as lever pressing or time spent in different zones of an apparatus (e.g., open vs. closed arms of an elevated plus maze). Recent advancements have made it easier to extract pose information from videos, and multiple approaches for extracting nuanced information about behavioral states from pose estimation data have been proposed. These include supervised, unsupervised, and self-supervised approaches, employing a variety of different model types. Representations of behavioral states derived from these methods can be correlated with recordings of neural activity to increase the scope of connections that can be drawn between the brain and behavior. In this mini review, we will discuss how deep learning techniques can be used in behavioral experiments and how different model architectures and training paradigms influence the type of representation that can be obtained.

A Swin Transformer-based model for mosquito species identification

Mosquito transmit numbers of parasites and pathogens resulting in fatal diseases. Species identification is a prerequisite for effective mosquito control. Existing morphological and molecular classification methods have evitable disadvantages. Here we introduced Deep learning techniques for mosquito species identification. A balanced, high-definition mosquito dataset with 9900 original images covering 17 species was constructed. After three rounds of screening and adjustment-testing (first round among 3 convolutional neural networks and 3 Transformer models, second round among 3 Swin Transformer variants, and third round between 2 images sizes), we proposed the first Swin Transformer-based mosquito species identification model (Swin MSI) with 99.04% accuracy and 99.16% F1-score. By visualizing the identification process, the morphological keys used in Swin MSI were similar but not the same as those used by humans. Swin MSI realized 100% subspecies-level identification in Culex pipiens Complex and 96.26% accuracy for novel species categorization. It presents a promising approach for mosquito identification and mosquito borne diseases control.

An overview of remote monitoring methods in biodiversity conservation

Conservation of biodiversity is critical for the coexistence of humans and the sustenance of other living organisms within the ecosystem. Identification and prioritization of specific regions to be conserved are impossible without proper information about the sites. Advanced monitoring agencies like the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES) had accredited that the sum total of species that are now threatened with extinction is higher than ever before in the past and are progressing toward extinct at an alarming rate. Besides this, the conceptualized global responses to these crises are still inadequate and entail drastic changes. Therefore, more sophisticated monitoring and conservation techniques are required which can simultaneously cover a larger surface area within a stipulated time frame and gather a large pool of data. Hence, this study is an overview of remote monitoring methods in biodiversity conservation via a survey of evidence-based reviews and related studies, wherein the description of the application of some technology for biodiversity conservation and monitoring is highlighted. Finally, the paper also describes various transformative smart technologies like artificial intelligence (AI) and/or machine learning algorithms for enhanced working efficiency of currently available techniques that will aid remote monitoring methods in biodiversity conservation.

A Review of Automated Bioacoustics and General Acoustics Classification Research

Automated bioacoustics classification has received increasing attention from the research community in recent years due its cross-disciplinary nature and its diverse application. Applications in bioacoustics classification range from smart acoustic sensor networks that investigate the effects of acoustic vocalizations on species to context-aware edge devices that anticipate changes in their environment adapt their sensing and processing accordingly. The research described here is an in-depth survey of the current state of bioacoustics classification and monitoring. The survey examines bioacoustics classification alongside general acoustics to provide a representative picture of the research landscape. The survey reviewed 124 studies spanning eight years of research. The survey identifies the key application areas in bioacoustics research and the techniques used in audio transformation and feature extraction. The survey also examines the classification algorithms used in bioacoustics systems. Lastly, the survey examines current challenges, possible opportunities, and future directions in bioacoustics.