Arthropods, including insects, represent the most diverse group and contribute significantly to animal biomass. Automatic monitoring of insects and other arthropods enables quick and efficient observation and management of ecologically and economically important targets such as pollinators, natural enemies, disease vectors, and agricultural pests. The integration of cameras and computer vision facilitates innovative monitoring approaches for agriculture, ecology, entomology, evolution, and biodiversity. However, studying insects and their interactions with flowers and vegetation in natural environments remains challenging, even with automated camera monitoring.This paper presents a comprehensive methodology to monitor abundance and diversity of arthropods in the wild and to quantify floral cover as a key resource. We apply the methods across more than 10 million images recorded over two years using 48 insect camera traps placed in three main habitat types. The cameras monitor arthropods, including insect visits, on a specific mix of Sedum plant species with white, yellow and red/pink colored of flowers. The proposed deep-learning pipeline estimates flower cover and detects and classifies arthropod taxa from time-lapse recordings. However, the flower cover serves only as an estimate to correlate insect activity with the flowering plants.Color and semantic segmentation with DeepLabv3 are combined to estimate the percent cover of flowers of different colors. Arthropod detection incorporates motion-informed enhanced images and object detection with You-Only-Look-Once (YOLO), followed by filtering stationary objects to minimize double counting of non-moving animals and erroneous background detections. This filtering approach has been demonstrated to significantly decrease the incidence of false positives, since arthropods, occur in less than 3% of the captured images.The final step involves grouping arthropods into 19 taxonomic classes. Seven state-of-the-art models were trained and validated, achieving F1-scores ranging from 0.81 to 0.89 in classification of arthropods. Among these, the final selected model, EfficientNetB4, achieved an 80% average precision on randomly selected samples when applied to the complete pipeline, which includes detection, filtering, and classification of arthropod images collected in 2021. As expected during the beginning and end of the season, reduced flower cover correlates with a noticeable drop in arthropod detections. The proposed method offers a cost-effective approach to monitoring diverse arthropod taxa and flower cover in natural environments using time-lapse camera recordings.

Abstract In the face of the global biodiversity crisis, collecting comprehensive data and making the best use of existing data are becoming increasingly important to understand patterns and drivers of environmental and biological phenomena at different scales. Here we address the concept of secondary data, which refers to additional information unintentionally captured in species records, especially in multimedia‐based citizen science reports. We argue that secondary data can provide a wealth of ecologically relevant information, the utilisation of which can enhance our understanding of traits and interactions among individual organisms, populations and biodiversity dynamics in general. We explore the possibilities offered by secondary data and describe their main types and sources. An overview of research in this field provides a synthesis of the results already achieved using secondary data and different approaches to information extraction. Finally, we discuss challenges to the widespread use of secondary data, such as biases, licensing issues, use of metadata and lack of awareness of this trove of data due to a missing common terminology, as well as possible solutions to overcome these barriers. Although the exploration and use of secondary data is only emerging, the many opportunities identified show how these data can enrich biodiversity research and monitoring.

Cameras and computer vision are revolutionising the study of insects, creating new research opportunities within agriculture, epidemiology, evolution, ecology and monitoring of biodiversity. However, the diversity of insects and close resemblances of many species are a major challenge for image-based species-level classification. 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) identify 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 to quantify the 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-ofthe-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 which were not present in the training set. We found that incorporating a simple taxonomy into our model increased the 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, forming a valuable step towards high-level classification of species not found in training data.

Fungi and invertebrates comprise a major part of biodiversity in dead wood ecosystems and invertebrates depend on fungi to utilise the dead wood resource. Many invertebrates also visit the long‐lived fruit bodies of wood‐decay fungi to feed on spores, the hymenium or other invertebrates. However, as traditional sampling methods are labour‐intensive, we know little of these interactions. In this study, we use time‐lapse cameras to monitor invertebrates visiting the hymenium of a common wood‐decay fungus, Fomitopsis pinicola , and explain their activity in terms of temporal variation, temperature and presence of Gyrophaena boleti , a highly abundant fungivorous beetle living primarily in fruit bodies of F. pinicola . The most common invertebrates on F. pinicola fruit bodies were Coleoptera, Araneae, Diptera, Gastropoda and Chilopoda. The invertebrate activity exhibited strong temporal variation with higher abundance during night and, for Coleoptera, earlier in the season. We discuss how this might correlate with the sporulation period of F. pinicola . The presence of G. boleti had a positive impact on the predatory Lordithon lunulatus and Ipidia binotata , and a negative impact on the fungivorous Thymalus limbatus and Peltis ferruginea . Chilopoda and L. lunulatus were ephemeral visitors, while the fungivorous Coleoptera and Araneae stayed the longest. We estimated the invertebrates' visitation frequency and duration, which would be time‐consuming to obtain with traditional methods. We offer improvements to our method and urge future research on invertebrate–fungus interactions to quantify invertebrate visits to fungal fruit bodies.

Table of 44 annotated visits to T. pratense inflorescences (‘visits.csv’), in chronological order. From left to right, column descriptions are as follows: OTU = operational taxonomic unit. Bombus is suffixed ‘Y’ for yellow-banded, ‘R’ for red-tailed or ‘G’ for ginger; ann_ID = inflorescence ID during annotation of visitors, links to Dataset S2; camera_ID = ID of the camera; DOY = day of the year of visit; hour = hour of visit; minute = minute of visit; continuous = logical flag for “continuous” camera schedule (TRUE) or “focused” camera schedule (FALSE).

AbstractThe advancement of spring is a widespread biological response to climate change observed across taxa and biomes. However, the species level responses to warming are complex and the underlying mechanisms are difficult to disentangle. This is partly due to a lack of data, which are typically collected by direct observations, and thus very time‐consuming to obtain. Data deficiency is especially pronounced in the Arctic where the warming is particularly severe. We present a method for automated monitoring of flowering phenology of specific plant species at very high temporal resolution through full growing seasons and across geographical regions. The method consists of image‐based monitoring of field plots using near‐surface time‐lapse cameras and subsequent automated detection and counting of flowers in the images using a convolutional neural network. We demonstrate the feasibility of collecting flower phenology data using automatic time‐lapse cameras and show that the temporal resolution of the results surpasses what can be collected by traditional observation methods. We focus on two Arctic species, the mountain avens Dryas octopetala and Dryas integrifolia in 20 image series from four sites. Our flower detection model proved capable of detecting flowers of the two species with a remarkable precision of 0.918 (adjusted to 0.966) and a recall of 0.907. Thus, the method can automatically quantify the seasonal dynamics of flower abundance at fine scale and return reliable estimates of traditional phenological variables such as the timing of onset, peak, and end of flowering. We describe the system and compare manual and automatic extraction of flowering phenology data from the images. Our method can be directly applied on sites containing mountain avens using our trained model, or the model could be fine‐tuned to other species. We discuss the potential of automatic image‐based monitoring of flower phenology and how the method can be improved and expanded for future studies.

R code (‘analyse_seedset.R’) to reproduce statistical analyses in the paper from the data provided.

High-resolution monitoring is fundamental to understand ecosystems dynamics in an era of global change and biodiversity declines. While real-time and automated monitoring of abiotic components has been possible for some time, monitoring biotic components-for example, individual behaviours and traits, and species abundance and distribution-is far more challenging. Recent technological advancements offer potential solutions to achieve this through: (i) increasingly affordable high-throughput recording hardware, which can collect rich multidimensional data, and (ii) increasingly accessible artificial intelligence approaches, which can extract ecological knowledge from large datasets. However, automating the monitoring of facets of ecological communities via such technologies has primarily been achieved at low spatiotemporal resolutions within limited steps of the monitoring workflow. Here, we review existing technologies for data recording and processing that enable automated monitoring of ecological communities. We then present novel frameworks that combine such technologies, forming fully automated pipelines to detect, track, classify and count multiple species, and record behavioural and morphological traits, at resolutions which have previously been impossible to achieve. Based on these rapidly developing technologies, we illustrate a solution to one of the greatest challenges in ecology: the ability to rapidly generate high-resolution, multidimensional and standardised data across complex ecologies.

Snow is an important driver of ecosystem processes in cold biomes. Snow accumulation determines ground temperature, light conditions, and moisture availability during winter. It also affects the growing season's start and end, and plant access to moisture and nutrients. Here, we review the current knowledge of the snow cover's role for vegetation, plant- animal interactions, permafrost conditions, microbial processes, and biogeochemical cycling. We also compare studies of natural snow gradients with snow experimental manipulation studies to assess time scale difference of these approaches. The number of tundra snow studies has increased considerably in recent years, yet we still lack a comprehensive overview of how altered snow conditions will affect these ecosystems. Specifically, we found a mismatch in the timing of snowmelt when comparing studies of natural snow gradients with snow manipulations. We found that snowmelt timing achieved by snow addition and snow removal manipulations (average 7.9 days advance and 5.5 days delay, respectively) were substantially lower than the temporal variation over natural spatial gradients within a given year (mean range 56 days) or among years (mean range 32 days). Differences between snow study approaches need to be accounted for when projecting snow dynamics and their impact on ecosystems in future climates.

Reported insect declines have dramatically increased the global demand for standardized insect monitoring data. Image-based monitoring can generate such data cost-efficiently and non-invasively. However, extracting ecological data from images is more challenging for insects than for vertebrates because of their small size and great diversity. Deep learning facilitates fast and accurate insect detection and identification, but the lack of training data for coveted deep learning models is a major obstacle for their application. We present a large annotated image dataset of functionally important insect taxa. The primary dataset consists of 29,960 annotated insects representing nine taxa including bees, hoverflies, butterflies and beetles across more than two million images recorded with ten time-lapse cameras mounted over flowers during the summer of 2019. The insect image dataset was extracted using an iterative approach: First, a preliminary detection model identified candidate insects. Second, candidate insects were manually screened by users of an online citizen science platform. Finally, all annotations were quality checked by experts. We used the dataset to train and compare the performance of selected You Only Look Once (YOLO) deep learning algorithms. We show that these models detect and classify small insects in complex scenes with unprecedented accuracy. The best performing YOLOv5 model consistently identifies nine dominant insect species that play important roles in pollination and pest control across Europe. The model reached an average precision of 92.7% and recall of 93.8 % in detection and classification across species. Importantly, when presented with uncommon or unclear insects not seen during training, our model detects 80% of individuals and usually interprets them as closely related species. This is a useful property to (1) detect rare insects for which training data are absent, and (2) generate new training data to correctly identify those insects in future. Our camera system, dataset and deep learning framework show promising results in non-destructive monitoring of insects. Furthermore, resulting data are useful to quantify phenology, abundance, and foraging behaviour of flower-visiting insects. Above all, this dataset represents a critical first benchmark for future development and evaluation of deep learning models for insect detection and identification.

Abstract Insects are declining in abundance and diversity, but their population trends remain uncertain as insects are difficult to monitor. Manual methods require substantial time investment in trapping and subsequent species identification. Camera trapping can alleviate some of the manual fieldwork, but the large quantities of image data are challenging to analyse. By embedding the image analyses into the recording process using computer vision techniques, it is possible to focus efforts on the most ecologically relevant image data. Here, we present an intelligent camera system, capable of detecting, tracking, and identifying individual insects in situ. We constructed the system from commercial off‐the‐shelf components and used deep learning open source software to perform species detection and classification. We present the Insect Classification and Tracking algorithm (ICT) that performs real‐time classification and tracking at 0.33 frames per second. The system can upload summary data on the identity and movement track of insects to a server via the internet on a daily basis. We tested our system during the summer 2020 and detected 2994 insect tracks across 98 days. We achieved an average precision of 89% for correctly classified insect tracks of eight different species. This result was based on 504 manually verified tracks observed in videos during 10 days with varying insect activities. Using the track data, we could estimate the mean residence time for individual flower visiting insects within the field of view of the camera, and we were able to show a substantial variation in residence time among insect taxa. For honeybees, which were most abundant, residence time also varied through the season in relation to the plant species in bloom. Our proposed automated system showed promising results in non‐destructive and real‐time monitoring of insects and provides novel information about phenology, abundance, foraging behaviour, and movement ecology of flower visiting insects.

Recent decades have seen a surge in awareness about insect pollinator declines. Social bees receive the most attention, but most flower-visiting species are lesser known, non-bee insects. Nocturnal flower visitors, e.g. moths, are especially difficult to observe and largely ignored in pollination studies. Clearly, achieving balanced monitoring of all pollinator taxa represents a major scientific challenge. Here, we use time-lapse cameras for season-wide, day-and-night pollinator surveillance of Trifolium pratense (L.; red clover) in an alpine grassland. We reveal the first evidence to suggest that moths, mainly Noctua pronuba (L.; large yellow underwing), pollinate this important wildflower and forage crop, providing 34% of visits (bumblebees: 61%). This is a remarkable finding; moths have received no recognition throughout a century of T. pratense pollinator research. We conclude that despite a non-negligible frequency and duration of nocturnal flower visits, nocturnal pollinators of T. pratense have been systematically overlooked. We further show how the relationship between visitation and seed set may only become clear after accounting for moth visits. As such, population trends in moths, as well as bees, could profoundly affect T. pratense seed yield. Ultimately, camera surveillance gives fair representation to non-bee pollinators and lays a foundation for automated monitoring of species interactions in future.

Most animal species on Earth are insects, and recent reports suggest that their abundance is in drastic decline. Although these reports come from a wide range of insect taxa and regions, the evidence to assess the extent of the phenomenon is sparse. Insect populations are challenging to study, and most monitoring methods are labor intensive and inefficient. Advances in computer vision and deep learning provide potential new solutions to this global challenge. Cameras and other sensors can effectively, continuously, and noninvasively perform entomological observations throughout diurnal and seasonal cycles. The physical appearance of specimens can also be captured by automated imaging in the laboratory. When trained on these data, deep learning models can provide estimates of insect abundance, biomass, and diversity. Further, deep learning models can quantify variation in phenotypic traits, behavior, and interactions. Here, we connect recent developments in deep learning and computer vision to the urgent demand for more cost-efficient monitoring of insects and other invertebrates. We present examples of sensor-based monitoring of insects. We show how deep learning tools can be applied to exceptionally large datasets to derive ecological information and discuss the challenges that lie ahead for the implementation of such solutions in entomology. We identify four focal areas, which will facilitate this transformation: 1) validation of image-based taxonomic identification; 2) generation of sufficient training data; 3) development of public, curated reference databases; and 4) solutions to integrate deep learning and molecular tools.