Laurel B. Symes

There has been a growing need for non‐lethal methods of monitoring pollinators. Despite advances in passive acoustic monitoring (PAM) transforming other fields of wildlife research, its application to pollinator monitoring has remained limited. However, bees produce distinctive flight and sonication sounds, making them promising candidates for PAM. We developed two convolutional neural network models to detect bee acoustic signals from field recordings. Our dataset comprised 594 recordings collected over five years from 43 sites and encompassed a broad range of habitat types and background noise conditions. The models primarily target honey bees ( Apis mellifera ) and bumble bees ( Bombus spp.). Model 1 detects overall bee activity, including honey bee and bumble bee flight and sonication sounds as well as foraging sounds produced by other species such as the eastern carpenter bee ( Xylocopa virginica ). Model 2 distinguishes honey bee flight, bumble bee flight and bumble bee sonication. Both models were validated against independent field observations made by trained observers. At a confidence threshold of 0.9, both models achieved high precision (93%–97%), with lower recall (13%–44%), prioritizing reliable detections over detection completeness. Model detections of overall bee activity and honey bee and bumble bee activity were strongly correlated with observer counts in the field. Model detections occurred primarily within 50 cm of the recorder. Both models are available within the Raven Pro platform, a user‐friendly acoustic analysis tool. This approach provides a standardized, non‐lethal method for monitoring pollinator activity in real‐world soundscapes, complementing traditional survey techniques and supporting long‐term ecological research and conservation.

Naturally selected adaptations are often thought to impair the elaboration of conspicuous sexual signals. In katydids, males produce acoustic signals by rubbing together structures on their forewings; specialized forewing cells then radiate this sound. These dedicated sound-producing structures are found on a physically distinct basal area of the forewing, but in many species, the remainder of the wing has evolved enormous, exaggerated blade-like or leaf-like structures under natural selection. We tested whether removal of such adjacent, naturally selected modifications enhances the attractiveness of male sexual signals by releasing bioacoustic constraints caused by their physical connection on the wing surface. Acoustic and resonance measurements of the leaf-mimic Viadana brunneri before and after removing the non-sound-producing, leaf-mimicking, portion of the forewing demonstrate that these regions decrease the frequency of male song and increase its amplitude (i.e. loudness). Using a playback experiment with calls from the intact versus wing-clipped males, we found that females prefer the lower frequency calls of males with the non-stridulatory portion of their forewings intact. Thus, the function and attractiveness of intraspecific signals can be enhanced by naturally selected adaptations, contradicting the common assumption that adaptations for mate attraction and predator avoidance represent functional compromises between sexual and natural selection.

Bird species vary widely in their diurnal vocalization patterns, and the drivers of this variation are not well understood. Using passive acoustic monitoring, we examined species-specific vocal activity patterns at dawn and dusk for a tropical bird community in the Western Ghats biodiversity hotspot in India. We tested whether environmental factors (e.g. signal transmission conditions, ambient light, and resource availability) and social factors (e.g. territoriality) best-explained patterns of diurnal variation in vocal activity. Overall, we found that species-specific vocal activity was significantly higher at dawn ( p < 0.05). Phylogenetic generalized least squares regressions revealed that territoriality and diet both predicted stronger dawn-biased activity. Specifically, highly territorial birds (standardized effect size (SES) = 1.20, lower donfidence interval (LCI)= 0.24, upper confidence interval (UCI) = 2.16, p = 0.01) and omnivores (SES = 0.82, LCI = −0.04, UCI = 1.68, p = 0.06) had higher levels of vocal activity at dawn. Surprisingly, we failed to find any evidence in support of environmental factors in explaining dawn-biased vocal activity. Our multi-taxon approach allowed us to assess the vocal activity patterns for an entire tropical bird community. Future research must incorporate additional geographic locations and combine visual and aural observations to better understand the drivers of diurnal variation in vocal activity. This article is part of the theme issue ‘Acoustic monitoring for tropical ecology and conservation’.

Passive acoustic monitoring (PAM) is a powerful tool for studying ecosystems. However, its effective application in tropical environments, particularly for insects, poses distinct challenges. Neotropical katydids produce complex species-specific calls, spanning mere milliseconds to seconds and spread across broad audible and ultrasonic frequencies. However, subtle differences in inter-pulse intervals or central frequencies are often the only discriminatory traits. These extremities, coupled with low source levels and susceptibility to masking by ambient noise, challenge species identification in PAM recordings. This study aimed to develop a deep learning-based solution to automate the recognition of 31 katydid species of interest in a biodiverse Panamanian forest with over 80 katydid species. Besides the innate challenges, our efforts were also encumbered by a limited and imbalanced initial training dataset comprising domain-mismatched recordings. To overcome these, we applied rigorous data engineering, improving input variance through controlled playback re-recordings and by employing physics-based data augmentation techniques, and tuning signal-processing, model and training parameters to produce a custom well-fit solution. Methods developed here are incorporated into Koogu, an open-source Python-based toolbox for developing deep learning-based bioacoustic analysis solutions. The parametric implementations offer a valuable resource, enhancing the capabilities of PAM for studying insects in tropical ecosystems. This article is part of the theme issue ‘Towards a toolkit for global insect biodiversity monitoring’.

Night-time light can have profound ecological effects, even when the source is natural moonlight. The impacts of light can, however, vary substantially by taxon, habitat and geographical region. We used a custom machine learning model built with the Python package Koogu to investigate the in situ effects of moonlight on the calling activity of neotropical forest katydids over multiple years. We prioritised species with calls that were commonly detected in human annotated data, enabling us to evaluate model performance. We focused on eight species of katydids that the model identified with high precision (generally greater than 0.90) and moderate-to-high recall (minimum 0.35), ensuring that detections were generally correct and that many calls were detected. These results suggest that moonlight has modest effects on the amount of calling, with the magnitude and direction of effect varying by species: half of the species showed positive effects of light and half showed negative. These findings emphasize the importance of understanding natural history for anticipating how biological communities respond to moonlight. The methods applied in this project highlight the emerging opportunities for evaluating large quantities of data with machine learning models to address ecological questions over space and time. This article is part of the theme issue ‘Towards a toolkit for global insect biodiversity monitoring’.

Synopsis: Animals often signal in multiple sensory modalities to attract mates, but the level of signaling investment in each modality can differ dramatically between individuals and across species. When functionally overlapping signals are produced in different modalities, their relative use can be influenced by many factors, including differences in signal active space, energetic costs, and predation risk. Characterizing differences in total signal investment across time can shed light on these factors, but requires long focal recordings of signal production. Neotropical pseudophylline katydids produce mate advertisement signals as airborne sound and substrate-borne vibration. Airborne calls, produced via stridulation, are extremely short, high-frequency, and longer-range signals. Conversely, substrate-borne calls produced via abdominal tremulation are longer, low-frequency, relatively more energetically costly, and shorter-range signals. To examine patterns of stridulation and tremulation across species and test hypotheses about the drivers of signal use in each modality, we recorded multimodal signaling activity over 24 hours for males from 10 pseudophylline species from a single Panamanian community. We also collected data on demographic and morphological species characteristics, and acoustic features of airborne calls, such as bandwidth, peak frequency, and duration. Finally, we generated a molecular phylogeny for these species and used phylogenetic generalized least squares models to test for relationships between variables while controlling for evolutionary relationships. We found a negative relationship between sound and vibration calling, indicating that substrate-borne vibrational signaling may compensate for reduced airborne signaling in these species. Sound call bandwidth and the proportion of males collected at lights, a proxy for the amount of male movement, also explained a significant amount of variation in sound calling across species, indicating that the overall relationship between the two types of calling signals may be mediated by the specific characteristics of the signals as well as other species traits.

Insects are an integral part of terrestrial ecosystems, but while they are ubiquitous, they can be difficult to census. Passive acoustic recording can provide detailed information on the spatial and temporal distribution of sound-producing insects. We placed recording devices in the forest canopy on Barro Colorado Island in Panamá and identified katydid calls in recordings to assess what species were present, in which seasons they were signaling, and how often they called. Soundscape recordings were collected at a height of 24 m in two replicate sites, sampled at three time-windows per night across five months, spanning both wet and dry seasons. Katydid calls were commonly detected in recordings, but the call repetition rates of many species were quite low, consistent with data from focal recordings of individual insects where calls were also repeated rarely. The soundscape recordings contained 6,789 calls with visible pulse structure. Of these calls, we identified 4,371 to species with the remainder representing calls that could not be identified to species. The identified calls corresponded to 24 species, with 15 of these species detected at both replicate sites. Katydid calls were detected throughout the night. Most species were detected at all three time points in the night, although some species called more just after dusk and just before dawn. The annotated dataset provided here serves as an archival sample of the species diversity and number of calls present in the forest canopy of Barro Colorado Island, Panama. These hand-annotated data will also be key for evaluating automated approaches to detecting and classifying insect calls. In changing forests and with declining insect populations, consistent approaches to insect sampling will be key for generating interpretable and actionable data.

The interface between field biology and technology is energizing the collection of vast quantities of environmental data. Passive acoustic monitoring, the use of unattended recording devices to capture environmental sound, is an example where technological advances have facilitated an influx of data that routinely exceeds the capacity for analysis. Computational advances, particularly the integration of machine learning approaches, will support data extraction efforts. However, the analysis and interpretation of these data will require parallel growth in conceptual and technical approaches for data analysis. Here, we use a large hand‐annotated dataset to showcase analysis approaches that will become increasingly useful as datasets grow and data extraction can be partially automated. We propose and demonstrate seven technical approaches for analyzing bioacoustic data. These include the following: (1) generating species lists and descriptions of vocal variation, (2) assessing how abiotic factors (e.g., rain and wind) impact vocalization rates, (3) testing for differences in community vocalization activity across sites and habitat types, (4) quantifying the phenology of vocal activity, (5) testing for spatiotemporal correlations in vocalizations within species, (6) among species, and (7) using rarefaction analysis to quantify diversity and optimize bioacoustic sampling. To demonstrate these approaches, we sampled in 2016 and 2018 and used hand annotations of 129,866 bird vocalizations from two forests in New Hampshire, USA, including sites in the Hubbard Brook Experiment Forest where bioacoustic data could be integrated with more than 50 years of observer‐based avian studies. Acoustic monitoring revealed differences in community patterns in vocalization activity between forests of different ages, as well as between nearby similar watersheds. Of numerous environmental variables that were evaluated, background noise was most clearly related to vocalization rates. The songbird community included one cluster of species where vocalization rates declined as ambient noise increased and another cluster where vocalization rates declined over the nesting season. In some common species, the number of vocalizations produced per day was correlated at scales of up to 15 km. Rarefaction analyses showed that adding sampling sites increased species detections more than adding sampling days. Although our analyses used hand‐annotated data, the methods will extend readily to large‐scale automated detection of vocalization events. Such data are likely to become increasingly available as autonomous recording units become more advanced, affordable, and power efficient. Passive acoustic monitoring with human or automated identification at the species level offers growing potential to complement observer‐based studies of avian ecology.