Parameter estimation of the hyperbolic frequency-modulated bat calls using hyperbolic scale transform.

Echolocating bats are known to vary their waveforms at the phases of searching, approaching, and capturing the prey. It is meaningful to estimate the parameters of the calls for bat species identification and the technological improvements of the synthetic systems, such as radar and sonar. The type of bat calls is species-related, and many calls can be modeled as hyperbolic frequency- modulated (HFM) signals. To obtain the parameters of the HFM-modeled bat calls, a reversible integral transform, i.e., hyperbolic scale transform (HST), is proposed to transform a call into two-dimensional peaks in the "delay-scale" domain, based on which harmonic separation and parameter estimation are realized. Compared with the methods based on time-frequency analysis, the HST-based method does not need to extract the instantaneous frequency of the bat calls, only searching for peaks. The verification results show that the HST is suitable for analyzing the HFM-modeled bat calls containing multiple harmonics with a large energy difference, and the estimated parameters imply that the use of the waveforms from the searching phase to the capturing phase is beneficial to reduce the ranging bias, and the trends in parameters may be useful for bat species identification.

Feeding efficiency of two coexisting nectarivorous bat species (Phyllostomidae: Glossophaginae) at flowers of two key-resource plants.

Animals should maximize their energy uptake while reducing the costs for foraging. For flower-visitors these costs and benefits are rather straight forward as the energy uptake equals the caloric content of the consumed nectar while the costs equal the handling time at the flower. Due to their energetically demanding lifestyle, flower-visiting bats face particularly harsh energetic conditions and thus need to optimize their foraging behavior at the flowers of the different plant species they encounter within their habitat. In flight cage experiments we examined the nectar-drinking behavior (i.e. hovering duration, nectar uptake, and the resulting feeding efficiency) of the specialized nectar-feeding bat Hylonycteris underwoodi and the more generalistic Glossophaga commissarisi at flowers of two plant species that constitute important nectar resources in the Caribbean lowland rainforests of Costa Rica and compared nectar-drinking behavior between both bat species and at both plant species. We hypothesized that the 1) specialized bat should outperform the more generalistic species and that 2) bats should generally perform better at flowers of the nectar-rich flowers of the bromeliad Werauhia gladioliflora than at the relatively nectar-poor flowers of the Solanaceae Merinthopodium neuranthum that has an extremely long flowering phase and therefore is an extremely reliable nectar resource, particularly for the specialized Hylonycteris. While we did not find substantial differences in the feeding efficiency of the generalist G. commissarisi, we observed an increased feeding efficiency of the specialized H. underwoodi at flowers of the nectar-poor M. neuranthum. This suggests that familiarity and ecological importance are more important determinants of the interaction than just morphological traits. Our results demonstrate that in addition to morphology, behavioral adaptations are also important drivers that determine the fitness of nectar-feeding bats. Both familiarity with and the ecological importance of a resource seem to contribute to shaping the interactions between pollinating bats and their plants.

Detection and validation of common noctule bats (Nyctalus noctula) with a pulse radar and acoustic monitoring in the proximity of an onshore wind turbine.

This paper presents the results of bats detected with marine radar and their validation with acoustic detectors in the vicinity of a wind turbine with a hub height of 120 m. Bat detectors are widely used by researchers, even though the common acoustic detectors can cover only a relatively small volume. In contrast, radar technology can overcome this shortcoming by offering a large detection volume, fully covering the rotor-swept areas of modern wind turbines. Our study focused on the common noctule bats (Nyctalus noctula). The measurement setup consisted of a portable X-band pulse radar with a modified radar antenna, a clutter shielding fence, and an acoustic bat detector installed in the wind turbine's nacelle. The radar's detection range was evaluated using an analytical simulation model. We developed a methodology based on a strict set of criteria for selecting suitable radar data, acoustic data and identified bat tracks. By applying this methodology, the study data was limited to time intervals with an average duration of 48 s, which is equal to approximately 20 radar images. For these time intervals, 323 bat tracks were identified. The most common bat speed was extracted to be between 9 and 10 m/s, matching the values found in the literature. Of the 323 identified bat tracks passed within 80 m of the acoustic detector, 32% had the potential to be associated with bat calls due to their timing, directionality, and distance to the acoustic bat detector. The remaining 68% passed within the studied radar detection volume but out of the detection volume of the acoustic bat detector. A comparison of recorded radar echoes with the expected simulated values indicated that the in-flight radar cross-section of recorded common noctule bats was mostly between 1.0 and 5.0 cm2, which is consistent with the values found in the literature for similar sized wildlife.

The effects of jaw clenching and mouthpiece use on bat swing velocity in Division II athletes.

Research assessing the effects of mouthpieces on an individual's aerobic, anaerobic, or muscular performance have attributed cited improvements to the participant's ability to jaw clench. Jaw clenching research finds positive outcomes with the task of jaw clenching with targeted muscle groups in a controlled laboratory setting. Thus, the study's goal was to determine if the addition of a mouthpiece would positively affect performance outcomes in a field-based whole-body muscle movement. Fourteen participants (8=F and 6=M) NCAA softball and baseball athletes completed 5 maximal bat swings with and without a mouthpiece in 4 conditions: no jaw clenching (NC), mouthpiece and jaw clenching (MP+C), mouthpiece only (MP), and jaw clenching only (C). Significant differences occurred in conditions, with the highest velocity noted in the combined condition of MP+C (71.9 mph) as compared to NC (67.9 mph), MP (68.6 mph), and C (70.9 mph). A repeated measures ANOVA demonstrated significant differences with bat swing velocity (F = 13.19, df 3, p < 0.0001). Pairwise comparisons revealed significant differences in MP+C with MP (p = 0.007); MP+C with NC (p = 0.001), and C with NC (p = 0.009). The results of this study provide evidence of jaw clenching's positive effects on the dynamic, whole-body explosive activity of a bat swing.

Winter diet of bats in working forests of the southeastern U.S. Coastal Plain.

Working forests comprise a large proportion of forested landscapes in the southeastern United States and are important to the conservation of bats, which rely on forests for roosting and foraging. While relationships between bat ecology and forest management are well studied during summer, winter bat ecology remains understudied. Hence, we aimed to identify the diet composition of overwintering bats, compare the composition of prey consumed by bat species, and determine the potential role of forest bats as pest controllers in working forest landscapes of the southeastern U.S. Coastal Plain. During January to March 2021-2022, we captured 264 bats of eight species. We used DNA metabarcoding to obtain diet composition from 126 individuals of seven bat species identifying 22 orders and 174 families of arthropod prey. Although Coleoptera, Diptera, and Lepidoptera were the most consumed orders, we found that bats had a generalist diet but with significant differences among some species. We also documented the consumption of multiple insect pests (e.g., Rhyacionia frustrana) and disease vectors (e.g., Culex spp). Our results provide important information regarding the winter diet of bats in the southeastern U.S. Coastal Plain and their potential role in controlling economically relevant pest species and disease vectors.

Disturbance of hibernating bats due to researchers entering caves to conduct hibernacula surveys.

Estimating population changes of bats is important for their conservation. Population estimates of hibernating bats are often calculated by researchers entering hibernacula to count bats; however, the disturbance caused by these surveys can cause bats to arouse unnaturally, fly, and lose body mass. We conducted 17 hibernacula surveys in 9 caves from 2013 to 2018 and used acoustic detectors to document cave-exiting bats the night following our surveys. We predicted that cave-exiting flights (i.e., bats flying out and then back into caves) of Townsend's big-eared bats (Corynorhinus townsendii) and western small-footed myotis (Myotis ciliolabrum) would be higher the night following hibernacula surveys than on nights following no surveys. Those two species, however, did not fly out of caves more than predicted the night following 82% of surveys. Nonetheless, the activity of bats flying out of caves following surveys was related to a disturbance factor (i.e., number of researchers × total time in a cave). We produced a parsimonious model for predicting the probability of Townsend's big-eared bats flying out of caves as a function of disturbance factor and ambient temperature. That model can be used to help biologists plan for the number of researchers, and the length of time those individuals are in a cave to minimize disturbing bats.

Gypsum Cave Biofilm Communities are Strongly Influenced by Bat- And Arthropod-Related Fungi.

The Gypsum Karst of Sorbas, Almeria, southeast Spain, includes a few caves whose entrances are open and allow the entry and roosting of numerous bats. Caves are characterized by their diversity of gypsum speleothems, such as stalactites, coralloids, gypsum crusts, etc. Colored biofilms can be observed on the walls of most caves, among which the Covadura and C3 caves were studied. The objective was to determine the influence that bat mycobiomes may have on the fungal communities of biofilms. The results indicate that the fungi retrieved from white and yellow biofilms in Covadura Cave (Ascomycota, Mortierellomycota, Basidiomycota) showed a wide diversity, depending on their location, and were highly influenced by the bat population, the guano and the arthropods that thrive in the guano, while C3 Cave was more strongly influenced by soil- and arthropod-related fungi (Ascomycota, Mortierellomycota), due to the absence of roosting bats.

Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species.

Acoustic surveys of bat echolocation calls are an important management tool for determining presence and probable absence of threatened and endangered bat species. In the northeastern United States, software programs such as Bat Call Identification (BCID), Kaleidoscope Pro (KPro), and Sonobat can automatically classify ultrasonic detector sound files, yet the programs' accuracy in correctly classifying calls to species has not been independently assessed. We used 1,500 full-spectrum reference calls with known identities for nine northeastern United States bat species to test the accuracy of these programs using calculations of Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity (SN), Specificity (SP), Overall Accuracy, and No Information Rate. We found that BCID performed less accurately than other programs, likely because it only operates on zero-crossing data and may be less accurate for recordings converted from full-spectrum to zero-crossing. NPV and SP values were high across all species categories for SonoBat and KPro, indicating these programs' success at avoiding false positives. However, PPV and SN values were relatively low, particularly for individual Myotis species, indicating these programs are prone to false negatives. SonoBat and KPro performed better when distinguishing Myotis species from non-Myotis species. We expect less accuracy from these programs for acoustic recordings collected under normal working conditions, and caution that a bat acoustic expert should verify automatically classified files when making species-specific regulatory or conservation decisions.

Artificial light at night drives diel activity patterns of synanthropic pipistrelle bats and their prey.

The use of artificial light at night (ALAN) has increased drastically worldwide over the last decades. ALAN can have major effects on nocturnal communities, including insects and bats. Insects are attracted to street lights and few bat species take advantage of this by foraging on the attracted insects. ALAN potentially affects the temporal patterns of insect abundance and thereby bat foraging behaviour. In a natural dark environment, these patterns are usually bimodal, with an activity peak in the early evening and the morning. Little is known about how ALAN affects insect presence throughout the night, and whether the light spectrum plays a role. This is important, as these temporal changes may be a key driver of disturbances in bat-insect interactions. Here, we studied how white and red light affect insects' and bats' nightly activity patterns. The activity of insects and bats (Pipistrellus spp.) was recorded throughout the night at seven experimentally illuminated sites in a forest-edge ecosystem. ALAN disrupted activity patterns, with both insects and bats being more active throughout the night. ALAN facilitated all-night foraging in bats especially near white light, but these effects were attenuated near red light. The ability to forage throughout the night may be a key advantage causing synanthropic bats to dominate in illuminated environments, but this could also prove detrimental in the long term. As red light reduced disturbing effects of ALAN on insects and bats diel activity pattern, it opens the possibility of using spectral composition as a mitigation measure.

Universal wing- and fin-beat frequency scaling.

We derive an equation that applies for the wing-beat frequency of flying animals and to the fin-stroke frequency of diving animals like penguins and whales. The equation states that the wing/fin-beat frequency is proportional to the square root of the animal's mass divided by the wing area. Data for birds, insects, bats, and even a robotic bird-supplemented by data for whales and penguins that must swim to stay submerged-show that the constant of proportionality is to a good approximation the same across all species; thus the equation is universal. The wing/fin-beat frequency equation is derived by dimensional analysis, which is a standard method of reasoning in physics. We finally demonstrate that a mathematically even simpler expression without the animal mass does not apply.

Clutter resilience via auditory stream segregation in echolocating greater mouse-eared bats.

Bats use echolocation to navigate and hunt in darkness, and must in that process segregate target echoes from unwanted clutter echoes. Bats may do this by approaching a target at steep angles relative to the plane of the background, utilizing their directional transmission and receiving systems to minimize clutter from background objects, but it remains unknown how bats negotiate clutter that cannot be spatially avoided. Here, we tested the hypothesis that when movement no longer offers spatial release, echolocating bats mitigate clutter by calling at lower source levels and longer call intervals to ease auditory streaming. We trained five greater mouse-eared bats (Myotis myotis) to land on a spherical loudspeaker with two microphones attached. We used a phantom-echo setup, where the loudspeaker/target transmitted phantom clutter echoes by playing back the bats' own calls at time delays of 1, 3 and 5 ms with a virtual target strength 7 dB higher than the physical target. We show that the bats successfully landed on the target, irrespective of the clutter echo delays. Rather than decreasing their source levels, the bats used similar source level distributions in clutter and control trials. Similarly, the bats did not increase their call intervals, but instead used the same distribution of call intervals across control and clutter trials. These observations reject our hypothesis, leading us to conclude that bats display great resilience to clutter via short auditory integration times and acute auditory stream segregation rather than via biosonar adjustments.

Auditory cortical regions show resting-state functional connectivity with the default mode-like network in echolocating bats.

Echolocating bats are among the most social and vocal of all mammals. These animals are ideal subjects for functional MRI (fMRI) studies of auditory social communication given their relatively hypertrophic limbic and auditory neural structures and their reduced ability to hear MRI gradient noise. Yet, no resting-state networks relevant to social cognition (e.g., default mode-like networks or DMLNs) have been identified in bats since there are few, if any, fMRI studies in the chiropteran order. Here, we acquired fMRI data at 7 Tesla from nine lightly anesthetized pale spear-nosed bats (Phyllostomus discolor). We applied independent components analysis (ICA) to reveal resting-state networks and measured neural activity elicited by noise ripples (on: 10 ms; off: 10 ms) that span this species' ultrasonic hearing range (20 to 130 kHz). Resting-state networks pervaded auditory, parietal, and occipital cortices, along with the hippocampus, cerebellum, basal ganglia, and auditory brainstem. Two midline networks formed an apparent DMLN. Additionally, we found four predominantly auditory/parietal cortical networks, of which two were left-lateralized and two right-lateralized. Regions within four auditory/parietal cortical networks are known to respond to social calls. Along with the auditory brainstem, regions within these four cortical networks responded to ultrasonic noise ripples. Iterative analyses revealed consistent, significant functional connectivity between the left, but not right, auditory/parietal cortical networks and DMLN nodes, especially the anterior-most cingulate cortex. Thus, a resting-state network implicated in social cognition displays more distributed functional connectivity across left, relative to right, hemispheric cortical substrates of audition and communication in this highly social and vocal species.

Southern Africa's Great Escarpment as an amphitheater of climate-driven diversification and a buffer against future climate change in bats.

Hosting 1460 plant and 126 vertebrate endemic species, the Great Escarpment (hereafter, Escarpment) forms a semi-circular "amphitheater" of mountains girdling southern Africa from arid west to temperate east. Since arid and temperate biota are usually studied separately, earlier studies overlooked the biogeographical importance of the Escarpment as a whole. Bats disperse more widely than other mammalian taxa, with related species and intraspecific lineages occupying both arid and temperate highlands of the Escarpment, providing an excellent model to address this knowledge gap. We investigated patterns of speciation and micro-endemism from modeled past, present, and future distributions in six clades of southern African bats from three families (Rhinolophidae, Cistugidae, and Vespertilionidae) having different crown ages (Pleistocene to Miocene) and biome affiliations (temperate to arid). We estimated mtDNA relaxed clock dates of key divergence events across the six clades in relation both to biogeographical features and patterns of phenotypic variation in crania, bacula and echolocation calls. In horseshoe bats (Rhinolophidae), both the western and eastern "arms" of the Escarpment have facilitated dispersals from the Afrotropics into southern Africa. Pleistocene and pre-Pleistocene "species pumps" and temperate refugia explained observed patterns of speciation, intraspecific divergence and, in two cases, mtDNA introgression. The Maloti-Drakensberg is a center of micro-endemism for bats, housing three newly described or undescribed species. Vicariance across biogeographic barriers gave rise to 29 micro-endemic species and intraspecific lineages whose distributions were congruent with those identified in other phytogeographic and zoogeographic studies. Although Köppen-Geiger climate models predict a widespread replacement of current temperate ecosystems in southern Africa by tropical or arid ecosystems by 2070-2100, future climate Maxent models for 13 bat species (all but one of those analyzed above) showed minimal range changes in temperate species from the eastern Escarpment by 2070, possibly due to the buffering effect of mountains to climate change.

All-you-can-eat buffet: A spider-specialized bat species (Myotis emarginatus) turns into a pest fly eater around cattle.

Determining the dietary spectrum of European insectivorous bats over time is the cornerstone of their conservation, as it will aid our understanding of foraging behavior plasticity in response to plummeting insect populations. Despite the global decline in insects, a restricted number of arthropod pest species thrive. Yet past research has overlooked the potential of European bats to suppress pests harmful to woodlands or livestock, in spite of their economic relevance. Here we investigated the diet composition, its breeding season variations and pest consumption of an insectivorous bat species (Myotis emarginatus), at the northern edge of its range (Wallonia, Belgium). We also explored the prey ecology to gain insight into the hunting strategies and foraging habitats of this bat species. We used DNA metabarcoding to amplify two COI markers within 195 bat droppings collected in June, July and August, thereby identifying 512 prey taxa predominated by Diptera, Araneae and Lepidoptera. Overall, in 97% of the samples we detected at least one of the 58 potential pest taxa, 41 of which targeting trees. The June samples were marked by a diet rich in orb-weaver spiders, in accordance with the archetypal diet of M. emarginatus bats. However, during the highly energy demanding July-August parturition and lactation period, roughly 55% of the dropping samples contained two cattle fly pests (Stomoxys calcitrans and Musca domestica). Moreover, among the 88 Diptera species preyed upon by M. emarginatus in July and August, these flies accounted for around 50% of the taxa occurrences. This plasticity-the switch from a spider-rich to a fly-rich diet-seems providential considering the dramatic ongoing drop in insect populations but this involves ensuring bat-friendly cattle farming. Our results revealed that bats widely consume pest entomofauna, thereby highlighting their potential role as allies of forest managers and farmers.

Tiger beetles produce anti-bat ultrasound and are probable Batesian moth mimics.

Echolocating bats and their eared insect prey are in an acoustic evolutionary war. Moths produce anti-bat sounds that startle bat predators, signal noxiousness, mimic unpalatable models and jam bat sonar. Tiger beetles (Cicindelidae) also purportedly produce ultrasound in response to bat attacks. Here we tested 19 tiger beetle species from seven genera and showed that they produce anti-bat signals to playback of authentic bat echolocation. The dominant frequency of beetle sounds substantially overlaps the sonar calls of sympatric bats. As tiger beetles are known to produce defensive chemicals such as benzaldehyde and hydrogen cyanide, we hypothesized that tiger beetle sounds are acoustically advertising their unpalatability. We presented captive big brown bats (Eptesicus fuscus) with seven different tiger beetle species and found that 90 out of 94 beetles were completely consumed, indicating that these tiger beetle species are not aposematically signalling. Instead, we show that the primary temporal and spectral characteristics of beetle warning sounds overlap with sympatric unpalatable tiger moth (Arctinae) sounds and that tiger beetles are probably Batesian mimics of noxious moth models. We predict that many insect taxa produce anti-bat sounds and that the acoustic mimicry rings of the night sky are hyperdiverse.

Calling to the collective: contact calling rates within groups of disc-winged bats do not vary by kinship or association.

Many group-living animals coordinate social behaviours using contact calls, which can be produced for all group members or targeted at specific individuals. In the disc-winged bat, Thyroptera tricolor, group members use 'inquiry' and 'response' calls to coordinate daily movements into new roosts (furled leaves). Rates of both calls show consistent among-individual variation, but causes of within-individual variation remain unknown. Here, we tested whether disc-winged bats produce more contact calls towards group members with higher kinship or association. In 446 experimental trials, we recorded 139 random within-group pairs of one flying bat (producing inquiry calls for roost searching) and one roosting bat (producing response calls for roost advertising). Using generalized linear mixed-effect models (GLMM), we assessed how response and inquiry calling rates varied by sender, receiver, genetic kinship and co-roosting association rate. Calling rates varied consistently across senders but not by receiver. Response calling was influenced by inquiry calling rates, but neither calling rate was higher when the interacting pair had higher kinship or association. Rather than dyadic calling rates indicating within-group relationships, our findings are consistent with the hypothesis that bats produce contact calls to maintain contact with any or all individuals within a group while collectively searching for a new roost site. This article is part of the theme issue 'The power of sound: unravelling how acoustic communication shapes group dynamics'.

Group vocal composition and decision-making during roost finding in Spix's disk-winged bats.

Theoretical work suggests that having many informed individuals within social groups can promote efficient resource location. However, it may also give rise to group fragmentation if members fail to reach consensus on their direction of movement. In this study, we investigate whether the number of informed individuals, exemplified by bats emitting calls from different roosts, influences group cohesion in Spix's disk-winged bats (Thyroptera tricolor). Additionally, we explore the role of signal reliability, quantified through signalling rates, in group consensus on where to roost. These bats use contact calls to announce the location of a roost site and recruit conspecifics. The groups they form exhibit high levels of cohesion and consist of both vocal and non-vocal bats, with vocal behaviour being consistent over time. Our findings revealed that an increase in the number of roosts broadcasting calls is strongly associated with the likelihood of groups fragmenting among multiple roosts. Additionally, we found that a majority of group members enter the roost with higher calling rates. This phenomenon can mitigate the risk of group fragmentation, as bats emitting more calls may contribute to greater group consensus on roosting locations, thereby reducing the likelihood of individuals separating and enhancing overall group cohesion. Our results highlight the potential costs of having too many information producers for group coordination, despite their established role in finding critical resources. This article is part of the theme issue 'The power of sound: unravelling how acoustic communication shapes group dynamics'.

Combined effects of ambient temperature and food availability on induced innate immune response of a fruit-eating bat (Carollia perspicillata).

Resilience of mammals to anthropogenic climate and land-use changes is associated with the maintenance of adequate responses of several fitness-related traits such as those related to immune functions. Isolated and combined effects of decreased food availability and increased ambient temperature can lead to immunosuppression and greater susceptibility to disease. Our study tested the general hypothesis that decreased food availability, increased ambient temperature and the combined effect of both factors would affect selected physiological and behavioral components associated with the innate immune system of fruit-eating bats (Carollia perspicillata). Physiological (fever, leukocytosis and neutrophil/lymphocyte ratio) and behavioral (food intake) components of the acute phase response, as well as bacterial killing ability of the plasma were assessed after immune challenge with lipopolysaccharide (LPS: 10 mg/kg) in experimental groups kept at different short-term conditions of food availability (ad libitum diet or 50% food-deprived) and ambient temperature (27 and 33°C). Our results indicate that magnitude of increase in body temperature was not affected by food availability, ambient temperature or the interaction of both factors, but the time to reach the highest increase took longer in LPS-injected bats that were kept under food restriction. The magnitude of increased neutrophil/lymphocyte ratio was affected by the interaction between food availability and ambient temperature, but food intake, total white blood cell count and bacterial killing ability were not affected by any factor or interaction. Overall, our results suggest that bacterial killing ability and most components of acute phase response examined are not affected by short-term changes in food availability and ambient temperature within the range evaluated in this study, and that the increase of the neutrophil/lymphocyte ratio when bats are exposed to low food availability and high ambient temperature might represent an enhancement of cellular response to deal with infection.

Unexpected bat community changes along an urban-rural gradient in the Berlin-Brandenburg metropolitan area.

Urbanization gradients are increasingly used in ecological studies to discover responses of species communities to different intensities of human-induced habitat transformation. Here, we investigated patterns of bat communities against the background of different urbanization levels using a priori defined urbanization categories based on distance classes (5 km intervals) along a linear transect from the urban core of the city of Berlin westwards into the rural outskirts of the state of Brandenburg. Using linear-mixed effects models, we found that "distance class", as a proxy for urbanization level, is a meaningful and suitable predictor of bat species richness and diversity. We observed an unexpectedly sudden increase in bat species richness and diversity and changes in species-specific activity levels relatively close to the urban center at the transition between urban and peri-urban areas. This change suggests a relevant influence of the peri-urban areas as a "buffer zone" for specific bat species not able to adapt to the heavily modified inner core of the metropolitan area. Although we could demonstrate that anthropogenic noise and artificial light have the potential to predict the variability of bat species activity along the urban-rural gradient, the actual influence on observed shifts in the bat community needs further research.

Bat2Web: A Framework for Real-Time Classification of Bat Species Echolocation Signals Using Audio Sensor Data.

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral.