The use of automated identification of bat echolocation calls in acoustic monitoring: A cautionary note for a sound analysis

Bats are a species-rich order of mammals providing key ecosystem services. Because bats are threatened by human action and also serve as important bioindicators, monitoring their populations is of utmost importance. However, surveying bats is difficult because of their nocturnal habits, elusiveness and sensitivity to disturbance. Bat detectors allow echolocating bats to be surveyed non-invasively and record species that would otherwise be difficult to observe by capture or roost inspection. Unfortunately, several bat species cannot be identified confidently from their calls so acoustic classification remains ambiguous or impossible in some cases.The popularity of automated classifiers of bat echolocation calls has escalated rapidly, including that of several packages available on purchase. Such products have filled a vacant niche on the market mostly in relation to the expanding monitoring efforts related to the development of wind energy production worldwide.We highlight that no classifier has yet proven capable of providing correct classifications in 100% of cases or getting close enough to this ideal performance. Besides, from the literature available and our own experience we argue that such tools have not yet been tested sufficiently in the field. Visual inspection of calls whose automated classification is judged suspicious is often recommended, but human intervention a posteriori represents a circular argument and requires noticeable experience.We are concerned that neophytes – including consultants with little experience with bats but specialized into other taxonomical groups – will accept passively automated responses of tools still awaiting sufficient validation. We remark that bat call identification is a serious practical issue because biases in the assessment of bat distribution or habitat preferences may lead to wrong management decisions with serious conservation consequences. Automated classifiers may crucially aid bat research and certainly merit further investigations but the boost in commercially available software may have come too early. Thorough field tests need to be carried out to assess limitations and strengths of these tools.     

Automated classification of bat echolocation call recordings with artificial intelligence

Acoustic recorders are commonly used to remotely monitor and collect data on bats (Order Chiroptera). These efforts result in many acoustic recordings that must be classified by a bat biologist with expertise in call classification in order to obtain useful information. The rarity of this expertise and time constraints have prompted efforts to automatically classify bat species in acoustic recordings using a variety of learning methods. There are several software programs available for this purpose, but they are imperfect and the United States Fish and Wildlife Service often recommends that a qualified acoustic analyst review bat call identifications even if using these software programs. We sought to build a model to classify bat species using modern computer vision techniques. We used images of bat echolocation calls (i.e., plots of the pulses) to train deep learning computer vision models that automatically classify bat calls to species. Our model classifies 10 species, five of which are protected under the Endangered Species Act. We evaluated our models using standard model validation procedures, and performed two external tests. For these tests, an entire dataset was withheld from the procedure before splitting the data into training and validation sets. We found that our validation accuracy (92%) and testing accuracy (90%) were higher than when we used Kaleidoscope Pro and BCID software (65% and 61% accuracy, respectively) to evaluate the same calls. Our results suggest that our approach is effective at classifying bat species from acoustic recordings, and our trained model will be incorporated into new bat call identification software: WEST-EchoVision.     

Testing the performances of automated identification of bat echolocation calls: A request for prudence

Echolocating bats are surveyed and studied acoustically with bat detectors routinely and worldwide, yet identification of species from calls often remains ambiguous or impossible due to intraspecific call variation and/or interspecific overlap in call design. To overcome such difficulties and to reduce workload, automated classifiers of echolocation calls have become popular, but their performance has not been tested sufficiently in the field. We examined the absolute performance of two commercially available programs (SonoChiro and Kaleidoscope) and one freeware package (BatClassify). We recorded noise from rain and calls of seven common bat species with Pettersson real-time full spectrum detectors in Sweden. The programs could always (100%) distinguish rain from bat calls, usually (68–100%) identify bats to group (Nyctalus/Vespertilio/Eptesicus, Pipistrellus, Myotis, Plecotus, Barbastella) and usually (83–99%) recognize typical calls of some species whose echolocation pulses are structurally distinct (Pipistrellus pygmaeus, Barbastella barbastellus). Species with less characteristic echolocation calls were not identified reliably, including Vespertilio murinus (16–26%), Myotis spp. (4–93%) and Plecotus auritus (0–89%). All programs showed major although different shortcomings and the often poor performance raising serious concerns about the use of automated classifiers for identification to species level in research and surveys. We highlight the importance of validating output from automated classifiers, and restricting their use to specific situations where identification can be made with high confidence. For comparison we also present the result of a manual identification test on a random subset of the files used to test the programs. It showed a higher classification success but performances were still low for more problematic taxa.     

Acoustic characterization of bats from Malta: setting a baseline for monitoring and conservation of bat populations

Bioacoustic research has made several advancements in developing systems to record extensive acoustic data and classify bat echolocation calls to species level using automated classifiers. These systems are useful as echolocation calls give valuable information on bat behaviour and ecology and hence are widely used for research and conservation of bat populations. Despite the challenges associated with automated classifiers, due to the interspecific differences in call characteristics of bat species found in the Maltese Islands, the use of a quantitative and automated approach is investigated. The sound analysis pipeline involved the use of an algorithm to clean sound files from background noise and measure temporal and spectral parameters of bat echolocation calls. These parameters were then fed to a trained and validated artificial neural network using a bat call library built from reference bat calls from Malta. The automatic classifier achieved an overall correct classification rate of 98%. This high correct classification rate for reliable species identification may have benefitted from the absence of typically problematic species, such as species in the genus Myotis, in the analyses. This study’s results pave the way for efficient and reliable bat acoustic surveys in Malta in aid of necessary monitoring and conservation by providing an updated bat species list and their echolocation characteristics.     

Effectiveness of an acoustic lure for surveying bats in British woodlands

1. A field experiment was used to test the effectiveness of a synthesized bat call as an acoustic lure to attract bats into mist nets in woodlands in southeast England. The stimulus was modelled on a social call of the rare Bechstein's bat Myotis bechsteinii. 2. In the Test condition, when the synthesized call was played, 23 bats of four species were captured, including six Bechstein's bats. In the Control condition, when no calls were played, only one bat was caught. 3. The bat call synthesizer is an effective tool for increasing capture rates for bats. Used as part of a systematic survey programme, it has the potential to provide the first baseline data on the distribution of bats in British woodlands.     

Little Brown Bats (Myotis lucifugus) Recognize Individual Identity of Conspecifics Using Sonar Calls

Bats use sonar calls to locate prey and orient in their environment but they may also be used by conspecifics to obtain information about a caller. Statistical analysis of sonar calls provides evidence that variation carries social information about a caller, including individual identity. We hypothesized that little brown bats (Myotis lucifugus) would be able to recognize individuals given the potential fitness benefits of doing so. We performed playback trials using a habituation‐discrimination design to determine whether little brown bats are able to recognize the individual identity of a caller based on variation in their sonar calls. Each subject bat was played the calls of bat A until they habituated (defined as a 50% decrease from the beginning call rate), then the calls of bat B or a new call sequence of bat A (a control, referred to as bat A’) were played. Each subject received a unique pair of playback recordings (bat A and B) from adult female bats from the same colony (but a different colony from the subject) and the order of trials was randomized. The response measures were habituation time (s) and call rate (calls/s). Within a trial, subjects habituated to calls of bat A and transferred this habituation to the bat A’ sequence. In addition, they increased their call rates when played calls of bat B. Comparing between trials, subjects increased their call rate to the calls of bat B to a greater relative extent than to the calls of bat A’. These results provide the first evidence that bats recognize individual identity of conspecifics (as opposed to discrimination of groups), which has implications for the social interactions of bats.     

Different Auditory Feedback Control for Echolocation and Communication in Horseshoe Bats

Auditory feedback from the animal''s own voice is essential during bat echolocation: to optimize signal detection, bats continuously adjust various call parameters in response to changing echo signals. Auditory feedback seems also necessary for controlling many bat communication calls, although it remains unclear how auditory feedback control differs in echolocation and communication. We tackled this question by analyzing echolocation and communication in greater horseshoe bats, whose echolocation pulses are dominated by a constant frequency component that matches the frequency range they hear best. To maintain echoes within this “auditory fovea”, horseshoe bats constantly adjust their echolocation call frequency depending on the frequency of the returning echo signal. This Doppler-shift compensation (DSC) behavior represents one of the most precise forms of sensory-motor feedback known. We examined the variability of echolocation pulses emitted at rest (resting frequencies, RFs) and one type of communication signal which resembles an echolocation pulse but is much shorter (short constant frequency communication calls, SCFs) and produced only during social interactions. We found that while RFs varied from day to day, corroborating earlier studies in other constant frequency bats, SCF-frequencies remained unchanged. In addition, RFs overlapped for some bats whereas SCF-frequencies were always distinctly different. This indicates that auditory feedback during echolocation changed with varying RFs but remained constant or may have been absent during emission of SCF calls for communication. This fundamentally different feedback mechanism for echolocation and communication may have enabled these bats to use SCF calls for individual recognition whereas they adjusted RF calls to accommodate the daily shifts of their auditory fovea.     

Acoustic identification of bats in the eastern United States: A comparison of parametric and nonparametric methods

Ultrasonic detectors are widely used to survey bats in ecological studies. To evaluate efficacy of acoustic identification, we compiled a library of search phase calls from across the eastern United States using the Anabat system. The call library included 1,846 call sequences of 12 species recorded from 14 states. We determined accuracy rates using 3 parametric and 4 nonparametric classification functions for acoustic identification. The 2 most flexible classification functions also were the most accurate: neural networks (overall classification accuracy = 0.94) and mixture discriminant analysis incorporating an adaptive regression model (overall classification accuracy = 0.93). Flexible nonparametric methods offer substantial benefits when discriminating among closely related species and may preclude the need to group species with similar calls. We demonstrate that quantitative methods provide an effective technique to acoustically identify bats in the eastern United States with known accuracy rates. © 2011 The Wildlife Society.     

Animal Sound Identifier (ASI): software for automated identification of vocal animals

Automated audio recording offers a powerful tool for acoustic monitoring schemes of bird, bat, frog and other vocal organisms, but the lack of automated species identification methods has made it difficult to fully utilise such data. We developed Animal Sound Identifier (ASI), a MATLAB software that performs probabilistic classification of species occurrences from field recordings. Unlike most previous approaches, ASI locates training data directly from the field recordings and thus avoids the need of pre‐defined reference libraries. We apply ASI to a case study on Amazonian birds, in which we classify the vocalisations of 14 species in 194 504 one‐minute audio segments using in total two weeks of expert time to construct, parameterise, and validate the classification models. We compare the classification performance of ASI (with training templates extracted automatically from field data) to that of monitoR (with training templates extracted manually from the Xeno‐Canto database), the results showing ASI to have substantially higher recall and precision rates.     

‘Compromise’ in Echolocation Calls between Different Colonies of the Intermediate Leaf-Nosed Bat (Hipposideros larvatus)

Each animal population has its own acoustic signature which facilitates identification, communication and reproduction. The sonar signals of bats can convey social information, such as species identity and contextual information. The goal of this study was to determine whether bats adjust their echolocation call structures to mutually recognize and communicate when they encounter the bats from different colonies. We used the intermediate leaf-nosed bats (Hipposideros larvatus) as a case study to investigate the variations of echolocation calls when bats from one colony were introduced singly into the home cage of a new colony or two bats from different colonies were cohabitated together for one month. Our experiments showed that the single bat individual altered its peak frequency of echolocation calls to approach the call of new colony members and two bats from different colonies adjusted their call frequencies toward each other to a similar frequency after being chronically cohabitated. These results indicate that the ‘compromise’ in echolocation calls might be used to ensure effective mutual communication among bats.     

Weather conditions determine attenuation and speed of sound: Environmental limitations for monitoring and analyzing bat echolocation

Echolocating bats are regularly studied to investigate auditory‐guided behaviors and as important bioindicators. Bioacoustic monitoring methods based on echolocation calls are increasingly used for risk assessment and to ultimately inform conservation strategies for bats. As echolocation calls transmit through the air at the speed of sound, they undergo changes due to atmospheric and geometric attenuation. Both the speed of sound and atmospheric attenuation, however, are variable and determined by weather conditions, particularly temperature and relative humidity. Changing weather conditions thus cause variation in analyzed call parameters, limiting our ability to detect, and correctly analyze bat calls. Here, I use real‐world weather data to exemplify the effect of varying weather conditions on the acoustic properties of air. I then present atmospheric attenuation and speed of sound for the global range of weather conditions and bat call frequencies to show their relative effects. Atmospheric attenuation is a nonlinear function of call frequency, temperature, relative humidity, and atmospheric pressure. While atmospheric attenuation is strongly positively correlated with call frequency, it is also significantly influenced by temperature and relative humidity in a complex nonlinear fashion. Variable weather conditions thus result in variable and unknown effects on the recorded call, affecting estimates of call frequency and intensity, particularly for high frequencies. Weather‐induced variation in speed of sound reaches up to about ±3%, but is generally much smaller and only relevant for acoustic localization methods of bats. The frequency‐ and weather‐dependent variation in atmospheric attenuation has a threefold effect on bioacoustic monitoring of bats: It limits our capability (1) to monitor bats equally across time, space, and species, (2) to correctly measure frequency parameters of bat echolocation calls, particularly for high frequencies, and (3) to correctly identify bat species in species‐rich assemblies or for sympatric species with similar call designs.     

Diseases and causes of death in European bats: dynamics in disease susceptibility and infection rates

Background

Bats receive increasing attention in infectious disease studies, because of their well recognized status as reservoir species for various infectious agents. This is even more important, as bats with their capability of long distance dispersal and complex social structures are unique in the way microbes could be spread by these mammalian species. Nevertheless, infection studies in bats are predominantly limited to the identification of specific pathogens presenting a potential health threat to humans. But the impact of infectious agents on the individual host and their importance on bat mortality is largely unknown and has been neglected in most studies published to date.

Methodology/Principal Findings

Between 2002 and 2009, 486 deceased bats of 19 European species (family Vespertilionidae) were collected in different geographic regions in Germany. Most animals represented individual cases that have been incidentally found close to roosting sites or near human habitation in urban and urban-like environments. The bat carcasses were subjected to a post-mortem examination and investigated histo-pathologically, bacteriologically and virologically. Trauma and disease represented the most important causes of death in these bats. Comparative analysis of pathological findings and microbiological results show that microbial agents indeed have an impact on bats succumbing to infectious diseases, with fatal bacterial, viral and parasitic infections found in at least 12% of the bats investigated.

Conclusions/Significance

Our data demonstrate the importance of diseases and infectious agents as cause of death in European bat species. The clear seasonal and individual variations in disease prevalence and infection rates indicate that maternity colonies are more susceptible to infectious agents, underlining the possible important role of host physiology, immunity and roosting behavior as risk factors for infection of bats.     

Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys

Owing to major technological advances, bioacoustics has become a burgeoning field in ecological research worldwide. Autonomous passive acoustic recorders are becoming widely used to monitor aerial insectivorous bats, and automatic classifiers have emerged to aid researchers in the daunting task of analysing the resulting massive acoustic datasets. However, the scarcity of comprehensive reference call libraries still hampers their wider application in highly diverse tropical assemblages. Capitalizing on a unique acoustic dataset of >650,000 bat call sequences collected over a 3-year period in the Brazilian Amazon, the aims of this study were (a) to assess how pre-identified recordings of free-flying and hand-released bats could be used to train an automatic classification algorithm (random forest), and (b) to optimize acoustic analysis protocols by combining automatic classification with visual post-validation, whereby we evaluated the proportion of sound files to be post-validated for different thresholds of classification accuracy. Classifiers were trained at species or sonotype (group of species with similar calls) level. Random forest models confirmed the reliability of using calls of both free-flying and hand-released bats to train custom-built automatic classifiers. To achieve a general classification accuracy of ~85%, random forest had to be trained with at least 500 pulses per species/sonotype. For seven out of 20 sonotypes, the most abundant in our dataset, we obtained high classification accuracy (>90%). Adopting a desired accuracy probability threshold of 95% for the random forest classifier, we found that the percentage of sound files required for manual post-validation could be reduced by up to 75%, a significant saving in terms of workload. Combining automatic classification with manual ID through fully customizable classifiers implemented in open-source software as demonstrated here shows great potential to help overcome the acknowledged risks and biases associated with the sole reliance on automatic classification.     

A comparison of supervised learning techniques in the classification of bat echolocation calls

Today's acoustic monitoring devices are capable of recording and storing tremendous amounts of data. Until recently, the classification of animal vocalizations from field recordings has been relegated to qualitative approaches. For large-scale acoustic monitoring studies, qualitative approaches are very time-consuming and suffer from the bias of subjectivity. Recent developments in supervised learning techniques can provide rapid, accurate, species-level classification of bioacoustics data. We compared the classification performances of four supervised learning techniques (random forests, support vector machines, artificial neural networks, and discriminant function analysis) for five different classification tasks using bat echolocation calls recorded by a popular frequency-division bat detector. We found that all classifiers performed similarly in terms of overall accuracy with the exception of discriminant function analysis, which had the lowest average performance metrics. Random forests had the advantage of high sensitivities, specificities, and predictive powers across the majority of classification tasks, and also provided metrics for determining the relative importance of call features in distinguishing between groups. Overall classification accuracy for each task was slightly lower than reported accuracies using calls recorded by time-expansion detectors. Myotis spp. were particularly difficult to separate; classifiers performed best when members of this genus were combined in genus-level classification and analyzed separately at the level of species. Additionally, we identified and ranked the relative contributions of all predictor features to classifier accuracy and found measurements of frequency, total call duration, and characteristic slope to be the most important contributors to classification success. We provide recommendations to maximize accuracy and efficiency when analyzing acoustic data, and suggest an application of automated bioacoustics monitoring to contribute to wildlife monitoring efforts.     

Bat point counts: A novel sampling method shines light on flying bat communities

Emerging technologies based on the detection of electro‐magnetic energy offer promising opportunities for sampling biodiversity. We exploit their potential by showing here how they can be used in bat point counts—a novel method to sample flying bats—to overcome shortcomings of traditional sampling methods, and to maximize sampling coverage and taxonomic resolution of this elusive taxon with minimal sampling bias. We conducted bat point counts with a sampling rig combining a thermal scope to detect bats, an ultrasound recorder to obtain echolocation calls, and a near‐infrared camera to capture bat morphology. We identified bats with a dedicated identification key combining acoustic and morphological features, and compared bat point counts with the standard bat sampling methods of mist‐netting and automated ultrasound recording in three oil palm plantation sites in Indonesia, over nine survey nights. Based on rarefaction and extrapolation sampling curves, bat point counts were similarly effective but more time‐efficient than the established methods for sampling the oil palm species pool in our study. Point counts sampled species that tend to avoid nets and those that are not echolocating, and thus cannot be detected acoustically. We identified some bat sonotypes with near‐infrared imagery, and bat point counts revealed strong sampling biases in previous studies using capture‐based methods, suggesting similar biases in other regions might exist. Our method should be tested in a wider range of habitats and regions to assess its performance. However, while capture‐based methods allow to identify bats with absolute and internal morphometry, and unattended ultrasound recorders can effectively sample echolocating bats, bat point counts are a promising, non‐invasive, and potentially competitive new tool for sampling all flying bats without bias and observing their behavior in the wild.     

Enhanced Passive Bat Rabies Surveillance in Indigenous Bat Species from Germany - A Retrospective Study

In Germany, rabies in bats is a notifiable zoonotic disease, which is caused by European bat lyssaviruses type 1 and 2 (EBLV-1 and 2), and the recently discovered new lyssavirus species Bokeloh bat lyssavirus (BBLV). As the understanding of bat rabies in insectivorous bat species is limited, in addition to routine bat rabies diagnosis, an enhanced passive surveillance study, i.e. the retrospective investigation of dead bats that had not been tested for rabies, was initiated in 1998 to study the distribution, abundance and epidemiology of lyssavirus infections in bats from Germany. A total number of 5478 individuals representing 21 bat species within two families were included in this study. The Noctule bat (Nyctalus noctula) and the Common pipistrelle (Pipistrellus pipistrellus) represented the most specimens submitted. Of all investigated bats, 1.17% tested positive for lyssaviruses using the fluorescent antibody test (FAT). The vast majority of positive cases was identified as EBLV-1, predominately associated with the Serotine bat (Eptesicus serotinus). However, rabies cases in other species, i.e. Nathusius'' pipistrelle bat (Pipistrellus nathusii), P. pipistrellus and Brown long-eared bat (Plecotus auritus) were also characterized as EBLV-1. In contrast, EBLV-2 was isolated from three Daubenton''s bats (Myotis daubentonii). These three cases contribute significantly to the understanding of EBLV-2 infections in Germany as only one case had been reported prior to this study. This enhanced passive surveillance indicated that besides known reservoir species, further bat species are affected by lyssavirus infections. Given the increasing diversity of lyssaviruses and bats as reservoir host species worldwide, lyssavirus positive specimens, i.e. both bat and virus need to be confirmed by molecular techniques.     

Identification of Behaviour in Freely Moving Dogs (Canis familiaris) Using Inertial Sensors

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.     

Calls in the Forest: A Comparative Approach to How Bats Find Tree Cavities

Although tree cavities are a particularly critical resource for forest bats, how bats search for and find new roosts is still poorly known. Building on a recent study on the sensory basis of roost finding in the noctule (Ruczynski et al. 2007), here we take a comparative approach to how bats find roosts. We tested the hypothesis that species' flight abilities and echolocation call characteristics play important roles in how well and by which cues bats find new tree roosts. We used the very manoeuvrable, faintly echolocating brown long-eared bat ( Plecotus auritus ) and the less manoeuvrable, louder Daubenton's bat ( Myotis daubentonii ) as study species. The species are sympatric in European temperate forests and both roost in tree cavities. We trained bats in short-term captivity to find entrances to tree cavities and experimentally manipulated the sensory cues available to them. In both species, cue type influenced the search time for successful cavity detection. Visual, olfactory and temperature cues did not improve the bats' performance over the performance by echolocation alone. Eavesdropping on conspecific echolocation calls played back from inside the cavity decreased search time in Daubenton's bat ( M. daubentonii ), underlining the double function of echolocation signals – orientation and communication. This was not so in the brown long-eared bat ( P. auritus ) that has low call amplitudes. The highly manoeuvrable P. auritus found cavities typically from flight and the less manoeuvrable M. daubentonii found more entrances during crawling. Comparison with the noctule data from Ruczyński et al. (2007) indicates that manoeuvrability predicts the mode of cavity search. It further highlights the importance of call amplitude for eavesdropping and cavity detection in bats.