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.     

Acoustic classification of dolphins in the California Current using whistles,echolocation clicks,and burst pulses

Passive acoustic monitoring of dolphins is limited by our ability to classify calls to species. Significant overlap in call characteristics among many species, combined with a wide range of call types and acoustic behavior, makes classification of calls to species challenging. Here, we introduce BANTER, a compound acoustic classification method for dolphins that utilizes information from all call types produced by dolphins rather than a single call type, as has been typical for acoustic classifiers. Output from the passive acoustic monitoring software, PAMGuard, was used to create independent classifiers for whistles, echolocation clicks, and burst pulses, which were then merged into a final, compound classifier for each species. Classifiers for five species found in the California Current ecosystem were trained and tested using 153 single‐species acoustic events recorded during a 4.5 mo combined visual and acoustic shipboard cetacean survey off the west coast of the United States. Correct classification scores for individual species ranged from 71% to 92%, with an overall correct classification score of 84% for all five species. The conceptual framework of this approach easily lends itself to other species and study areas as well as to noncetacean taxa.     

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.     

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.     

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.     

Echolocation calls in Central American emballonurid bats: signal design and call frequency alternation

In southern Central America, 10 species of emballonurid bats occur, which are all aerial insectivores: some hunt flying insects preferably away from vegetation in open space, others hunt in edge space near vegetation and one species forages mainly over water. We present a search call design of each species and link signal structure to foraging habitat. All emballonurid bats use a similar type of echolocation call that consists of a central, narrowband component and one or two short, frequency-modulated sweeps. All calls are multi-harmonic, generally with most energy concentrated in the second harmonic. The design of search calls is closely related to habitat type, in particular to distance of clutter. Emballonurid bats foraging in edge space near vegetation and over water used higher frequencies, shorter call durations and shorter pulse intervals compared with species mostly hunting in open, uncluttered habitats. Peak frequency correlated negatively with body size. Regular frequency alternation between subsequent calls was typical in the search sequences of four out of 10 species. We discuss several hypotheses regarding the possible role of this frequency alternation, including species identification and partitioning of acoustic channels. Furthermore, we propose a model of how frequency alternation could increase the maximum detection distance of obstacles by marking search calls with different frequencies.     

BOOK REVIEW

Echolocation calls of four species of insectivorous bats of central Chile were recorded and characterized to determine vocal signatures that allow their identification in the field. Pulses of Tadarida brasiliensis were characterized by the highest duration and the lowest values for all frequencies, which do not overlap those of the remaining species. Tadarida emits narrowband, shallow frequency-modulated search calls. All three vespertilionid species studied (Histiotus montanus, Lasiurus varius and Myotis chiloensis) showed similar echolocation design to one another, consisting of a downward frequency modulation at the beginning of the signal followed by a narrowband quasi-constant frequency component; however, their calls differ by their spectral characteristics. Discriminant function analysis of six acoustic parameters (duration, initial frequency, slope frequency modulation, peak frequency, minimal and maximal frequencies) gave an overall classification of 87.4%, suggesting species could be correctly classified based on echolocation calls. Call duration and minimal frequency were the variables most important for species identification.     

‘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.     

Use of Vocal Signatures for the Inventory of Free-flying Neotropical Bats1

An ongoing study is being conducted to test the efficacy of the Anabat II detector and analysis system in obtaining reliable vocal signatures for the identification of non–phyllostomid species of bats. We sampled a wide range of elevations and associated habitat types throughout Belize. Anabat provides an instantaneous output of echolocation call structure with a laptop computer. Select sequences can be saved directly to the hard drive, avoiding extraneous noise and sound distortion commonly associated with tape recorders. To date, 18 of the 37 species known or expected to occur in the study region were identified by recognizable differences in the time–frequency characteristics of echolocation calls. In general, each family is recognizable by call structure patterns and species readily separated by frequency range parameters. Species that commute or forage at high altitudes are not susceptible to capture but are conspicuous by acoustic sampling. Further work is needed to determine limitations of the equipment, establish better sampling procedures, and develop a comprehensive library of vocal signatures incorporating the range of variation inherent in each species. As this work progresses, we predict the addition of hitherto unknown species occurring within the study region.     

Effectiveness of acoustic lures for increasing tropical forest understory bat captures

Bats are the most diverse mammalian order second to rodents, with 1400+ species globally. In the tropics, it is possible to find more than 60 bat species at a single site. However, monitoring bats is challenging due to their small size, ability to fly, cryptic nature, and nocturnal activity. Recently, bioacoustic techniques have been incorporated into survey methods, either through passive acoustic monitoring or acoustic bat lures. Lures have been developed on the premise that broadcasting acoustic stimuli increases the number of captures in harp traps or mist nets. However, this is a relatively new, niche method. This study tested the efficacy of two commonly used acoustic bat lure devices, broadcasting two different acoustic stimuli, to increase forest understory bat captures in the tropics. This is the first time an acoustic bat lure has been systematically tested in a tropical rainforest, and the first study to compare two lure devices (Sussex AutoBat and Apodemus BatLure). Using a paired experimental design, two synthesized acoustic stimuli were broadcasted, a feeding call and a social call, to understand the importance of the call type used on capture rates and genus‐specific responses. Using an acoustic lure significantly increased capture rates, while the type of device did not impact capture rates. The two acoustic stimuli had an almost even distribution of captures, suggesting that the type of call may be less important than previously thought. Results indicate a possible deterrent effect on Rhinolophous sp., while being particularly effective for attracting bats in the genera Murina and Kerivoula. This study highlights the effectiveness of lures, however, also indicates that lure effects can vary across genera. Therefore, lures may bias survey results by altering the species composition of bats caught. Future research should focus on a single species or genus, using synthesized calls of conspecifics, to fully understand the effect of lures.     

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.     

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.     

Understanding signal design during the pursuit of aerial insects by echolocating bats: tools and applications

Bats are among the few predators that can exploit the large quantities of aerial insects active at night. They do this by using echolocation to detect, localize, and classify targets in the dark. Echolocation calls are shaped by natural selection to match ecological challenges. For example, bats flying in open habitats typically emit calls of long duration, with long pulse intervals, shallow frequency modulation, and containing low frequencies-all these are adaptations for long-range detection. As obstacles or prey are approached, call structure changes in predictable ways for several reasons: calls become shorter, thereby reducing overlap between pulse and echo, and calls change in shape in ways that minimize localization errors. At the same time, such changes are believed to support recognition of objects. Echolocation and flight are closely synchronized: we have monitored both features simultaneously by using stereo photogrammetry and videogrammetry, and by acoustic tracking of flight paths. These methods have allowed us to quantify the intensity of signals used by free-living bats, and illustrate systematic changes in signal design in relation to obstacle proximity. We show how signals emitted by aerial feeding bats can be among the most intense airborne sounds in nature. Wideband ambiguity functions developed in the processing of signals produce two-dimensional functions showing trade-offs between resolution of time and velocity, and illustrate costs and benefits associated with Doppler sensitivity and range resolution in echolocation. Remarkably, bats that emit broadband calls can adjust signal design so that Doppler-related overestimation of range compensates for underestimation of range caused by the bat's movement in flight. We show the potential of our methods for understanding interactions between echolocating bats and those prey that have evolved ears that detect bat calls.     

Operator bias in software‐aided bat call identification

Software-aided identification facilitates the handling of large sets of bat call recordings, which is particularly useful in extensive acoustic surveys with several collaborators. Species lists are generated by “objective” automated classification. Subsequent validation consists of removing any species not believed to be present. So far, very little is known about the identification bias introduced by individual validation of operators with varying degrees of experience. Effects on the quality of the resulting data may be considerable, especially for bat species that are difficult to identify acoustically. Using the batcorder system as an example, we compared validation results from 21 volunteer operators with 1–26 years of experience of working on bats. All of them validated identical recordings of bats from eastern Austria. The final outcomes were individual validated lists of plausible species. A questionnaire was used to enquire about individual experience and validation procedures. In the course of species validation, the operators reduced the software''s estimate of species richness. The most experienced operators accepted the smallest percentage of species from the software''s output and validated conservatively with low interoperator variability. Operators with intermediate experience accepted the largest percentage, with larger variability. Sixty-six percent of the operators, mainly with intermediate and low levels of experience, reintroduced species to their validated lists which had been identified by the automated classification, but were finally excluded from the unvalidated lists. These were, in many cases, rare and infrequently recorded species. The average dissimilarity of the validated species lists dropped with increasing numbers of recordings, tending toward a level of ˜20%. Our results suggest that the operators succeeded in removing false positives and that they detected species that had been wrongly excluded during automated classification. Thus, manual validation of the software''s unvalidated output is indispensable for reasonable results. However, although application seems easy, software-aided bat call identification requires an advanced level of operator experience. Identification bias during validation is a major issue, particularly in studies with more than one participant. Measures should be taken to standardize the validation process and harmonize the results of different operators.     

Echolocation call description of 15 species of Middle-Eastern desert dwelling insectivorous bats

Modern advances in acoustic technology have made possible new and broad ranges of research in bioacoustics, particularly with regard to echolocating bats. In the present study, we present an acoustic guide to the calls of 15 species of bats in the Arava rift valley, Israel, with a focus on their bioacoustics, habitat use and explaining differences between similar species. We also describe a potential case of frequency separation where four bat species using six call types appear to separate the frequencies of their calls to minimize overlap. The studied community of bat species is also found in other Middle Eastern deserts including the deserts of Jordan, Syria and Saudi Arabia and we hope that data gathered will benefit other bat researchers in the region.     

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.     

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.     

Vocal individuality,but not stability,in wild palm cockatoos (Probosciger aterrimus)

The ability to identify individuals within a population is often essential for a detailed understanding of the ecology and conservation of a species. However, some species, including large parrots, are notoriously difficult to catch and mark for individual identification. Palm cockatoos (Probosciger aterrimus) are a large, poorly understood species of parrot which are likely in severe decline within the eastern part – and possibly the western part – of their range on Cape York Peninsula, Australia. Here, we investigated whether three different palm cockatoo call types are sufficiently individually distinctive to function as a non-invasive “marker” for identifying individuals over time. Using Discriminant Function Analysis, overall identification accuracy among 12 putative individuals for all call types was 81% (i.e. 148 out of 183 calls were assigned to the correct individual) on the basis of multiple temporal, energy (amplitude) and frequency measurements on the spectrogram. For three different call types, individual identification accuracy among males and females ranged from 69 to 95%. However, based on a limited sample sizes of five putative individuals between years, our data suggest that individual call structure, as quantified by call parameters, was not stable between years. We discuss the applicability of these results for future studies of palm cockatoos and other parrot species.