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.     

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.     

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.     

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.     

Geographical variation in the high-duty cycle echolocation of the cryptic common mustached bat Pteronotus cf. rubiginosus (Mormoopidae)

The use of bioacoustics as a tool for bat research is rapidly increasing worldwide. There is substantial evidence that environmental factors such as weather conditions or habitat structure can affect echolocation call structure in bats and thus compromise proper species identification. However, intraspecific differences in echolocation due to geographical variation are poorly understood, which poses a number of issues in terms of method standardization. We examined acoustic data for Pteronotus cf. rubiginosus from the Central Amazon and the Guiana Shield. We provide the first evidence of intraspecific geographic variation in bat echolocation in the Neotropics, with calls significantly differing in almost all standard acoustic parameters for the two lineages of this clade. We complement our bioacoustic data with molecular and morphological data for both species. Considerable overlap in trait values prevents reliable discrimination between the two sympatric Pteronotus based on morphological characters. On the other hand, significant divergence in the frequency of maximum energy suggests that bioacoustics can be used to readily separate both taxa despite extensive intraspecific variability in their echolocation across the Amazon. Given the relative lack of barriers preventing contact between bat populations from the Central Amazon and French Guiana, the documented acoustic variation needs to be further studied in geographically intermediate locations to understand the potential isolation processes that could be causing the described divergence in echolocation and to determine whether this variation is either discrete or continuous.     

菲菊头蝠回声定位声波频率的性二态有利于性别识别

许多动物的叫声频率呈现性二态现象。蝙蝠夜间活动,主要利用声音信号导航空间、追踪猎物、传递交流信息。本研究选择成体菲菊头蝠作为研究对象,检验回声定位声波频率性二态是否有利于性别识别。研究发现,菲菊头蝠回声定位声波频率参数具有显著性别差异。播放白噪音、雄性回声定位声波及雌性回声定位声波期间,实验个体的反应叫声数量依次递减。播放白噪音、雌性回声定位声波及雄性回声定位声波后,实验个体的反应叫声数量依次递增。白噪音诱导反应叫声强度高于回声定位声波诱导反应叫声强度。研究结果表明,菲菊头蝠回声定位声波的频率参数编码发声者性别信息,有利于种群内部的性别识别。本研究暗示,回声定位声波可能在蝙蝠配偶选择中扮演一定作用。     

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.     

Functional differences in echolocation call design in an adaptive radiation of bats

All organisms have specialized systems to sense their environment. Most bat species use echolocation for navigation and foraging, but which and how ecological factors shaped echolocation call diversity remains unclear for the most diverse clades, including the adaptive radiation of neotropical leaf‐nosed bats (Phyllostomidae). This is because phyllostomids emit low‐intensity echolocation calls and many inhabit dense forests, leading to low representation in acoustic surveys. We present a field‐collected, echolocation call dataset spanning 35 species and all phyllostomid dietary guilds. We analyze these data under a phylogenetic framework to test the hypothesis that echolocation call design and parameters are specialized for the acoustic demands of different diets, and investigate the contributions of phylogeny and body size to echolocation call diversity. We further link call parameters to dietary ecology by contrasting minimum detectable prey size estimates (MDPSE) across species. We find phylogeny and body size explain a substantial proportion of echolocation call parameter diversity, but most species can be correctly assigned to taxonomic (61%) or functional (77%) dietary guilds based on call parameters. This suggests a degree of acoustic ecological specialization, albeit with interspecific similarities in call structure. Theoretical MDPSE are greatest for omnivores and smallest for insectivores. Omnivores significantly differ from other dietary guilds in MDPSE when phylogeny is not considered, but there are no differences among taxonomic dietary guilds within a phylogenetic context. Similarly, predators of non‐mobile/non‐evasive prey and predators of mobile/evasive prey differ in estimated MDPSE when phylogeny is not considered. Phyllostomid echolocation call structure may be primarily specialized for overcoming acoustic challenges of foraging in dense habitats, and then secondarily specialized for the detection of food items according to functional dietary guilds. Our results give insight into the possible ecological mechanisms shaping the diversity of sensory systems, and their reciprocal influence on resource use.     

蝙蝠回声定位声波的可塑性及其生态适应

蝙蝠通过调节回声定位声波特征来满足自身的感官需求,表现出回声定位声波的可塑性及其对生态环境与需求的适应。声波频率、强度、脉冲持续时间和间隔时间等特征与蝙蝠所处的生态位密切相关,声波可塑性在蝙蝠进化过程中起着至关重要的作用。本文结合马铁菊头蝠(Rhinolophus ferrumequinum)和大趾鼠耳蝠(Myotis macrodactylus)回声定位声波可塑性的研究,从回声定位声波的方向性、目标距离、环境复杂度和应对干扰4个方面总结了蝙蝠如何通过改变回声定位声波特征来满足自身在导航和捕捉猎物过程中的感官需求与生态适应,并阐述了回声定位声波可塑性的研究现状,为开展蝙蝠声学和行为学研究提供参考。     

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.     

Female Mate Choice Can Drive the Evolution of High Frequency Echolocation in Bats: A Case Study with Rhinolophus mehelyi

Animals employ an array of signals (i.e. visual, acoustic, olfactory) for communication. Natural selection favours signals, receptors, and signalling behaviour that optimise the received signal relative to background noise. When the signal is used for more than one function, antagonisms amongst the different signalling functions may constrain the optimisation of the signal for any one function. Sexual selection through mate choice can strongly modify the effects of natural selection on signalling systems ultimately causing maladaptive signals to evolve. Echolocating bats represent a fascinating group in which to study the evolution of signalling systems as unlike bird songs or frog calls, echolocation has a dual role in foraging and communication. The function of bat echolocation is to generate echoes that the calling bat uses for orientation and food detection with call characteristics being directly related to the exploitation of particular ecological niches. Therefore, it is commonly assumed that echolocation has been shaped by ecology via natural selection. Here we demonstrate for the first time using a novel combined behavioural, ecological and genetic approach that in a bat species, Rhinolophus mehelyi: (1) echolocation peak frequency is an honest signal of body size; (2) females preferentially select males with high frequency calls during the mating season; (3) high frequency males sire more off-spring, providing evidence that echolocation calls may play a role in female mate choice. Our data refute the sole role of ecology in the evolution of echolocation and highlight the antagonistic interplay between natural and sexual selection in shaping acoustic signals.     

IDENTIFICATION OF BRITISH BAT SPECIES BY MULTIVARIATE ANALYSIS OF ECHOLOCATION CALL PARAMETERS

ABSTRACT

Previous studies have found variability and individual distinctiveness in the echolocation calls of bats. We consider two implications of individually distinct echolocation calls: 1) whether bats may be able to use such variation to recognise familiar conspecifics, and 2) whether investigators could use such variation to identify known individuals or to census populations. We compared the discriminability of the echolocation calls of big brown bats (Eptesicus fuscus) recorded in three situations: (a) while held in the hand, (b) while perched on a platform, and (c) while flying in an anechoic chamber. Using variables describing each sonar call, we employed discriminant function analysis (DFA) to assign calls to recording situation or to bat. Discrimination of calls by recording situation was largely unsuccessful, although flying calls could be distinguished from platform calls. Assignment of calls to individual bat across recording situations yielded 72% success, and, within a given recording situation, yielded 87% success. Stepwise DFA reduced the number of variables needed to discriminate between individuals with only a slight decrease in correct classification. These results suggest that bats (or researchers) may be able to use the information contained in the echolocation calls for individual recognition. Individual distinctiveness raises the possibility of censusing bats by sound. We used cluster analysis in an attempt to determine whether, given a sample of calls from an unknown number of bats, a reasonable estimate of the number of bats could be obtained. Results were unsatisfactory, suggesting that cluster analysis probably will not permit acoustic censusing of bats in the field.     

The development of vocalizations in Pipistrellus pipistrellus (Chiroptera: Vespertilionidae) during post-natal growth and the maintenance of individual vocal signatures

The development of vocalizations during post-natal growth in the microchiropteran bat Pipistrellus pipistrellus is described. Vocalizations served as precursors of echolocation sounds and as isolation calls used to attract mothers. Although calls judged to be echolocation precursors tended to be of short duration and possessed high rates of frequency modulation when compared with isolation calls, a wide spectrum of intermediate calls existed making classification diffuse. Changes in the frequencies and durations of calls during growth are described. Multiple discriminant analysis showed considerable inter-individual variation in isolation calls, while the calls of any individual were remarkably consistent in their structure at both six days and 15 days of age. The relative importance of acoustic call parameters in contributing towards inter-individual variation changed between six days and 15 days. Vocal signatures of youngsters were probably important in allowing a mother to identify her own offspring in a creche thus preventing misdirected maternal care in this species, though vocal signatures of infants changed during development. Echolocation calls of flying juveniles were compared with calls from their mothers.     

Moth hearing in response to bat echolocation calls manipulated independently in time and frequency

We measured the auditory responses of the noctuid moth Noctua pronuba to bat echolocation calls which were manipulated independently in time and frequency. Such manipulations are important in understanding how insect hearing influences the evolution of echolocation call characteristics. We manipulated the calls of three bat species (Rhinolophus hipposideros, Myotis nattereri and Pipistrellus pipistrellus) that use different echolocation call features by doubling their duration or reducing their frequency, and measured the auditory thresholds from the A1 cells of the moths. Knowing the auditory responses of the moth we tested three predictions. (i) The ranking of the audibility of unmanipulated calls to the moths should be predictable from their temporal and/or frequency structure. This was supported. (ii) Doubling the duration of the calls should increase their audibility by ca. 3 dB for all species. Their audibility did indeed increase by 2.1-3.5 dB. (iii) Reducing the frequency of the calls would increase their audibility for all species. Reducing the frequency had small effects for the two bat species which used short duration (2.7-3.6 ms) calls. However, the relatively long-duration (50 ms), largely constant-frequency calls of R. hipposideros increased in audibility by 21.6 dB when their frequency was halved. Time and frequency changes influence the audibility of calls to tympanate moths in different ways according to call design. Large changes in frequency and time had relatively small changes on the audibility of calls for short, largely broadband calls. Channelling energy into the second harmonic of the call substantially decreased the audibility of calls for bats which use long-duration, constant-frequency components in echolocation calls. We discuss our findings in the contexts of the evolution of both bat echolocation call design and the potential responses of insects which hear ultrasound.     

Plasticity in echolocation calls of <Emphasis Type="Italic">Myotis macrodactylus</Emphasis> (Chiroptera: Vespertilionidae): implications for acoustic identification

Poor knowledge of the intraspecific variability in echolocation calls is recognized as an important limiting factor for the accurate acoustic identification of bats. We studied the echolocation behaviors of an ecologically poorly known bat species, Myotis macrodactylus, while they were commuting in three types of habitats differing significantly in the amount of background clutter, as well as searching for prey above the water surface in a river. Results showed that M. macrodactylus altered their echolocation call structure in the same way during commuting as foraging bats do in relation to the changing level of clutter. With increasing level of clutter, M. macrodactylus generally produced echolocation calls with higher start, end, and peak frequencies; wider bandwidth; and shorter pulse duration. Compared to commuting, bats emitted significantly lower frequency calls with narrower bandwidth while searching for prey. Discriminant function analysis indicated that 79.8% of the calls from the three commuting habitats were correctly grouped, and 87% of the calls were correctly classified to the commuting and foraging contexts. Our finding has implications for those who would identify species by their calls.     

Identification of sympatric bat species by the echolocation calls

One hundred and thirty-eight echolocation calls of 63 free-flying individuals of five bat species (Rhinolophus ferrumequinum,Myotis formosus,Myotis ikonnikovi,Myotis daubentoni and Murina leucogaster)were recorded (by ultrasonic bat detector (D980)) in Zhi'an village of Jilin Province,China.According to the frequency-time spectra,these calls were categorized into two types:FM/CF (constant frequency) / FM (R.ferrumequinum) and FM (frequency modulated)(M.formosus,M.ikonnikovi,M.daubentoni and M.leucogaster).Sonograms of the calls of R.ferrumequinum could easily be distinguished from those of the other four species.For the calls of the remaining four species,six echolocation call parameters,including starting frequency,ending frequency,peak frequency duration,longest inter-pulse interval and shortest inter-pulse interval,were examined by stepwise discriminant analysis.The results show that 84.1% of calls were correctly classified,which indicates that these parameters of echolocation calls play an important role in identifying bat species.These parameters can be used to test the accuracy of general predictions based on bats' morphology in the same forest and can provide essential information for assessing patterns of bat habitat use.     

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.     

Identification of sympatric bat species by the echolocation calls

One hundred and thirty-eight echolocation calls of 63 free-flying individuals of five bat species (Rhinolophus ferrumequinum, Myotis formosus, Myotis ikonnikovi, Myotis daubentoni and Murina leucogaster) were recorded (by ultrasonic bat detector (D980)) in Zhi’an village of Jilin Province, China. According to the frequency-time spectra, these calls were categorized into two types: FM/CF (constant frequency) / FM (R. ferrumequinum) and FM (frequency modulated) (M. formosus, M. ikonnikovi, M. daubentoni and M. leucogaster). Sonograms of the calls of R. ferrumequinum could easily be distinguished from those of the other four species. For the calls of the remaining four species, six echolocation call parameters, including starting frequency, ending frequency, peak frequency duration, longest inter-pulse interval and shortest inter-pulse interval, were examined by stepwise discriminant analysis. The results show that 84.1% of calls were correctly classified, which indicates that these parameters of echolocation calls play an important role in identifying bat species. These parameters can be used to test the accuracy of general predictions based on bats’ morphology in the same forest and can provide essential information for assessing patterns of bat habitat use. __________ Translated from Journal of Northeast Normal University (Natural Science Edition), 2006, 38 (3): 109–114 [译自: 东北师范大学学报(自然科学版)]