The question matters because the existing literature has been strikingly inconsistent. Researchers have long known that bats modify their echolocation behavior when flying in groups compared with flying alone, but studies have reported different, sometimes conflicting, patterns in exactly which call properties change and in which direction. Some of this confusion is methodological. Echolocation recordings from a colony are a mixture of many overlapping signals, and separating the influence of social context from the influence of physical surroundings is genuinely difficult. A bat flying through a cluttered forest edge will naturally adjust its calls whether or not any companions are nearby, so disentangling the two effects requires data collected in a setting where both vary and an analytical framework flexible enough to detect their influence without prejudging its form.

That is precisely the approach the team took. Working with a colony of wild gray bats, they recorded echolocation calls as animals emerged from the roost and flew through their environment, while also tracking how many bats were emerging at a given time and noting the presence of obstacles along the flight path. Gray bats are an ideal subject for this kind of work. They are highly social, roosting and emerging in large numbers, which means group size varies substantially across emergence events. Their cave-roosting lifestyle also means they routinely navigate around and through physical structures, so environmental clutter is a natural feature of their daily flights rather than an artificial laboratory condition.

The researchers focused on two call properties that capture the energetic and temporal character of echolocation: the number of calls a bat produces and the acoustic power of those calls. Call rate and call intensity are the levers a bat can pull to change how much information its sonar gathers and how far that sonar reaches. Producing more calls refreshes the acoustic picture of the world more frequently, which is useful when maneuvering quickly or flying through tight spaces. Increasing acoustic power extends the range of detection but also increases the chance that the call interferes with, or is masked by, the calls of nearby conspecifics. The central hypothesis was that both the number of flying companions and the geometry of the surroundings would leave measurable fingerprints on these two properties.

To test that hypothesis without assuming in advance what the relationship should look like, the team turned to a time-series analysis tool called transfer entropy. Transfer entropy quantifies how much knowing the past state of one variable reduces uncertainty about the future state of another, beyond what the variable’s own history already reveals. In this context, it allowed the researchers to ask whether group size carries information about future call properties, and whether the presence of obstacles does, without imposing a linear or any other predetermined functional form on the relationship. This is a crucial advantage in a system as complex as a flying bat colony, where the true dynamics are almost certainly nonlinear and shaped by feedback between individuals and their environment.

The analysis revealed significant transfer entropy values linking both social and environmental factors to call properties. In plain terms, the number of bats emerging together and the presence of obstacles each carried genuine predictive information about how many calls individual bats produced and how acoustically powerful those calls were. The influence was detected without the researchers assuming any particular mathematical shape for it, which strengthens the conclusion that the relationships are real features of the bats’ behavior rather than artifacts of a chosen model. This finding helps resolve the inconsistency in earlier literature by suggesting that reported differences across studies may reflect genuine context dependence: the direction and magnitude of call adjustments plausibly depend on the specific combination of group density and environmental clutter a colony experiences.

Transfer entropy established that the influences exist, but the team wanted to go further and sketch what the underlying dynamics might actually look like. For this they applied a data-driven algorithm known as sparse identification of nonlinear dynamics, or SINDy. The core idea behind SINDy is elegant: given time-series measurements, it searches an enormous library of candidate functions and terms for the simplest set of equations that can reproduce the observed dynamics. Rather than a human modeler guessing that call rate should depend linearly on group size, say, or quadratically on obstacle proximity, SINDy lets the data nominate the terms that matter and discard the rest. The result is a compact mathematical description of echolocation behavior assembled directly from recordings of wild bats going about their nightly business.

The SINDy-based models suggested concrete ways in which gray bats adjust their echolocation in response to conspecifics and obstacles, offering a candidate structure for the phenomenon that earlier descriptive studies could only gesture at. This modeling step is what elevates the study from a correlation hunt to a constructive contribution toward predictive theory. If the identified equations capture real behavioral rules, they can be tested against new recordings, compared across bat species with different social systems, and eventually incorporated into larger models of collective movement in which echolocation serves simultaneously as a sensory channel and, potentially, as a medium of unintended information sharing among group members.

The broader significance of the work lies in how it reframes the interplay between sociality and sensory ecology. Schools of fish and flocks of birds coordinate largely through vision and lateral-line or aerodynamic sensing, channels that do not degrade in the same way when many individuals use them at once. Echolocation is different: it is an active sensing modality in which every individual’s measurement apparatus is also a potential source of noise for everyone else. The new results indicate that gray bats manage this trade-off in a way that is jointly sensitive to who else is flying and what the physical environment demands. Sociality, in other words, is not just a background condition for echolocation but an active driver of its dynamics, intertwined with the geometry of caves, cliffs, and forest corridors through which the animals move.

For researchers studying collective behavior, bioacoustics, and sensory ecology, the study offers both a methodological template and a set of testable expectations. The combination of transfer entropy and SINDy provides a pipeline for extracting dynamical rules from noisy field recordings of animals whose signals overlap and interfere, a challenge that extends well beyond bats to any species using active sensing in groups. For the gray bats themselves, the findings paint a picture of animals continuously recalibrating their sonar against two competing pressures: the need to navigate a cluttered, obstacle-strewn world and the need to keep their acoustic measurements usable in the company of hundreds of calling companions. As the authors note, these results provide new insights into the role of sociality and physical surroundings in shaping echolocation dynamics, and they suggest that the nightly exodus from a gray bat cave is not just a mass of sound but a richly structured information environment, one the bats themselves are constantly measuring, adjusting to, and rewriting call by call.

Subject of Research: How group size and environmental obstacles influence echolocation call properties in flying gray bats

Article Title: Group size and environmental obstacles drive acoustic call properties for gray bats in flight: A data-driven analysis

Article References: Grey, M., Aung, E., & Abaid, N. (2026). Group size and environmental obstacles drive acoustic call properties for gray bats in flight: A data-driven analysis. PLOS Complex Systems, 3(4), e0000100. https://doi.org/10.1371/journal.pcsy.0000100

Image Credits: AI Generated

DOI: 10.1371/journal.pcsy.0000100

Keywords: gray bats, echolocation, Myotis grisescens, transfer entropy, SINDy, collective behavior, bioacoustics, group size, environmental obstacles, nonlinear dynamics, sensory ecology, PLOS Complex Systems

The Azores host just two confirmed extant bat species, both of them endemics with restricted ranges. The Azorean bat, Nyctalus azoreum, is found nowhere else in the world and has so far been confirmed on seven of the archipelago’s nine islands. The Madeiran pipistrelle, Pipistrellus maderensis, is a Macaronesian endemic that also occurs in Madeira and the Canary Islands. In the western group of the Azores, composed of Flores and the even smaller Corvo, only pipistrelle-type calls had ever been detected acoustically. But recent observations of bats flying during daylight hours on Flores, together with the recovery of a dead pipistrelle specimen, raised questions about what was really living on the island and prompted the new investigation.

The genetic half of the study rested on a single, poignant specimen. In August 2024, a nature conservation ranger recovered a dead bat at Fazenda on the northern coast of Flores. The dark brown adult, with a forearm measuring 32.4 millimetres, bore tears in its wing membranes and lower abdomen, and contextual evidence suggested it had likely been killed by a domestic cat. Researchers excised a three-millimetre puncture of wing tissue, stored it in ethanol, and extracted genomic DNA in the laboratory. They amplified a fragment of the mitochondrial cytochrome b gene by polymerase chain reaction and sequenced it commercially, producing an 814-base-pair sequence that was subsequently deposited in GenBank under accession number PZ699694.

The sequence told an unambiguous story. When compared against public databases, it showed its highest identity, 98.8 percent, with P. maderensis sequences from the Madeira archipelago. To place the Flores bat in a broader geographic context, the team built a median-joining haplotype network from 465 base pairs of cytochrome b, drawing on published sequences from Madeira, Porto Santo, the Canary Islands, and multiple populations of the related Kuhl’s pipistrelle from Europe, North Africa, and the Middle East, alongside Azorean N. azoreum sequences. The Flores specimen fell squarely within the P. maderensis cluster, most closely associated with haplotypes from Madeira and Porto Santo. Intriguingly, the Flores sequence represents a unique haplotype, separated by six mutational steps from the shared Madeira and Porto Santo group and ten steps from the nearest Canarian haplotype, a pattern that hints at either colonisation from the Madeira region or shared ancestry followed by local differentiation in the Azores.

This genetic confirmation carries real weight for Macaronesian biogeography. Although P. maderensis had previously been genetically identified on the Azorean island of Santa Maria, that sequence was never published in a public database, meaning the Flores specimen now constitutes the first publicly available genetic reference for the species in the Azores. Until now, pipistrelle records across most of the archipelago rested on acoustic detections alone, which cannot distinguish P. maderensis from morphologically similar relatives with complete certainty. The new sequence establishes a baseline for future studies of population structure, connectivity, and colonisation history across the scattered island groups of the region, where small founder populations can diverge rapidly in isolation.

The acoustic half of the study was equally revealing. Between 16 and 19 September 2024, the team deployed autonomous AudioMoth recorders at ten sites across Flores, mounted on tree trunks or poles about 1.8 metres above the ground. The devices sampled at 192 kilohertz in a cyclical pattern of four and a half minutes of recording followed by a thirty-second pause, running continuously over consecutive 24-hour periods. Persistent heavy rainfall caused two devices to malfunction, and two remote northwestern sites could not be reached by vehicle, but the remaining ten sites provided broad coverage of the island’s main habitat types. Out of 5,760 recordings, 296 files contained bat activity, yielding a total of 3,862 bat passes, each defined as at least two sequential recognisable echolocation pulses.

The species split within those passes was strikingly lopsided. Pipistrellus maderensis accounted for 99.6 percent of all recorded activity and was detected at every sampled site, confirming its status as the most widespread and acoustically active bat on Flores, with particularly high activity along the northern coast. Nyctalus azoreum, by contrast, contributed just 0.4 percent of passes and was detected only at a handful of sites in the central and southern parts of the island. The two species can be reliably separated acoustically because their echolocation calls occupy similar but non-overlapping frequency ranges: N. azoreum calls peak at around 32.1 kilohertz, while Pipistrellus calls peak at about 45.3 kilohertz. The detection of the Azorean bat at sites that had been surveyed before suggests that earlier non-detections reflected low detectability and lower sampling effort rather than true absence, since previous surveys relied on short-duration hand-held detectors rather than recorders running for days at a time.

Activity patterns followed a strictly nocturnal rhythm. Every call was recorded between sunset at 20:06 and sunrise at 07:47 local time, with no daytime activity detected during the study period, despite N. azoreum being known elsewhere in the archipelago to forage in daylight. Both species remained active throughout the night, tapering off in the hours before dawn. The earliest P. maderensis call came at 20:07 and the latest at 07:30, while N. azoreum activity spanned from 20:23 to 05:40. To test whether the bats favoured particular environments, the researchers classified sites as stream or urban habitats and fitted a negative binomial generalised linear mixed model with the number of passes per night as the response. The effect of species on activity was only marginal, and neither habitat nor the species-by-habitat interaction was statistically significant, suggesting that both species use a range of environments on the island, although the very low number of Azorean bat detections limits any firm conclusions about its habitat preferences.

The findings matter well beyond Flores. Island bat populations are typically small, isolated, and vulnerable to habitat alteration, invasive species, and stochastic events, and previous work has shown substantial genetic structuring among N. azoreum populations, with haplotypes often restricted to individual islands and limited inter-island gene flow. That pattern implies the small Flores population may have little connection to bats elsewhere in the archipelago, raising questions about its long-term viability and the mechanisms that allow it to coexist with the far more abundant pipistrelle. The authors argue that continued monitoring is essential, and they recommend reassessing the occurrence of N. azoreum on neighbouring Corvo using passive acoustic recording, since earlier hand-held surveys there may likewise have missed a rare species. Surveys on São Miguel, Terceira, and Faial, where P. maderensis has not yet been confirmed, could also clarify the pipistrelle’s full distribution.

There is also a sobering conservation note embedded in the data. The only P. maderensis specimen collected during the study was likely predated by a domestic cat, a vivid illustration of the threat that introduced predators pose to island bats worldwide. Cats are increasingly recognised as significant predators of bats on oceanic islands, where native species evolved without such hunters and often roost or forage in accessible places. Combined with the apparent rarity of the Azorean bat on Flores and the vulnerability that comes with small population size, the study underscores a broader lesson: even in a well-studied European archipelago, remote islands can still hide species that only modern, patient, and integrated methods, listening to the night and reading the DNA of a single recovered wing, can bring to light.

Subject of Research: Distribution and conservation of bat species on Flores Island in the Azores, assessed through genetic and bioacoustic monitoring

Article Title: Bats of a remote island: integrated genetic and bioacoustics monitoring confirms species occurrence in Flores (Azores, Portugal)

Article References: Rainho, A., Estácio, C. S., Silva, C. G., & Gabriel, S. I. (2026). Bats of a remote island: integrated genetic and bioacoustics monitoring confirms species occurrence in Flores (Azores, Portugal). Web Ecology, 26(2), 193-202. https://doi.org/10.5194/we-26-193-2026

Image Credits: AI Generated

DOI: 10.5194/we-26-193-2026

Keywords: Azores, Flores Island, bats, Nyctalus azoreum, Pipistrellus maderensis, bioacoustics, mitochondrial DNA, island biogeography, conservation, endemic species, haplotype network, invasive predators

The review’s starting point is striking: one of the earliest machine learning applications in the field was an automatic frog call monitoring system presented back in 2002. From those modest beginnings, computational bioacoustics has expanded into a discipline that underpins large-scale biodiversity monitoring on every continent. The authors document a marked inflection point around 2016, after which research activity surged. That timing is no coincidence. It follows the deep learning revolution that transformed computer vision after the 2012 ImageNet breakthrough, when convolutional neural networks demonstrated that learned features could outperform hand-crafted ones. Bioacoustics, which treats animal sounds as images by converting recordings into spectrograms, was perfectly positioned to inherit those advances.

Taxonomically, the field has broadened dramatically. Early studies were overwhelmingly bird-focused, reflecting both the richness of avian vocalizations and the availability of recordings from citizen science repositories such as Xeno-Canto. The review shows a steady expansion toward amphibians, insects, marine mammals, fish, bats, rodents, and even livestock, culminating in multispecies soundscape analyses that attempt to characterize entire acoustic communities rather than individual species. Landmark applications along the way include passive acoustic monitoring of northern spotted owls across varied forest conditions, deep learning detection of humpback whale song in long-term datasets, classification of sperm whale bioacoustics, and automated recognition of insect pests such as the red palm weevil and rice weevil. The technology has even been used to distinguish individual chimpanzee infant distress calls and to track song variation in endangered birds like the white-bellied heron in Bhutan.

Methodologically, the review builds a unified comparative framework that standardizes studies across five dimensions: classification objectives, taxonomic groups, preprocessing strategies, learning paradigms, and algorithm families. This kind of harmonization is rare and valuable, because bioacoustics papers have historically been scattered across ecology, computer science, and engineering journals, each with its own vocabulary and conventions. By mapping every study onto a common structure, the authors can identify genuine trends rather than anecdotes. What they find is that supervised learning remains the dominant paradigm, which is unsurprising given that labeled recordings are the fuel of most classifiers, but that unsupervised and semi-supervised approaches have carved out important niches, particularly for exploratory soundscape analysis and for species where labeled data are scarce.

On the algorithmic front, deep learning architectures now reign. Convolutional neural networks, which excel at extracting spatial patterns from spectrograms, and recurrent neural networks, which capture temporal structure in call sequences, have become the most widely adopted approaches for bioacoustic classification. The review traces this shift through the literature, from early support vector machine and random forest classifiers working on hand-engineered features such as mel-frequency cepstral coefficients, to end-to-end deep models, to transfer learning pipelines built on pretrained networks like BirdNET, a deep learning solution for avian diversity monitoring that has become a workhorse for ecologists. Yet the authors are careful not to declare traditional methods obsolete. Support vector machines and random forests continue to deliver competitive performance in many applications, especially when embedded in well-designed analytical workflows, a finding that should give pause to anyone assuming bigger models are always better.

Perhaps the most technically interesting result concerns preprocessing. The comparative analysis indicates that strategies including data augmentation, feature reduction, noise removal, and window segmentation are consistently associated with high-performing classification pipelines. In other words, what happens to the audio before it reaches the model matters enormously. Field recordings are notoriously messy: wind, rain, insects, traffic, and overlapping animal calls all contaminate the signal. Techniques such as spectral filtering, sound separation, careful segmentation of long recordings into analysis windows, and augmentation methods that artificially expand small training sets can make the difference between a classifier that works in the lab and one that works in the rainforest. The review also highlights studies showing that even the parameters used to generate spectrograms measurably affect the accuracy of convolutional neural network classifiers, underscoring how sensitive these systems are to upstream choices.

The authors went beyond simple tallies, applying mixed-effects statistical analyses to ask which factors actually predict reported classification performance. Their conclusion is subtle and important: performance is more strongly associated with specific algorithmic implementations than with broader algorithm families, and significant interactions between methodological components mean that classification outcomes cannot be explained by any single factor considered in isolation. A convolutional neural network is not intrinsically superior to a random forest; rather, success depends on the coherent integration of preprocessing, feature representation, and learning algorithm within a complete pipeline. This holistic view challenges the common practice of comparing algorithms in isolation and suggests that much of the reported variation in the literature reflects pipeline design rather than fundamental differences between model types.

That insight leads directly to the review’s most sobering finding. Despite a decade of methodological progress, considerable heterogeneity persists in datasets, preprocessing procedures, evaluation protocols, and reported performance metrics across the field. Studies differ in how they split data, which metrics they report, how they handle class imbalance, and even how they define a detection. The consequence is that results from different papers often cannot be directly compared, and reproducibility suffers. This mirrors a broader reproducibility crisis documented across machine learning research, and it has practical stakes: conservation managers deciding whether to trust an automated recognizer for monitoring an endangered species need to know how performance estimates were produced and whether they will generalize to new sites and seasons.

To address these problems, the authors propose a set of good-practice recommendations centered on standardized dataset documentation, transparent methodological reporting, consistent evaluation frameworks, and clearly defined research objectives. The spirit of these recommendations is that a bioacoustics study should be legible to outsiders: readers should be able to tell exactly what data were used, how they were processed, how the model was trained and validated, and under what conditions the reported accuracy can be expected to hold. The authors argue that adopting such standards will improve reproducibility, facilitate cross-study comparisons, and strengthen computational bioacoustics as a robust discipline capable of supporting large-scale biodiversity monitoring and conservation.

The timing of this synthesis could hardly be better. Passive acoustic monitoring is rapidly becoming one of the most scalable tools in ecology, with low-cost autonomous recorders now deployed for months at a time in environments from Arctic tundra to tropical rainforest and deep ocean. As foundation models for bioacoustics emerge and recording archives swell into petabytes, the field stands at an inflection point where the lessons of the past twenty years will determine whether the next twenty deliver on the promise of a planet continuously listened to by machines. This review makes clear that the algorithms are largely ready; the challenge now is to make the science around them as rigorous as the technology itself, so that every chirp, click, and song captured by a microphone can be translated into reliable knowledge about the living world.

Subject of Research: Machine learning methods for automated classification of animal vocalizations and soundscapes in computational bioacoustics

Article Title: Two decades of machine learning in bioacoustics: a systematic review

Article References: Mora-González, E., Canepa-Oneto, A., Barbero-Aparicio, J. A., & Arnaiz-González, Á. (2026). Two decades of machine learning in bioacoustics: a systematic review. Applied Intelligence, 56(15), Article 435. https://doi.org/10.1007/s10489-026-07454-0

Image Credits: AI Generated

DOI: 10.1007/s10489-026-07454-0

Keywords: bioacoustics, machine learning, deep learning, convolutional neural networks, passive acoustic monitoring, biodiversity monitoring, systematic review, preprocessing, reproducibility, conservation, soundscape ecology, classification

The study was led by Til Böttner as part of his doctoral thesis at the Department of General Zoology and Neurobiology at Ruhr University Bochum. As he explains, the team set out to determine which components of low-frequency, vibroacoustic stimuli actually elicit behavioral responses in the sea squirt. To answer that question, the researchers combined two complementary approaches: field experiments conducted in the Mediterranean, where Halocynthia papillosa lives naturally, and controlled laboratory conditions that allowed them to isolate and manipulate individual components of acoustic stimulation. This dual design matters, because in the real ocean, sound pressure, particle motion, and substrate-borne vibrations are physically intertwined, and teasing apart their relative contributions is one of the hardest problems in modern bioacoustics.

The behavioral results were clear and, in one respect, surprising. The sea squirts responded with contractions mainly to stimuli in a frequency band between 50 and 800 Hertz, a range that overlaps substantially with the low-frequency noise produced by shipping, construction, and other human activities at sea. Interestingly, these reactions were associated with increased vibrations in the substrate, the solid material on which the animals sit. In other words, when the seafloor itself trembled, the sea squirts noticed, contracting in a measurable defensive response. The frequency specificity of the reaction suggests a genuine sensory process rather than a generic startle, and it places these seemingly primitive animals within the growing roster of marine invertebrates known to detect and react to anthropogenic noise.

The most striking result, however, was what the animals did not do. Even when the underwater sound pressure levels exceeded 130 decibels, a level that would be considered significant by many standards used in noise-impact assessments, the sea squirts showed no comparable reactions, provided that the substrate vibrations remained below the thresholds the team had determined experimentally. As researcher Huhn concludes, the results show that sound pressure alone cannot explain the observed behavioral reactions. That single sentence carries considerable weight. Much of the regulatory and scientific framework for underwater noise relies on sound pressure measurements, and this study demonstrates that for at least one benthic species, such measurements may simply miss the stimulus that matters.

The physics behind this distinction is worth unpacking. Underwater sound is conventionally described by two related but distinct quantities: sound pressure, the oscillating compression of the water, and particle motion, the back-and-forth displacement of water molecules, which can be characterized in terms of displacement, velocity, or acceleration. Most fish and many invertebrates are thought to be sensitive to particle motion rather than pressure, yet pressure is far easier to measure and remains the standard metric in noise monitoring. To complicate matters further, at low frequencies a portion of the acoustic energy couples into the seabed and propagates as seismic waves, producing substrate-borne vibrations. For an animal cemented to a rock, like an ascidian, the substrate may effectively be the most direct pathway through which mechanical energy from a distant noise source reaches its body.

What sensory machinery might these animals be using? The answer is not yet certain, and the researchers are careful on this point. However, sea squirts possess specialized ciliated mechanoreceptor cells in the region of their siphons, the twin openings through which they draw in and expel water for filter feeding. These cells are particularly concentrated in a structure known as the coronal organ, and they may register local movements in the water or mechanical deformations of the body surface. Böttner notes that further physiological and neurobiological studies are required to determine whether these receptors are stimulated by particle motion in the water or by vibrations transmitted via the substrate and the mantle, the tough outer covering of the animal. Resolving that question will require direct recordings from the sensory cells and their associated neural pathways, work that is now on the research agenda in Bochum.

The coronal organ itself is a fascinating structure in evolutionary terms. Ciliated mechanoreceptor cells lining the siphons of ascidians are considered homologous, in a broad sense, to the hair cells of vertebrate ears, making tunicates a valuable model for understanding the deep evolutionary origins of mechanosensation. If Halocynthia papillosa is indeed detecting noise through these cells, the study would suggest that sensitivity to low-frequency mechanical disturbance is an ancient trait, present in animals whose lineage split from ours hundreds of millions of years ago. It would also imply that the coronal organ, long studied for its role in detecting water flow and potential threats as the animal adjusts its pumping behavior, may serve double duty as a vibroacoustic sensor tuned to the frequency range where human noise is loudest.

The researchers are candid about the limits of the current work. Sound pressure, particle motion, and substrate-borne vibrations are physically closely intertwined under water, especially at low frequencies, which makes it impossible to completely separate these factors, including in this study. Every acoustic stimulus delivered to an animal in a tank or on a reef carries some mixture of all three components, and even the most careful experimental design can only approximate the isolation of one pathway. Nevertheless, the findings show, as the researchers in Bochum put it, that the mechanical components of underwater sound have to be more closely considered in the examination of benthic organisms, the animals that live on or in the seafloor. For a field that has historically focused on fish, whales, and other free-swimming species, that is a significant redirection of attention toward the sessile majority of marine life.

The broader context makes this redirection urgent. Anthropogenic underwater noise, from commercial shipping and seismic surveys to pile driving and coastal construction, has increased dramatically over recent decades and is now recognized as a global environmental concern. Most impact assessments rest on sound pressure thresholds derived from studies of vertebrates, and the possibility that attached invertebrates respond primarily to substrate vibrations suggests that current metrics may systematically underestimate or mischaracterize the exposure of benthic communities. Since ascidians, mussels, corals, and other sessile animals cannot swim away from a noise source, their behavioral responses, such as the contractions observed in this study, may represent one of the few defenses available to them, and repeated disturbances could carry energetic or ecological costs that have yet to be quantified.

Future studies at Ruhr University Bochum aim to identify which mechanical stimuli are actually perceived by the sea squirts and how these stimuli are sensorially and neuronally processed, integrating marine biology, bioacoustics, and neurobiology into a single research program dedicated to understanding the effects of anthropogenic underwater noise in greater detail. The work has already drawn international recognition: Til Böttner received the prize for the best presentation by an early-career researcher at the International Tunicate Meeting for his presentation of this research. For now, the message of the study is both simple and disruptive to conventional thinking. An animal without ears can still feel the noise of the ocean, and it feels it through the ground. Any serious effort to understand, predict, or mitigate the impact of underwater noise on marine ecosystems will need to listen not only to the water, but to the seafloor beneath it.

Subject of Research: Behavioral responses of the sea squirt Halocynthia papillosa to underwater vibroacoustic stimuli and substrate-borne vibrations

Article Title: How sea squirts perceive underwater noise

Article References: How sea squirts perceive underwater noise. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: sea squirts, ascidians, underwater noise, substrate vibrations, sound pressure, particle motion, mechanoreceptors, coronal organ, bioacoustics, marine biology, anthropogenic noise, benthic organisms

The study, published in the journal Discover Conservation, is a systematic review of more than three decades of bat bioacoustics research. Researchers Luna Pino-Aedo and Andrés Muñoz-Sáez of the Universidad de Chile searched the ISI Web of Science database for studies published between 1990 and 2022, the period since passive acoustic monitoring of terrestrial ecosystems began in earnest. Their initial queries returned 531 candidate articles, and after screening each one at full text, 207 studies met the criteria: they analyzed bat echolocation calls and specified exactly how those calls were analyzed. From this body of work the authors catalogued 34 distinct echolocation analysis methods, spanning commercial software packages and a growing arsenal of supervised machine learning techniques.

The review reveals a field that has expanded explosively. Most of the included studies appeared after 2010, a trend the authors attribute to the falling cost and rising availability of automated ultrasonic recorders, with a notable peak in publications in 2021 that may reflect pandemic-era restrictions pushing researchers toward data analysis rather than fieldwork. Geographically, the science is heavily skewed: the United States accounted for 36.28 percent of the articles, followed by China with 12.56 percent. That concentration matters, because reference libraries of bat calls and the classifiers trained on them are richest for Nearctic and Palearctic species, leaving tropical hotspots of bat diversity comparatively underserved.

Echolocation itself is a remarkable biological technology. Bats generate ultrasonic pulses in the larynx and emit them through the mouth or nose; the returning echoes build an acoustic image of the surroundings that the animals use to navigate, forage and communicate. Because each species tends to produce calls with characteristic frequencies, durations and shapes, researchers realized decades ago that recordings could be used to identify species without ever catching them. Bat detectors from manufacturers such as Pettersson, Titley Scientific, Wildlife Acoustics and Avisoft dominated the reviewed studies, capturing calls at high sampling frequencies for later analysis through spectrograms and oscillograms.

But turning a recording into a species name is where things get complicated. Among the 118 studies whose primary goal was species identification, only 29 relied on fully automated identification; 55 used manual identification by a specialist, and 34 used a mixed approach in which experts verified or complemented machine output. The most frequently used software packages were Kaleidoscope, Avisoft, Analook, BatSound and SonoBat, often made by the same companies that build the detectors. While all of these tools visualize calls and filter noise, only some, notably Kaleidoscope and SonoBat, were actually used for automated species classification; the rest served mainly for manual inspection and parameter measurement.

Alongside commercial software, the review documented a parallel rise of supervised learning methods implemented in platforms such as Python and RStudio. Discriminant function analysis, a statistical technique that models predefined classes from numerical acoustic features, was among the most common, followed by artificial neural networks, random forests and support vector machines. Each brings distinct trade-offs. In a benchmark study by Armitage and Ober, artificial neural networks achieved the highest training accuracy at 86.1 percent of calls correctly identified but demanded the most computational resources and training time. Random forests delivered the best overall combination of accuracy, sensitivity and specificity at 85.5 percent while remaining fast to train. Discriminant function analysis was quickest but least accurate on average at 75.9 percent. In Uruguay, Botto Nuñez and colleagues found random forests outperformed both support vector machines and neural networks, correctly identifying 92.9 percent of calls with lower variance than either alternative.

Head-to-head comparisons under controlled conditions expose the gap between machine learning and commercial packages most starkly. Tabak and colleagues built a deep learning model based on convolutional neural networks that achieved an average accuracy of 91 percent, while Kaleidoscope Pro and BCID managed only 65 percent and 61 percent respectively on the same task. Earlier discriminant function and neural network approaches also outperformed the modern software evaluated by Rydell and colleagues, whose study found that the best automated program still fell short of the top human expert, though the software did reliably classify calls at the genus level and distinguished species with highly distinctive calls. Brabant and colleagues, testing four programs on nine European species, found BatIdent achieved the highest proportion of correct species-level identifications but also produced more misclassifications, while Kaleidoscope left the largest share of calls unidentified. Sensitivity settings materially changed results: Kaleidoscope’s accuracy rose under more sensitive configurations, whereas SonoChiro stayed relatively stable across settings.

Perhaps most disquieting is what happens when there is no ground truth at all. Studies by Lemen and by Nocera that assessed agreement between software packages without a reference identification found concordance rates of only around 40 percent, varying by species and sampling period. Agreement between programs, the authors conclude, is not a reliable proxy for accuracy. Even software version matters in unpredictable ways: Goodwin and Gillam found the best performance from Kaleidoscope Pro version 4.3.0 and SonoBat version 3.2.2, meaning newer releases were not necessarily better classifiers. Accuracy reporting itself remains rare, with only 28 of the 207 studies quantifying how often their methods classified calls correctly.

The review also catalogues the tangled web of factors that influence identification beyond the algorithms themselves. Call type matters, since search, approach, feeding and social calls differ within a single species, and many species produce calls so similar that even experts struggle. Recording context matters, whether calls come from free-flying animals or hand-released individuals. Weather matters, with temperature shifting peak frequencies. So do geography, age, morphology and even the roost a population occupies, all of which inject intraspecific variation that classifiers trained on narrow libraries cannot handle. Habitat structure and detector placement also shape outcomes: models trained on calls recorded at structurally complex forest edges outperformed those trained in open spaces, and recording angle significantly affected correct classification.

The authors’ prescription is a hybrid future. Automated classifiers should be treated as accelerators that triage enormous audio volumes and flag candidate events for expert review, not as stand-alone oracles, and they should be deployed unsupervised only for taxa with highly distinctive calls. Capture-based methods such as mist-netting remain indispensable, both for species with highly directional sound beams that evade standard detectors and for building verified reference datasets; combined acoustic-and-capture designs consistently detect more species than either method alone. The researchers call for open, regionally representative call libraries with detailed metadata on habitat and recording context, versioned benchmark datasets spanning detectors and ecoregions, and transparent reporting of complete analysis pipelines. With bat populations declining worldwide amid accelerating biodiversity loss, the stakes of getting this right could hardly be higher: misidentified calls can translate directly into misinformed conservation decisions for one of the planet’s most important, and most imperiled, groups of mammals.

Subject of Research: Systematic review of bat echolocation call analysis methods for species identification and conservation monitoring

Article Title: A systematic review of bat echolocation analysis methods and their implications for monitoring and conservation

Article References: Pino-Aedo, L., & Muñoz-Sáez, A. (2026). A systematic review of bat echolocation analysis methods and their implications for monitoring and conservation. Discover Conservation, 3(1), Article 17. https://doi.org/10.1007/s44353-026-00087-x

Image Credits: AI Generated

DOI: 10.1007/s44353-026-00087-x

Keywords: bats, echolocation, bioacoustics, machine learning, acoustic monitoring, species identification, conservation, neural networks, random forests, Kaleidoscope, passive acoustic monitoring, biodiversity

The study, led by Cristian Pérez-Granados and an international team of ornithologists, set out to do something rarely attempted: compare how songs and calls, the two main categories of bird vocalizations, respond to individual, population, and geographic factors within the same species. Songs are typically complex, learned, and tied to sexual selection, while calls tend to be shorter, more innate, and used for immediate communication such as territorial defense. Because these signals follow different developmental pathways, the team reasoned they might respond differently to habitat fragmentation, population size, and social isolation, providing complementary windows into population health.

Dupont’s lark proved an ideal model. Males sing and give territorial calls at high rates during the hour before dawn, and the species’ communication system is already known to be shaped by landscape structure. Songs are learned after juveniles disperse from their natal areas, by copying nearby adult males, and typically consist of three to eight discrete types. Territorial calls, by contrast, are learned before dispersal during a short learning phase in summer, likely from parents and neighbors in the natal patch, and consist of just one to three short whistles repeated regularly. This difference in timing means that songs and calls should carry information about movement and social interaction at different life stages.

Between March and June of 2024 and 2025, the researchers surveyed 27 habitat patches spanning the two main strongholds of the species in Spain, the Ebro Valley and the Iberian System. Patch areas ranged from 14 to 1,903 hectares and local male abundance from three to 77 individuals. Working in the pre-dawn darkness, they recorded 188 singing males with directional microphones and high-resolution digital recorders, capturing at least two minutes of song per male, sufficient to document the complete individual repertoire. For calls, they recorded a minimum of three calls per individual, ultimately sampling 74 calling males across 11 populations. When no birds were detected during repeated visits, autonomous recorders were deployed to confirm genuine absence.

The acoustic analysis was meticulous. A single expert scanned all recordings through spectrogram inspection in Raven Pro, delineating each vocalization and classifying it into types based on morphology, temporal patterns, frequency characteristics, and note structure. When classifications were uncertain or types appeared across populations, additional experienced ornithologists reviewed the material, and types were only confirmed when at least two researchers agreed. The final catalog contained 396 distinct song types drawn from 4,208 annotated songs, and 60 call types from 634 annotated calls. These were converted into presence-absence matrices allowing the team to compute repertoire sizes at both individual and population levels, and to quantify acoustic similarity between every pair of males using the Jaccard index.

The results revealed a striking divergence between the two vocalization types. Individual song repertoire size did not depend on population size, but varied significantly between regions, with Ebro Valley males singing larger repertoires than those in the Iberian System. At the population level, however, song repertoire size increased significantly with the number of territories, likely because larger patches host multiple local dialects among neighboring groups of males. Call repertoires, whether measured per individual or per population, showed no relationship with population size, geography, or sampling effort. Songs, in short, behave as flexible cultural traits molded by social environment, while calls remain remarkably conservative and spatially stable.

The spatial analysis sharpened this contrast. Acoustic similarity between males declined steeply with distance for both signal types, but calls were always more similar than songs at every scale examined. Neighboring males within 500 meters shared substantial portions of both repertoires, with mean song similarity of 0.48 and call similarity of 0.60, both far above random expectations. Between populations, similarity collapsed to almost nothing. Fine-scale analysis in 100-meter distance classes uncovered a telling threshold: song similarity declined steadily and leveled off beyond roughly 500 meters, while call similarity remained relatively constant up to a kilometer. Because adults disperse only about 100 to 150 meters, the wider coherence of calls hints that juveniles move at least a kilometer within their natal patches before dispersing, offering a rare behavioral clue about a life stage that has remained almost entirely invisible to researchers.

The most consequential result came from a two-decade natural experiment. The team revisited 50 populations originally monitored between 2004 and 2007, spanning most of the European range, and asked whether historical mean song repertoire size predicted population fate in 2025. A binomial logistic regression delivered a clear answer: populations with larger individual song repertoires had significantly higher persistence probabilities. Extinct populations had averaged 4.9 song types per male, compared with 5.7 in those that survived. Only one extinct population, five percent, had exceeded a mean repertoire size of 6.0, whereas 43 percent of surviving populations did, and not one of the nine populations with means above 6.25 was lost over the following twenty years. This threshold, the authors suggest, may mark the point below which extinction risk rises markedly.

The researchers are careful to note that population persistence depends on many interacting pressures, from wind farm development and grazing regimes to genetic erosion, habitat quality, and extreme weather events. Yet the strength of the acoustic signal is hard to ignore, and it validates, on a far broader geographic scale and a much longer timescale, an idea first proposed in 2008: that a cultural trait can serve as a predictor of population viability. Because vocal repertoire size can be measured non-invasively from field recordings, even with autonomous units, it offers managers a practical, low-cost indicator for tracking population health before declines become irreversible.

Beyond its conservation implications, the study fills a fundamental gap in behavioral ecology. Most research on avian vocal behavior has focused on songs and alarm calls, rarely comparing multiple signal types within the same species. By showing that songs and calls follow partially independent ecological rules, shaped by different learning schedules, dispersal stages, and social contexts, the work demonstrates how much information is layered into a dawn chorus. For a species clinging to fragmented fragments of Spanish steppe, those layers may now determine whether conservationists hear its song for decades to come, or only its echo.

Subject of Research: Acoustic communication, vocal repertoire size, and population viability of the endangered Dupont's lark

Article Title: Singing and Calling Behavior of a Threatened Passerine With Spatially Variable Vocalizations: Individual, Population and Geographic Patterns

Article References: Pérez‐Granados, C., Alonso‐Moya, C. D., Barrero, A., Sáez‐Gómez, P., Bota, G., Lahoz‐Monfort, J. J., Laiolo, P., Méndez, M., Serrano, D., Tella, J. L., Vögeli, M., & Traba, J. (2026). Singing and Calling Behavior of a Threatened Passerine With Spatially Variable Vocalizations: Individual, Population and Geographic Patterns. Ecology and Evolution, 16(9), Article e74380. https://doi.org/10.1002/ece3.74380

Image Credits: AI Generated

DOI: 10.1002/ece3.74380

Keywords: Dupont's lark, birdsong, vocal repertoire, bioacoustics, habitat fragmentation, population viability, conservation, cultural transmission, acoustic similarity, dialects, steppe birds, early-warning signal

Estrus detection is one of the most economically consequential tasks in modern dairy management. A cow that is not inseminated at the right moment misses a breeding cycle, extending the interval between calvings and reducing lifetime milk yield. Yet identifying the behavioral signs of heat in a barn holding hundreds of animals is notoriously difficult. Progesterone testing, often considered the gold standard, is costly and cannot provide continuous monitoring. Human observation, even when conducted at regular intervals, struggles against the sheer scale of a large herd and the irregular timing of behavioral onset.

Acoustic monitoring offers a tempting alternative because cows vocalize differently during estrus, and microphones can capture those changes without any invasive sampling. The challenge has always been practical: a continuous day of barn audio is dominated by machinery noise, fans, bird calls, and collisions of equipment, with only brief bursts of high-pitched cow calls embedded in the acoustic clutter. Storing and processing all of that raw audio for an entire herd quickly becomes an enormous data-management problem, and conventional lossy compression risks distorting the very timing and spectral cues that matter.

The research team, led by Jun Wang of Henan University of Science and Technology, built a custom dual-channel acoustic tag around an STM32 microcontroller. One unidirectional microphone, pressed against the cow’s neck, picks up vibrations from the animal’s own vocalizations, while a second omnidirectional microphone records airborne calls and ambient barn sound. An accelerometer tracks movement simultaneously. The waterproof device weighs 115 grams, runs for more than twelve hours per charge, and stores each audio channel on a separate memory card. Over two spring recording periods, the researchers equipped 116 Holstein cows with the tags and had experienced veterinarians score estrus behavior from ceiling-mounted surveillance video at three-hour intervals.

From 27 cows with complete 24-hour records spanning an entire estrus episode, the team catalogued vocalizations and split them by pitch. Low-pitched calls showed only a moderate association with estrus stage, with a Spearman rank correlation of 0.38, but high-pitched calls tracked the reproductive cycle far more closely, with a correlation of 0.74. During estrus, high-pitched vocalizations occurred in 99.3 percent of hourly intervals, and their mean duration more than doubled compared with the post-estrus period. Notably, first-time (primiparous) mothers were considerably more vocal than older cows, averaging about 161 seconds of high-pitched calling per hour of active vocalization versus 88 seconds for multiparous animals.

The heart of the method lies in what the authors call an enhanced SAX strategy—a reworking of the classic Symbolic Aggregate Approximation technique used in time-series mining. Each two-minute segment of audio, a window length chosen after testing alternatives and balancing correct recognition accuracy against both error rates and runtime, is transformed into a waveform image. The algorithm first normalizes the energy of every sample, then applies a gain compression whose strength varies sample by sample according to that energy. It then squeezes the waveform horizontally by dividing it into segments and keeping one representative value per segment. This dual vertical-and-horizontal compression produces 265 candidate images per window, and a selection rule based on structural similarity (SSIM) minus a penalty for average gain retains just one image per window.

The numbers behind this filtering are striking. Processing 46,080 minutes of raw audio generated more than six million temporary candidate images, from which the algorithm kept exactly 23,040 representatives. Crucially, this aggressive compression preserved the biologically relevant signal: 99.09 percent of the measured high-pitched vocalization duration survived, and a Jensen-Shannon divergence measure confirmed that the distributional change was far below the threshold that would indicate meaningful information loss. Cow calls were kept; machinery noise and birdsong were discarded.

Classification then proceeds on the retained images. A convolutional neural network with 12.8 million trainable parameters serves double duty, both assigning its own labels and providing a 512-dimensional feature embedding that feeds four additional classifiers: random forest, k-nearest neighbors, support vector machine, and XGBoost. A hard-voting scheme combines the five opinions into a single verdict for each image, and 30 consecutive image labels are aggregated into one cow-hour decision, with an hour classified as estrus when at least ten of the thirty images were flagged as high-pitched vocalization. On a pooled test set of 790 images, the ensemble correctly classified 782, achieving 98.99 percent accuracy with a 95 percent confidence interval of 98.01 to 99.49 percent, modestly outperforming every individual learner.

Timing matters as much as detection. In a same-farm comparison across 32 cows, the system’s predicted onset of estrus came before the veterinarian-reconstructed onset in 22 cases, with a mean prediction lead of roughly 89 minutes, and lagged behind in 10 cases by an average of about 28 minutes. Earlier alerts give farm staff a wider window to schedule insemination at the optimal moment, though the authors caution that the veterinary onset itself was reconstructed from three-hour observation intervals rather than minute-resolved measurements.

The researchers are careful to frame these results as an internal, single-farm evaluation. All animals were Holsteins managed under the same conditions, the image-level data split was not documented as cow-disjoint, and no external farm, breed, or climate was tested. The authors also note that dense or overlapping calls produced the highest error rates, that no measured edge-hardware benchmarks exist for the CNN, and that formal ablation studies are still needed to isolate the contribution of the gain term. Nevertheless, the framework demonstrates that a thoughtfully compressed acoustic representation can carry nearly all of the estrus-relevant information while making the data burden of continuous herd monitoring manageable, and it points toward acoustic estrus surveillance as a viable complement to accelerometers and hormonal testing in precision livestock farming.

Subject of Research: An acoustic estrus detection method for large-herd dairy cows combining enhanced SAX audio compression with heterogeneous ensemble learning

Article Title: Towards precise estrus identification of large-herd dairy cows: An acoustic detection method using enhanced SAX strategy and heterogeneous ensemble learning

Article References: Wang, J., Yue, Y., Wang, H., Aboelmaaty, A. M., Si, P., Zhao, K., Zhao, Y., & Shakweer, W. M. E.-S. (2026). Towards precise estrus identification of large-herd dairy cows: An acoustic detection method using enhanced SAX strategy and heterogeneous ensemble learning. Smart Agricultural Technology, 15, Article 102524. https://doi.org/10.1016/j.atech.2026.102524

Image Credits: AI Generated

DOI: 10.1016/j.atech.2026.102524

Keywords: dairy cows, estrus detection, acoustic monitoring, SAX compression, ensemble learning, precision livestock farming, bioacoustics, machine learning, Holstein cattle, reproductive management, wearable sensors, convolutional neural network