Low-cost open-source recorders and ready-to-use machine learning approaches provide effective monitoring of threatened species

Passive acoustic monitoring is a powerful tool for monitoring vocally active taxa. Automated signal recognition software reduces the expert time needed for recording analyses and allows researchers and managers to manage large acoustic datasets. The application of state-of-the-art techniques for automated identification, such as Convolutional Neural Networks, may be challenging for ecologists and managers without informatics or engineering expertise. Here, we evaluated the use of AudioMoth — a low-cost and open-source sound recorder — to monitor a threatened and patchily distributed species, the Eurasian bittern (Botaurus stellaris). Passive acoustic monitoring was carried out across 17 potential wetlands in north Spain. We also assessed the performance of BirdNET — an automated and freely available classifier able to identify over 3000 bird species — and Kaleidoscope Pro — a user-friendly recognition software — to detect the vocalizations and the presence of the target species. The percentage of presences and vocalizations of the Eurasian bittern automatically detected by BirdNET and Kaleidoscope Pro software was compared to manual annotations of 205 recordings. The species was effectively recorded up to distances of 801–900 m, with at least 50% of the vocalizations uttered within that distance being manually detected; this distance was reduced to 601–700 m when considering the analyses carried out using Kaleidoscope Pro. BirdNET detected the species in 59 of the 63 (93.7%) recordings with known presence of the species, while Kaleidoscope detected the bittern in 62 recordings (98.4%). At the vocalization level, BirdNet and Kaleidoscope Pro were able to detect between 76 and 78%, respectively, of the vocalizations detected by a human observer. Our study highlights the ability of AudioMoth for detecting the bittern at large distances, which increases the potential of that technique for monitoring the species at large spatial scales. According to our results, a single AudioMoth could be useful for monitoring the species' presence in wetlands of up to 150 ha. Our study proves the utility of passive acoustic monitoring, coupled with BirdNET or Kaleidoscope Pro, as an accurate, repeatable, and cost-efficient method for monitoring the Eurasian bittern at large spatial and temporal scales. Nonetheless, further research should evaluate the performance of BirdNET on a larger number of species, and under different recording conditions (e.g., more closed habitats), to improve our knowledge about BirdNET's ability to perform bird monitoring. Future studies should also aim to develop an adequate protocol to perform effective passive acoustic monitoring of the Eurasian bittern.     

基于音节聚类分析的被动声学监测技术及其在鸟类监测中的应用

被动声学监测通过分析鸟鸣声信息来实现物种识别,为鸟类多样性监测提供了一种切实可行的技术方案。由于鸟种的鸣声复杂多变,如何通过声纹快速准确辨别物种,分析鸟类丰度,降低对人工操作的需求等技术难题,成为基于声纹的鸟类多样性监测所面临的挑战。本文提出了基于音节聚类的鸟类鸣声监测框架:首先通过音高、频率平坦度等音频特征在声纹数据中提取音节,然后通过无监督表征学习与狄利克雷过程(Dirichlet process)混合模型对音节进行深度无监督聚类训练,完成音节聚类和自动音节种类推断。分析结果表明,本文提出的基于音节聚类的鸟类鸣声监测框架在处理开源数据集白腰文鸟(Lonchura striata)的曲目时可获得接近90%的聚类准确率。在此基础上,本研究对2022年4-5月在广州市白云山公园固定监测点所录制的10种鸟类鸣声进行了无监督的音节聚类分析,验证了本文所提出的基于音节聚类的鸟类鸣声监测框架的有效性:本技术不仅可以支持快速鸟类物种识别,还可以统计和分析不同物种鸟鸣在时间、频度、数量上的变化。这些结果表明,基于音节聚类的鸟类鸣声监测框架可以显著降低对人工标注训练数据的要求,克服传统鸟鸣物种识别框架...     

A low‐cost,yet simple and highly repeatable system for acoustically surveying cryptic species

Accurate determination of the population density of key focal species is necessary for monitoring the success of management programs and ecosystem health across a wide range of contexts. Unfortunately, many key taxa are visually cryptic and thus difficult to count using traditional observation‐based techniques. Bell miners (Manorina melanophrys), are just such a species. They are widespread throughout south‐eastern Australia, yet they are critical to monitor given their association and potential causal link to spreading vegetative dieback in this region. A new passive acoustic monitoring technique was trialled by testing its ability to determine population densities of bell miner colonies via counting the distinctive ‘tink’ vocalization of this species. This call was given at a constant rate per individual, and at a common amplitude across 10 colonies throughout the entire geographic range of the species. Theoretical sound transmission and playback trials through typical habitat determined that any bird within a 50‐m radius of the recorders used would be louder than 70 dB, enabling this threshold amplitude to be used to determine the number of birds in a 50 m radius of the recorder. Field trials of the acoustic protocol versus human observers using traditional visual surveys found that passive acoustic monitoring was able to detect more individuals, using a less expensive protocol that drastically reduced the need for observer training or expertise. Sound therefore offers a reliable method for determining the density of this vocal, but visually cryptic species. We present methods for calibrating recording devices and detecting calls louder than species‐specific thresholds using readily available freeware, enabling our methods to be easily adapted to census a variety of acoustically distinctive species, offering a more effective, yet lower cost and in our case more efficient census technique for surveying difficult species.     

Climate change is creating a mismatch between protected areas and suitable habitats for frogs and birds in Puerto Rico

Climate change is altering the spatial distribution of many species around the world. In response, we need to identify and protect suitable areas for a large proportion of the fauna so that they persist through time. This exercise must also evaluate the ability of existing protected areas to provide safe havens for species in the context of climate change. Here, we combined passive acoustic monitoring, semi-automatic species identification models, and species distribution models of 21 bird and frog species based on past (1980–1989), present (2005–2014), and future (2040–2060) climate scenarios to determine how species distributions relate to the current distribution of protected areas in Puerto Rico. Species detection/non-detection data were acquired across?~?700 sampling sites. We developed always-suitable maps that characterized suitable habitats in all three time periods for each species and overlaid these maps to identify regions with high species co-occurrence. These distributions were then compared with the distribution of existing protected areas. We show that Puerto Rico is projected to become dryer by 2040–2060, and precipitation in the warmest quarter was among the most important variables affecting bird and frog distributions. A large portion of always-suitable areas (ASA) is outside of protected areas (>?80%), and the percent of protected areas that overlaps with always-suitable areas is larger for bird (75%) than frog (39%) species. Our results indicate that present protected areas will not suffice to safeguard bird and frog species under climate change; however, the establishment of larger protected areas, buffer zones, and connectivity between protected areas may allow species to find suitable niches to withstand environmental changes.

     

Do acoustic indices correlate with bird diversity? Insights from two biodiverse regions in Yunnan Province,south China

Human activities are affecting biodiversity to a greater extent than ever. Consequently, tools that can efficiently monitor changes in communities are becoming increasingly important. In the case of birds and other vocalizing animals, it has been suggested that passive acoustic methods can be used for this purpose. Multiple acoustic indices have been developed recently, to be used as proxies for species diversity. Preliminary results have been promising. Yet, before the indices can be applied widely, it is necessary to understand better how well they reflect the communities to be monitored, and how they perform under diverse environmental conditions. Here, we tested seven of the available indices, on sound recordings made in two biodiverse regions in Yunnan Province, south China. We assessed each index’s performance by measuring its correlation to bird species richness and diversity, estimated using point-count surveys. Each survey was conducted by an expert observer, at the same time each recording was made, and for the same duration. We also tested whether the performance of the indices was affected by levels of environmental dissimilarity between the sites sampled. We found that although no index showed a very strong correlation with species richness or diversity, three indices (the acoustic entropy, acoustic diversity and acoustic evenness indices) performed consistently better that the other four, showing moderate correlations. The levels of environmental dissimilarity among the sites did not seem to affect the performance of any of the indices tested, suggesting consistency − an important property for the indices to have. We conclude that although the acoustic indices have the potential to be used for passive acoustic monitoring, perhaps they need to be refined further before they can be applied widely. Meanwhile, they should be tested in more environments to reveal fully their potential and limitations.     

Acoustic activity across a seabird colony reflects patterns of within-colony flight rather than nest density

Passive acoustic monitoring is increasingly being used as a cost-effective way to study wildlife populations, especially those that are difficult to census using conventional methods. Burrow-nesting seabirds are among the most threatened birds globally, but they are also one of the most challenging taxa to census, making them prime candidates for research into such automated monitoring platforms. Passive acoustic monitoring has the potential to determine presence/absence or quantify burrow-nesting populations, but its effectiveness remains unclear. We compared passive acoustic monitoring, tape-playbacks and GPS tracking data to investigate the ability of passive acoustic monitoring to capture unbiased estimates of within-colony variation in nest density for the Manx Shearwater Puffinus puffinus. Variation in acoustic activity across 12 study plots on an island colony was examined in relation to burrow density and environmental factors across 2 years. As predicted fewer calls were recorded when wind speed was high, and on moon-lit nights, but there was no correlation between acoustic activity and the density of breeding birds within the plots as determined by tape-playback surveys. Instead, acoustic indices correlated positively with spatial variation in the in-colony flight activity of breeding individuals detected by GPS. Although passive acoustic monitoring has enormous potential in avian conservation, our results highlight the importance of understanding behaviour when using passive acoustic monitoring to estimate density and distribution.     

Acoustic region workflow for efficient comparison of soundscapes under different invasive mammals' management regimes

One quarter of all terrestrial native bird species have become extinct since human arrival in New Zealand, leading to a pervasive silence in many natural environments due to the decrease in native bird song. Passive acoustic techniques are a potential tool for environmental monitoring, especially for testing whether the control of mammals can reverse the ‘silent forest’ effect. Here we compare soundscapes from two nearby sites within the Waitakere Ranges Regional Park, New Zealand, that have contrasting predator control levels: one with high-level pest mammal control, and the other with low-level pest control. Measurements of twelve acoustic indices extracted from two seasons of passive acoustic recordings are split into 20 acoustic regions to identify which regions best discriminate between the two management regimes. We define the acoustic regions as units of analysis bounded by a specific time period and frequency range chosen to capture the main groups of biologically relevant acoustic events within a soundscape. Analysis of variance and pairwise comparisons indicated the acoustic region bounded from 9 pm to 11:59 pm and a range of 0.988–3.609 kHz in autumn presented the greatest differences between sites. The sounds responsible for these acoustic differences were generated by invasive mammals in the site with no pest control. Results also supports spring season as the most important for bird monitoring in New Zealand. Acoustic indices analysis did not detect a reversal of the “silence forest” effect in the site with high-level predator control.     

Western Mediterranean Wetland Birds dataset: A new annotated dataset for acoustic bird species classification

The deployment of an expert system running over a wireless acoustic sensors network made up of bioacoustic monitoring devices that recognize bird species from their sounds would enable the automation of many tasks of ecological value, including the analysis of bird population composition or the detection of endangered species in areas of environmental interest. Endowing these devices with accurate audio classification capabilities is possible thanks to the latest advances in artificial intelligence, among which deep learning techniques stand out. To train such algorithms, data from the sources to be classified is required. For this reason, this paper presents the Western Mediterranean Wetland Birds (WMWB) dataset, consisting of 201.6 min and 5795 annotated audio excerpts of 20 endemic bird species of the Aiguamolls de l'Empordà Natural Park. The main objective of this work is to describe and analyze this new dataset. Moreover, this work presents the results of bird species classification experiments using four well- known deep neural networks fine-tuned on our dataset, whose models are also made public along with the dataset. These results are aimed to serve as a performance baseline reference for the community when using the WMWB dataset for their experiments.     

Classifying and ranking audio clips to support bird species richness surveys

Advances in programmable field acoustic sensors provide immense data for bird species study. Manually searching for bird species present in these acoustic data is time-consuming. Although automated techniques have been used for species recognition in many studies, currently these techniques are prone to error due to the complexity of natural acoustics.In this paper we propose a smart sampling approach to help identify the maximum number of bird species while listening to the minimum amount of acoustic data. This approach samples audio clips in a manner that can direct bird species surveys more efficiently. First, a classifier is built to remove audio clips that are unlikely to contain birds; second, the remaining audio clips are ranked by a proxy for the number of species. This technique enables a more efficient determination of species richness.The experimental results show that the use of a classifier enables to remove redundant acoustic data and make our approach resilient to various weather conditions. By ranking audio clips classified as “Birds”, our method outperforms the currently best published strategy for finding bird species after 30 one-minute audio clip samples. Particularly after 60 samples, our method achieves 10 percentage points more species. Despite our focus on bird species, the proposed sampling approach is applicable to the search of other vocal species.     

Climate change, phenology and species detectability in a monitoring scheme

The knowledge of the state of biodiversity on the globe is based on a large number of monitoring schemes. Quite often the results of these schemes are sensitive to the timing of monitoring due to the phenology of species, which in turn may affect the detectability of species during censuses. As global warming has been shown to cause changes in phenology, there is an increasing risk that species detectability will be altered if the timing of monitoring is not adapted to this change. I tested how sensitive species detectability is to the timing of censuses and whether there are potential climate-driven temporal changes in the detectability of 73 Finnish land bird species monitored using single-visit line-transects in 1987–2010. This was done by investigating seasonal and annual patterns in the proportion of birds in the main belt and those detected by displaying activity. Over 20 of the study species showed significant changes in detectability within the census season. However, only three species showed a significant trend in annual detectability. According to multi-species analyses there was a slight but significant increasing trend in the proportion of displaying birds and a slight decreasing trend in the proportion of birds in the main belt. However, the observed species-specific annual changes in displaying activity or in proportion of birds in main belt were not associated with the observed population trends of species during the same period. Nevertheless, the findings highlight a strong potential risk that species detectability can change if climate change escalates in the future. I recommend researchers to investigate how sensitive their monitoring systems are for phenological changes and prepare tools for taking potential changes in detectability into account.     

Vocal activity rate index: a useful method to infer terrestrial bird abundance with acoustic monitoring

Autonomous recording units have been widely used in a large number of bird studies in recent years, but challenges remain in estimating abundance based on acoustic monitoring. We tested whether vocal activity rate index (VAR; the number of songs per unit time for a species), recorded using autonomous recording units, was related to population abundance in two terrestrial bird species, the European Bee‐eater Merops apiaster and the Dupont's Lark Chersophilus duponti. We took recordings at sites where censuses were also carried out to estimate local populations around recorders. We found a positive and significant relationship for the two monitored species. Although our results are not conclusive, the strong and significant relationship found for both monitored species suggests that VAR may be used to infer bird abundance around recorders in terrestrial species. We describe five logical steps for using the VAR with autonomous recording units in other species to guide future studies.     

Automatic Classification of a Taxon-Rich Community Recorded in the Wild

There is a rich literature on automatic species identification of a specific target taxon as regards various vocalizing animals. Research usually is restricted to specific species – in most cases a single one. It is only very recently that the number of monitored species has started to increase for certain habitats involving birds. Automatic acoustic monitoring has not yet been proven to be generic enough to scale to other taxa and habitats than the ones described in the original research. Although attracting much attention, the acoustic monitoring procedure is neither well established yet nor universally adopted as a biodiversity monitoring tool. Recently, the multi-instance multi-label framework on bird vocalizations has been introduced to face the obstacle of simultaneously vocalizing birds of different species. We build on this framework to integrate novel, image-based heterogeneous features designed to capture different aspects of the spectrum. We applied our approach to a taxon-rich habitat that included 78 birds, 8 insect species and 1 amphibian. This dataset constituted the Multi-label Bird Species Classification Challenge-NIPS 2013 where the proposed approach achieved an average accuracy of 91.25% on unseen data.     

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.     

Soundscape diversity in the Great Barrier Reef: Lizard Island,a case study

Passive acoustic monitoring can provide valuable information on coral reefs, and examining the acoustic attributes of these ecosystems has the potential to provide an insight into their status and condition. From 2014 to 2016, a series of underwater recordings were taken at field sites around Lizard Island in the Great Barrier Reef, Australia. Six individual fish choruses were identified where each chorus displayed distinct acoustic characteristics. Choruses exhibited diurnal activity and some field sites displayed consistently higher diversity of choruses and levels than others, suggesting that particular locations are important aggregation areas for soniferous fish species. During peak activity, choruses were a prominent component of reef soundscapes, where received levels of a chorus reached upwards of 120 dB re 1μPa rms over the 450–650 Hz band, equating to a 40 dB increase above ambient noise levels of ≈80 dB re 1μPa rms. Three out of the six detected choruses exhibited spectral and temporal characteristics similar to choruses previously documented at these sites and elsewhere, produced by planktivorous fish species. Three of these choruses appear to be undocumented and could hold information on the presence, abundance and dispersal patterns of important fish species, which may have potential long-term management applications. Future research should focus on extricating the temporal patterns associated with bioacoustic activity and determining the potential environmental drivers of biological choruses. Additionally, developing appropriate techniques for direct identification of vocalizing species would strongly increase the management applicability of passive acoustic monitoring.     

声学指数在城市森林鸟类多样性评估中的应用

鸣声是鸟类之间进行沟通和传递信息的重要方式,这为通过声学监测评估鸟类多样性提供了独特的机会。利用声学指数快速评估生物多样性是一种新兴的调查方法,但城市森林中的复杂声环境可能会导致声学指数的指示结果出现偏差。为了解声学指数在城市森林中应用的可行性,本研究在北京市东郊森林公园设置了50个矩阵式调查样点,于2021年4–6月每月进行1次鸟类传统观测和同步鸣声采集,通过比较两种方法的结果来探究声学监测的有效性。采用Spearman相关分析和广义线性混合模型评估6个常用声学指数与鸟类丰富度和多度的关系,并衡量了每个指数的性能。结果表明:(1)本研究共记录到鸟类10目23科35种,通过声学监听识别的总物种数与传统鸟类观测相等,但具体鸟种存在差异;(2)不同月份间声学指数与鸟类丰富度和多度的相关性有明显差别,声学复杂度指数(ACI)和标准化声景差异指数(NDSI)优于其他指数,是评估鸟类多样性的关键变量;(3)声学指数对鸟类多度的预测能力(R²m=0.32,R2c=0.80)要高于丰富度(R²m=0.12,R2c=0.18)。声学指数为快速评估生物多样性提...     

Handling dolphin detections from C-PODs,with the development of acoustic parameters for verification and the exploration of species identification possibilities

C-PODs are static passive acoustic monitoring devices used to detect odontocete vocalizations in the range of 20–160 kHz. However, falsely classified detections may be an issue, particularly with broadband species (i.e. many dolphin species) due to anthropogenic and other noise occurring at the same frequency. While porpoise detections are verified using species-specific acoustic parameters, the equivalent does not currently exist for verifying dolphin detections. Development of such parameters would increase the accuracy of dolphin detections and eliminate the need for additional monitoring techniques or devices, reducing the cost of monitoring programmes. Herein, we present parameters based on acoustic characteristics of bottlenose (n = 29), common (n = 19) and Risso’s (n = 99) dolphin click trains, sighted within 1 km of C-PODs during land-based surveys, for in-software verification. Overlap of click train parameters among dolphin species prevented robust species identification; therefore, parameters were devised for these dolphin species collectively using frequency, inter-click interval and click train duration. A data set of 4898 Detection Positive Hours was visually verified using these parameters. The temporal and spatial patterns in the visually verified data were similar to land-based observations, suggesting the parameters operate at an acceptable accuracy. However, 68% of high-, moderate- and low-quality KERNO detections were false-positive. Our results suggest that the accuracy of classifiers and quality class weightings are site-specific, and we highlight the importance of data exploration to make the most appropriate software choices based on the aims of a study.     

Automatic classification of Furnariidae species from the Paranaense Littoral region using speech-related features and machine learning

Over the last years, researchers have addressed the automatic classification of calling bird species. This is important for achieving more exhaustive environmental monitoring and for managing natural resources. Vocalisations help to identify new species, their natural history and macro-systematic relations, while computer systems allow the bird recognition process to be sped up and improved. In this study, an approach that uses state-of-the-art features designed for speech and speaker state recognition is presented. A method for voice activity detection was employed previous to feature extraction. Our analysis includes several classification techniques (multilayer perceptrons, support vector machines and random forest) and compares their performance using different configurations to define the best classification method. The experimental results were validated in a cross-validation scheme, using 25 species of the family Furnariidae that inhabit the Paranaense Littoral region of Argentina (South America). The results show that a high classification rate, close to 90%, is obtained for this family in this Furnariidae group using the proposed features and classifiers.     

Automatic recognition of bird individuals on an open set using as-is recordings

The most common method used to determine the identity of an individual bird is the capture-mark-recapture technique. The method has several major disadvantages, e.g. some species are difficult to capture/recapture and the capturing process itself may cause significant stress in animals leading even to injuries of more vulnerable species. Some studies introduce systems based on methods used for human identification. An automatic system for recognition of bird individuals (ASRBI) described in this article is based on a Gaussian mixture model (GMM) and a universal background model (GMM-UBM) method extended by an advanced voice activity detection (VAD) algorithm. It is focused on recognizing the bird individuals on an open set, i.e. any number of unknown birds may appear anytime during the identification process as is common in nature. The introduced ASRBI processes the recordings just as if they were recorded by an ornithologist: with durations from seconds to minutes, containing noise and unwanted sounds, as well as masking of the singer, etc. Thanks to the VAD algorithm, the proposed system is fully automatic, no manual pre-processing of recordings is needed, neither by cutting off the songs nor syllables. The overall achieved identification accuracy is 78.5%, the lowest 60.3% and the highest 95.7%. In total, 90% of all experiments reach at least 70% accuracy. The result suggests the application of the GMM-UBM with VAD is feasible for individual identification on the open set processing real-life recordings. The described method is capable of reducing both the time consumption and human intervention in animal monitoring projects.     

Comparing population trend estimates of migratory birds from breeding censuses and capture data at a spring migration bottleneck

Europe has a well‐established network of breeding bird monitoring that is used to produce supranational indices of population trends for many species. However, a comparison of breeding bird censuses with other methods may be beneficial to confirm the validity of such indices. The aim of this study was to assess the value of standardized capture data of migratory birds at migration bottlenecks as an indicator of the effective breeding populations. One limitation to this method is that several populations are co‐occurring at these bottlenecks and their catchment areas need to be clearly identified to allow extrapolation of population indices. Here, we used standardized trends in capture numbers of 30 species on the island of Ponza, a migration bottleneck in the central Mediterranean, and compared them to population trends estimated in the putative catchment breeding areas between 2005 and 2016. The catchment areas were identified through the analysis of ring recoveries during the breeding season of birds passing through Ponza. Our results show an agreement between the population trends observed on Ponza and those in the breeding areas in 15 out of 30 species. The correlations were strongest in species with a more robust definition of the catchment areas, that is, species with more than 10 recoveries, and for which the recoveries were most likely of breeding birds. The main reason for disagreement between the two indices in the remaining species might be related to different intensity of sampling in different areas. This issue can be solved by further developing monitoring projects in underrepresented countries, as well as by intensifying monitoring through ringing, both in the breeding grounds and at migration bottlenecks. These results show that spring migration monitoring at bottlenecks has the potential to provide a valuable complement and an independent control of breeding bird surveys, allowing raising early warnings of population declines and contributing to their conservation.