Automated bioacoustics: methods in ecology and conservation and their potential for animal welfare monitoring

LIES of omission: complex observation processes in ecology

Advances in statistics mean that it is now possible to tackle increasingly sophisticated observation processes. The intricacies and ambitious scale of modern data collection techniques mean that this is now essential. Methodological research to make inference about the biological process while accounting for the observation process has expanded dramatically, but solutions are often presented in field-specific terms, limiting our ability to identify commonalities between methods. We suggest a typology of observation processes that could improve translation between fields and aid methodological synthesis. We propose the LIES framework (defining observation processes in terms of issues of Latency, Identifiability, Effort and Scale) and illustrate its use with both simple examples and more complex case studies.

Utilizing vocalizations to gain insight into the affective states of non-human mammals

This review discusses how welfare scientists can examine vocalizations to gain insight into the affective states of individual animals. In recent years, researchers working in professionally managed settings have recognized the value of monitoring the types, rates, and acoustic structures of calls, which may reflect various aspects of welfare. Fortunately, recent technological advances in the field of bioacoustics allow for vocal activity to be recorded with microphones, hydrophones, and animal-attached devices (e.g., collars), as well as automated call recognition. We consider how vocal behavior can be used as an indicator of affective state, with particular interest in the valence of emotions. While most studies have investigated vocal activity produced in negative contexts (e.g., experiencing pain, social isolation, environmental disturbances), we highlight vocalizations that express positive affective states. For instance, some species produce vocalizations while foraging, playing, engaging in grooming, or interacting affiliatively with conspecifics. This review provides an overview of the evidence that exists for the construct validity of vocal indicators of affective state in non-human mammals. Furthermore, we discuss non-invasive methods that can be utilized to investigate vocal behavior, as well as potential limitations to this line of research. In the future, welfare scientists should attempt to identify reliable, valid species-specific calls that reflect emotional valence, which may be possible by adopting a dimensional approach. The dimensional approach considers both arousal and valence by comparing vocalizations emitted in negative and positive contexts. Ultimately, acoustic activity can be tracked continuously to detect shifts in welfare status or to evaluate the impact of animal transfers, introductions, and changes to the husbandry routine or environment. We encourage welfare scientists to expand their welfare monitoring toolkits by combining vocal activity with other behavioral measures and physiological biomarkers.

BovineTalk: machine learning for vocalization analysis of dairy cattle under the negative affective state of isolation

There is a critical need to develop and validate non-invasive animal-based indicators of affective states in livestock species, in order to integrate them into on-farm assessment protocols, potentially via the use of precision livestock farming (PLF) tools. One such promising approach is the use of vocal indicators. The acoustic structure of vocalizations and their functions were extensively studied in important livestock species, such as pigs, horses, poultry, and goats, yet cattle remain understudied in this context to date. Cows were shown to produce two types of vocalizations: low-frequency calls (LF), produced with the mouth closed, or partially closed, for close distance contacts, and open mouth emitted high-frequency calls (HF), produced for long-distance communication, with the latter considered to be largely associated with negative affective states. Moreover, cattle vocalizations were shown to contain information on individuality across a wide range of contexts, both negative and positive. Nowadays, dairy cows are facing a series of negative challenges and stressors in a typical production cycle, making vocalizations during negative affective states of special interest for research. One contribution of this study is providing the largest to date pre-processed (clean from noises) dataset of lactating adult multiparous dairy cows during negative affective states induced by visual isolation challenges. Here, we present two computational frameworks-deep learning based and explainable machine learning based, to classify high and low-frequency cattle calls and individual cow voice recognition. Our models in these two frameworks reached 87.2 and 89.4% accuracy for LF and HF classification, with 68.9 and 72.5% accuracy rates for the cow individual identification, respectively.

Capturing wild animal welfare: a physiological perspective

Affective states, such as emotions, are presumably widespread across the animal kingdom because of the adaptive advantages they are supposed to confer. However, the study of the affective states of animals has thus far been largely restricted to enhancing the welfare of animals managed by humans in non-natural contexts. Given the diversity of wild animals and the variable conditions they can experience, extending studies on animal affective states to the natural conditions that most animals experience will allow us to broaden and deepen our general understanding of animal welfare. Yet, this same diversity makes examining animal welfare in the wild highly challenging. There is therefore a need for unifying theoretical frameworks and methodological approaches that can guide researchers keen to engage in this promising research area. The aim of this article is to help advance this important research area by highlighting the central relationship between physiology and animal welfare and rectify its apparent oversight, as revealed by the current scientific literature on wild animals. Moreover, this article emphasises the advantages of including physiological markers to assess animal welfare in the wild (e.g. objectivity, comparability, condition range, temporality), as well as their concomitant limitations (e.g. only access to peripheral physiological markers with complex relationships with affective states). Best-practice recommendations (e.g. replication and multifactorial approaches) are also provided to allow physiological markers to be used most effectively and appropriately when assessing the welfare of animals in their natural habitat. This review seeks to provide the foundation for a new and distinct research area with a vast theoretical and applied potential: wild animal welfare physiology.

Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion

To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.

Groundwater is a hidden global keystone ecosystem

Groundwater is a vital ecosystem of the global water cycle, hosting unique biodiversity and providing essential services to societies. Despite being the largest unfrozen freshwater resource, in a period of depletion by extraction and pollution, groundwater environments have been repeatedly overlooked in global biodiversity conservation agendas. Disregarding the importance of groundwater as an ecosystem ignores its critical role in preserving surface biomes. To foster timely global conservation of groundwater, we propose elevating the concept of keystone species into the realm of ecosystems, claiming groundwater as a keystone ecosystem that influences the integrity of many dependent ecosystems. Our global analysis shows that over half of land surface areas (52.6%) has a medium-to-high interaction with groundwater, reaching up to 74.9% when deserts and high mountains are excluded. We postulate that the intrinsic transboundary features of groundwater are critical for shifting perspectives towards more holistic approaches in aquatic ecology and beyond. Furthermore, we propose eight key themes to develop a science-policy integrated groundwater conservation agenda. Given ecosystems above and below the ground intersect at many levels, considering groundwater as an essential component of planetary health is pivotal to reduce biodiversity loss and buffer against climate change.

Review: Using animal welfare to frame discussion on dairy farm technology

The use of technology on dairy farms has increased dramatically over the last half-century. The ways that scientists describe the potential benefits and risk of technology are likely to affect if it is accepted for use on farms. The aim of our study was to identify papers that describe a linkage between technologies used on dairy farms and the welfare of dairy cattle. Our systematic review identified 380 papers, of which 28 met our inclusion criteria and were used to describe the technologies examined, the welfare-relevant measures used, and the ways in which authors framed welfare benefits and risks associated with the technologies. The large majority (27 of 28 papers) used positive frames, considering how the technology could improve welfare. Some authors carefully articulated the logic linking the specific measures to specific welfare-related outcomes (such as the use of accelerometer data to draw inferences about changes in lying times), but others made more general inferences (about health and welfare) that were not (and perhaps could not) be assessed. We conclude that much of the framing focused on animal welfare is biased toward welfare benefits and that future work should strive to address both potential benefits and harms; more balanced coverage may better inform solutions to the problems encountered by the people and animals affected by the technology. Welfare is a complex and multifaced concept, and it is unlikely that any one technology (or perhaps even a combination of technologies) can adequately capture this complexity. Thus, we encourage authors to restrict their claims to specific, welfare-relevant measures that can be assessed independently and thus validated. More general claims about welfare should be treated with skepticism.

Acoustic Monitoring of Professionally Managed Marine Mammals for Health and Welfare Insights

Research evaluating marine mammal welfare and opportunities for advancements in the care of species housed in a professional facility have rapidly increased in the past decade. While topics, such as comfortable housing, adequate social opportunities, stimulating enrichment, and a high standard of medical care, have continued to receive attention from managers and scientists, there is a lack of established acoustic consideration for monitoring the welfare of these animals. Marine mammals rely on sound production and reception for navigation and communication. Regulations governing anthropogenic sound production in our oceans have been put in place by many countries around the world, largely based on the results of research with managed and trained animals, due to the potential negative impacts that unrestricted noise can have on marine mammals. However, there has not been an established best practice for the acoustic welfare monitoring of marine mammals in professional care. By monitoring animal hearing and vocal behavior, a more holistic view of animal welfare can be achieved through the early detection of anthropogenic sound sources, the acoustic behavior of the animals, and even the features of the calls. In this review, the practice of monitoring cetacean acoustic welfare through behavioral hearing tests and auditory evoked potentials (AEPs), passive acoustic monitoring, such as the Welfare Acoustic Monitoring System (WAMS), as well as ideas for using advanced technologies for utilizing vocal biomarkers of health are introduced and reviewed as opportunities for integration into marine mammal welfare plans.

Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls

Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings, most often noisy, and unbalanced in number between the individuals or categories of vocalizations. SUNG datasets therefore offer a valuable but inevitably distorted vision of communication systems. Adopting the best practices in their analysis is essential to effectively extract the available information and draw reliable conclusions. Here we show that the most recent advances in machine learning applied to a SUNG dataset succeed in unraveling the complex vocal repertoire of the bonobo, and we propose a workflow that can be effective with other animal species. We implement acoustic parameterization in three feature spaces and run a Supervised Uniform Manifold Approximation and Projection (S-UMAP) to evaluate how call types and individual signatures cluster in the bonobo acoustic space. We then implement three classification algorithms (Support Vector Machine, xgboost, neural networks) and their combination to explore the structure and variability of bonobo calls, as well as the robustness of the individual signature they encode. We underscore how classification performance is affected by the feature set and identify the most informative features. In addition, we highlight the need to address data leakage in the evaluation of classification performance to avoid misleading interpretations. Our results lead to identifying several practical approaches that are generalizable to any other animal communication system. To improve the reliability and replicability of vocal communication studies with SUNG datasets, we thus recommend: i) comparing several acoustic parameterizations; ii) visualizing the dataset with supervised UMAP to examine the species acoustic space; iii) adopting Support Vector Machines as the baseline classification approach; iv) explicitly evaluating data leakage and possibly implementing a mitigation strategy.

Glucocorticoids in relation to behavior, morphology, and physiology as proxy indicators for the assessment of animal welfare. A systematic mapping review

Translating theoretical concepts of animal welfare into quantitative assessment protocols is an ongoing challenge. Glucocorticoids (GCs) are frequently used as physiological measure in welfare assessment. The interpretation of levels of GCs and especially their relation to welfare, however, is not as straightforward, questioning the informative power of GCs. The aim of this systematic mapping review was therefore to provide an overview of the relevant literature to identify global patterns in studies using GCs as proxy for the assessment of welfare of vertebrate species. Following a systematic protocol and a-priory inclusion criteria, 509 studies with 517 experiments were selected for data extraction. The outcome of the experiments was categorized based on whether the intervention significantly affected levels of GCs, and whether these effects were accompanied by changes in behavior, morphology and physiology. Additional information, such as animal species, type of intervention, experimental set up and sample type used for GC determination was extracted, as well. Given the broad scope and large variation in included experiments, meta-analyses were not performed, but outcomes are presented to encourage further, in-depth analyses of the data set. The interventions did not consistently lead to changes in GCs with respect to the original authors hypothesis. Changes in GCs were not consistently paralleled by changes in additional assessment parameter on behavior, morphology and physiology. The minority of experiment quantified GCs in less invasive sample matrices compared to blood. Interventions showed a large variability, and species such as fish were underrepresented, especially in the assessment of behavior. The inconclusive effects on GCs and additional assessment parameter urges for further validation of techniques and welfare proxies. Several conceptual and technical challenges need to be met to create standardized and robust welfare assessment protocols and to determine the role of GCs herein.

Energy Assessment from Broiler Chicks' Vocalization Might Help Improve Welfare and Production

Vocalization seems to be a viable source of signal for assessing broiler welfare. However, it may require an understanding of the birds' signals, both quantitatively and qualitatively. The delivery of calls with a specific set of acoustic features must be understood to assess the broiler's well-being. The present study aimed to analyze broiler chick vocalization through the sounds emitted during social isolation and understand what would be the flock size where the chicks present the smallest energy loss in vocalizing. The experiments were carried out during the first 3 days of growth, and during the trial, chicks received feed and water ad libitum. A total of 30 1-day-old chicks Cobb^® breed were acquired at a commercial hatching unit. The birds were tested from 1 to 3 days old. A semi-anechoic chamber was used to record the vocalization with a unidirectional microphone connected to a digital recorder. We placed a group of 15 randomly chosen chicks inside the chamber and recorded the peeping sound, and the assessment was conducted four times with randomly chosen birds. We recorded the vocalization for 2 min and removed the birds sequentially stepwise until only one bird was left inside the semi-anechoic chamber. Each audio signal recorded during the 40 s was chosen randomly for signal extraction and analysis. Fast Fourier transform (FFT) was used to extract the acoustic features and the energy emitted during the vocalization. Using data mining, we compared three classification models to predict the rearing condition (classes distress and normal). The results show that birds' vocalization differed when isolated and in a group. Results also indicate that the energy spent in vocalizing varies depending on the size of the flock. When isolated, the chicks emit a high-intensity sound, "alarm call", which uses high energy. In contrast, they spent less energy when flocked in a group, indicating good well-being when the flock was 15 chicks. The weight of birds influenced the amount of signal energy. We also found that the most effective classifier model was the Random Forest, with an accuracy of 85.71%, kappa of 0.73, and cross-entropy of 0.2.

Occupational Safety and Health with Technological Developments in Livestock Farms: A Literature Review

In recent decades, there have been considerable technological developments in the agriculture sector to automate manual processes for many factors, including increased production demand and in response to labor shortages/costs. We conducted a review of the literature to summarize the key advances from installing emerging technology and studies on robotics and automation to improve agricultural practices. The main objective of this review was to survey the scientific literature to identify the uses of these new technologies in agricultural practices focusing on new or reduced occupational safety risks affecting agriculture workers. We screened 3248 articles with the following criteria: (1) relevance of the title and abstract with occupational safety and health; (2) agriculture technologies/applications that were available in the United States; (3) written in English; and (4) published 2015-2020. We found 624 articles on crops and harvesting and 80 articles on livestock farming related to robotics and automated systems. Within livestock farming, most (78%) articles identified were related to dairy farms, and 56% of the articles indicated these farms were using robotics routinely. However, our review revealed gaps in how the technology has been evaluated to show the benefits or potential hazards to the safety and well-being of livestock owners/operators and workers.

Towards the fully automated monitoring of ecological communities

High-resolution monitoring is fundamental to understand ecosystems dynamics in an era of global change and biodiversity declines. While real-time and automated monitoring of abiotic components has been possible for some time, monitoring biotic components-for example, individual behaviours and traits, and species abundance and distribution-is far more challenging. Recent technological advancements offer potential solutions to achieve this through: (i) increasingly affordable high-throughput recording hardware, which can collect rich multidimensional data, and (ii) increasingly accessible artificial intelligence approaches, which can extract ecological knowledge from large datasets. However, automating the monitoring of facets of ecological communities via such technologies has primarily been achieved at low spatiotemporal resolutions within limited steps of the monitoring workflow. Here, we review existing technologies for data recording and processing that enable automated monitoring of ecological communities. We then present novel frameworks that combine such technologies, forming fully automated pipelines to detect, track, classify and count multiple species, and record behavioural and morphological traits, at resolutions which have previously been impossible to achieve. Based on these rapidly developing technologies, we illustrate a solution to one of the greatest challenges in ecology: the ability to rapidly generate high-resolution, multidimensional and standardised data across complex ecologies.

A Review of Automated Bioacoustics and General Acoustics Classification Research

Automated bioacoustics classification has received increasing attention from the research community in recent years due its cross-disciplinary nature and its diverse application. Applications in bioacoustics classification range from smart acoustic sensor networks that investigate the effects of acoustic vocalizations on species to context-aware edge devices that anticipate changes in their environment adapt their sensing and processing accordingly. The research described here is an in-depth survey of the current state of bioacoustics classification and monitoring. The survey examines bioacoustics classification alongside general acoustics to provide a representative picture of the research landscape. The survey reviewed 124 studies spanning eight years of research. The survey identifies the key application areas in bioacoustics research and the techniques used in audio transformation and feature extraction. The survey also examines the classification algorithms used in bioacoustics systems. Lastly, the survey examines current challenges, possible opportunities, and future directions in bioacoustics.

Dither: A unifying model of the effects of visitor numbers on zoo animal behavior

Interest in the impact of human presence on the behavior and well-being of zoo and aquarium animals is increasing. Previous work has conceptualized the presence of zoo visitors as having one of three impacts on the behavior of animals in zoos: positive, negative, or neutral. Research suggests the same species may exhibit all three responses under different conditions, calling into question whether the positive/negative/neutral framework is the most useful way of considering visitor impact on animal behavior. Here we present a model of visitor effects that unifies these three predictions. Our model suggests that zoo-goers may provide a "dither effect" for some animals living in zoos. We posit animals may show nonlinear behavioral responses over a range of visitor densities, effectively exhibiting changes in both comfortable and anxiety-like behaviors under different levels of human presence. We tested this model during two COVID-19 related closures at the San Francisco Zoo, studying seven species for evidence of nonlinear relationships between visitor numbers and animal behavior. Our results support the dither effect acting in several species observed.

Introducing the Software CASE (Cluster and Analyze Sound Events) by Comparing Different Clustering Methods and Audio Transformation Techniques Using Animal Vocalizations

Simple Summary

Unsupervised clustering algorithms are widely used in ecology and conservation to classify animal vocalizations, but also offer various advantages in basic research, contributing to the understanding of acoustic communication. Nevertheless, there are still some challenges to overcome. For instance, the quality of the clustering result depends on the audio transformation technique previously used to adjust the audio data. Moreover, it is difficult to verify the reliability of the clustering result. To analyze bioacoustic data using a clustering algorithm, it is, therefore, essential to select a reasonable algorithm from the many existing algorithms and prepare the recorded vocalizations so that the resulting values characterize a vocalization as accurately as possible. Frequency-modulated vocalizations, whose frequencies change over time, pose a particular problem. In this paper, we present the software CASE, which includes various clustering methods and provides an overview of their strengths and weaknesses concerning the classification of bioacoustic data. This software uses a multidimensional feature-extraction method to achieve better clustering results, especially for frequency-modulated vocalizations.

Abstract

Unsupervised clustering algorithms are widely used in ecology and conservation to classify animal sounds, but also offer several advantages in basic bioacoustics research. Consequently, it is important to overcome the existing challenges. A common practice is extracting the acoustic features of vocalizations one-dimensionally, only extracting an average value for a given feature for the entire vocalization. With frequency-modulated vocalizations, whose acoustic features can change over time, this can lead to insufficient characterization. Whether the necessary parameters have been set correctly and the obtained clustering result reliably classifies the vocalizations subsequently often remains unclear. The presented software, CASE, is intended to overcome these challenges. Established and new unsupervised clustering methods (community detection, affinity propagation, HDBSCAN, and fuzzy clustering) are tested in combination with various classifiers (k-nearest neighbor, dynamic time-warping, and cross-correlation) using differently transformed animal vocalizations. These methods are compared with predefined clusters to determine their strengths and weaknesses. In addition, a multidimensional data transformation procedure is presented that better represents the course of multiple acoustic features. The results suggest that, especially with frequency-modulated vocalizations, clustering is more applicable with multidimensional feature extraction compared with one-dimensional feature extraction. The characterization and clustering of vocalizations in multidimensional space offer great potential for future bioacoustic studies. The software CASE includes the developed method of multidimensional feature extraction, as well as all used clustering methods. It allows quickly applying several clustering algorithms to one data set to compare their results and to verify their reliability based on their consistency. Moreover, the software CASE determines the optimal values of most of the necessary parameters automatically. To take advantage of these benefits, the software CASE is provided for free download.

From Soundwave to Soundscape: A Guide to Acoustic Research in Captive Animal Environments

Sound is a complex feature of all environments, but captive animals' soundscapes (acoustic scenes) have been studied far less than those of wild animals. Furthermore, research across farms, laboratories, pet shelters, and zoos tends to focus on just one aspect of environmental sound measurement: its pressure level or intensity (in decibels). We review the state of the art of captive animal acoustic research and contrast this to the wild, highlighting new opportunities for the former to learn from the latter. We begin with a primer on sound, aimed at captive researchers and animal caregivers with an interest (rather than specific expertise) in acoustics. Then, we summarize animal acoustic research broadly split into measuring sound from animals, or their environment. We guide readers from soundwave to soundscape and through the burgeoning field of conservation technology, which offers new methods to capture multiple features of complex, gestalt soundscapes. Our review ends with suggestions for future research, and a practical guide to sound measurement in captive environments.

Automated identification of chicken distress vocalizations using deep learning models

The annual global production of chickens exceeds 25 billion birds, which are often housed in very large groups, numbering thousands. Distress calling triggered by various sources of stress has been suggested as an 'iceberg indicator' of chicken welfare. However, to date, the identification of distress calls largely relies on manual annotation, which is very labour-intensive and time-consuming. Thus, a novel convolutional neural network-based model, light-VGG11, was developed to automatically identify chicken distress calls using recordings (3363 distress calls and 1973 natural barn sounds) collected on an intensive farm. The light-VGG11 was modified from VGG11 with significantly fewer parameters (9.3 million versus 128 million) and 55.88% faster detection speed while displaying comparable performance, i.e. precision (94.58%), recall (94.89%), F1-score (94.73%) and accuracy (95.07%), therefore more useful for model deployment in practice. To additionally improve light-VGG11's performance, we investigated the impacts of different data augmentation techniques (i.e. time masking, frequency masking, mixed spectrograms of the same class and Gaussian noise) and found that they could improve distress calls detection by up to 1.52%. Our distress call detection demonstration on continuous audio recordings, shows the potential for developing technologies to monitor the output of this call type in large, commercial chicken flocks.

Comparing methodologies for classification of zebra finch distance calls

Bioacoustic analysis has been used for a variety of purposes including classifying vocalizations for biodiversity monitoring and understanding mechanisms of cognitive processes. A wide range of statistical methods, including various automated methods, have been used to successfully classify vocalizations based on species, sex, geography, and individual. A comprehensive approach focusing on identifying acoustic features putatively involved in classification is required for the prediction of features necessary for discrimination in the real world. Here, we used several classification techniques, namely discriminant function analyses (DFAs), support vector machines (SVMs), and artificial neural networks (ANNs), for sex-based classification of zebra finch (Taeniopygia guttata) distance calls using acoustic features measured from spectrograms. We found that all three methods (DFAs, SVMs, and ANNs) correctly classified the calls to respective sex-based categories with high accuracy between 92 and 96%. Frequency modulation of ascending frequency, total duration, and end frequency of the distance call were the most predictive features underlying this classification in all of our models. Our results corroborate evidence of the importance of total call duration and frequency modulation in the classification of male and female distance calls. Moreover, we provide a methodological approach for bioacoustic classification problems using multiple statistical analyses.

Affective State Recognition in Livestock—Artificial Intelligence Approaches

Simple Summary

Emotions or affective states recognition in farm animals is an underexplored research domain. Despite significant advances in animal welfare research, animal affective state computing through the development and application of devices and platforms that can not only recognize but interpret and process the emotions, are in a nascent stage. The analysis and measurement of unique behavioural, physical, and biological characteristics offered by biometric sensor technologies and the affiliated complex and large data sets, opens the pathway for novel and realistic identification of individual animals amongst a herd or a flock. By capitalizing on the immense potential of biometric sensors, artificial intelligence enabled big data methods offer substantial advancement of animal welfare standards and meet the urgent needs of caretakers to respond effectively to maintain the wellbeing of their animals.

Abstract

Farm animals, numbering over 70 billion worldwide, are increasingly managed in large-scale, intensive farms. With both public awareness and scientific evidence growing that farm animals experience suffering, as well as affective states such as fear, frustration and distress, there is an urgent need to develop efficient and accurate methods for monitoring their welfare. At present, there are not scientifically validated ‘benchmarks’ for quantifying transient emotional (affective) states in farm animals, and no established measures of good welfare, only indicators of poor welfare, such as injury, pain and fear. Conventional approaches to monitoring livestock welfare are time-consuming, interrupt farming processes and involve subjective judgments. Biometric sensor data enabled by artificial intelligence is an emerging smart solution to unobtrusively monitoring livestock, but its potential for quantifying affective states and ground-breaking solutions in their application are yet to be realized. This review provides innovative methods for collecting big data on farm animal emotions, which can be used to train artificial intelligence models to classify, quantify and predict affective states in individual pigs and cows. Extending this to the group level, social network analysis can be applied to model emotional dynamics and contagion among animals. Finally, ‘digital twins’ of animals capable of simulating and predicting their affective states and behaviour in real time are a near-term possibility.

Classification of pig calls produced from birth to slaughter according to their emotional valence and context of production

Vocal expression of emotions has been observed across species and could provide a non-invasive and reliable means to assess animal emotions. We investigated if pig vocal indicators of emotions revealed in previous studies are valid across call types and contexts, and could potentially be used to develop an automated emotion monitoring tool. We performed an analysis of an extensive and unique dataset of low (LF) and high frequency (HF) calls emitted by pigs across numerous commercial contexts from birth to slaughter (7414 calls from 411 pigs). Our results revealed that the valence attributed to the contexts of production (positive versus negative) affected all investigated parameters in both LF and HF. Similarly, the context category affected all parameters. We then tested two different automated methods for call classification; a neural network revealed much higher classification accuracy compared to a permuted discriminant function analysis (pDFA), both for the valence (neural network: 91.5%; pDFA analysis weighted average across LF and HF (cross-classified): 61.7% with a chance level at 50.5%) and context (neural network: 81.5%; pDFA analysis weighted average across LF and HF (cross-classified): 19.4% with a chance level at 14.3%). These results suggest that an automated recognition system can be developed to monitor pig welfare on-farm.

Is It Time for Ecotremology?

Our awareness of air-borne sounds in natural and urban habitats has led to the recent recognition of soundscape ecology and ecoacoustics as interdisciplinary fields of research that can help us better understand ecological processes and ecosystem dynamics. Because the vibroscape (i.e., the substrate-borne vibrations occurring in a given environment) is hidden to the human senses, we have largely overlooked its ecological significance. Substrate vibrations provide information crucial to the reproduction and survival of most animals, especially arthropods, which are essential to ecosystem functioning. Thus, vibroscape is an important component of the environment perceived by the majority of animals. Nowadays, when the environment is rapidly changing due to human activities, climate change, and invasive species, this hidden vibratory world is also likely to change without our notice, with potentially crucial effects on arthropod communities. Here, we introduce ecotremology, a discipline that mainly aims at studying substrate-borne vibrations for unraveling ecological processes and biological conservation. As biotremology follows the main research concepts of bioacoustics, ecotremology is consistent with the paradigms of ecoacoustics. We argue that information extracted from substrate vibrations present in the environment can be used to comprehensively assess and reliably predict ecosystem changes. We identify key research questions and discuss the technical challenges associated with ecotremology studies.

Key Issues for Realizing Open Ecoacoustic Monitoring in Australia

Many organizations are attempting to scale ecoacoustic monitoring for conservation but are hampered at the stages of data management and analysis. We reviewed current ecoacoustic hardware, software, and standards, and conducted workshops with 23 participants across 10 organizations in Australia to learn about their current practices, and to identify key trends and challenges in their use of ecoacoustics data. We found no existing metadata schemas that contain enough ecoacoustics terms for current practice, and no standard approaches to annotation. There was a strong need for free acoustics data storage, discoverable learning resources, and interoperability with other ecological modeling tools. In parallel, there were tensions regarding intellectual property management, and siloed approaches to studying species within organizations across different regions and between organizations doing similar work. This research contributes directly to the development of an open ecoacoustics platform to enable the sharing of data, analyses, and tools for environmental conservation.

Utilizing DeepSqueak for automatic detection and classification of mammalian vocalizations: a case study on primate vocalizations

Bioacoustic analyses of animal vocalizations are predominantly accomplished through manual scanning, a highly subjective and time-consuming process. Thus, validated automated analyses are needed that are usable for a variety of animal species and easy to handle by non-programing specialists. This study tested and validated whether DeepSqueak, a user-friendly software, developed for rodent ultrasonic vocalizations, can be generalized to automate the detection/segmentation, clustering and classification of high-frequency/ultrasonic vocalizations of a primate species. Our validation procedure showed that the trained detectors for vocalizations of the gray mouse lemur (Microcebus murinus) can deal with different call types, individual variation and different recording quality. Implementing additional filters drastically reduced noise signals (4225 events) and call fragments (637 events), resulting in 91% correct detections (N_total = 3040). Additionally, the detectors could be used to detect the vocalizations of an evolutionary closely related species, the Goodman’s mouse lemur (M. lehilahytsara). An integrated supervised classifier classified 93% of the 2683 calls correctly to the respective call type, and the unsupervised clustering model grouped the calls into clusters matching the published human-made categories. This study shows that DeepSqueak can be successfully utilized to detect, cluster and classify high-frequency/ultrasonic vocalizations of other taxa than rodents, and suggests a validation procedure usable to evaluate further bioacoustics software.

From human wellbeing to animal welfare

What does it mean to be "well" and how might such a state be cultivated? When we speak of wellbeing, it is of ourselves and fellow humans. When it comes to nonhuman animals, consideration turns to welfare. My aim herein is to suggest that theoretical approaches to human wellbeing might be beneficially applied to consideration of animal welfare, and in so doing, introduce new lines of inquiry and practice. I will review current approaches to human wellbeing, adopting a triarchic structure that delineates hedonic wellbeing, eudaimonic wellbeing, and social wellbeing. For each, I present a conceptual definition and a review of how researchers have endeavored to measure the construct. Drawing these three domains of research together, I highlight how these traditionally anthropocentric lines of inquiry might be extended to the question of animal welfare - namely by considering hedonic welfare, eudaimonic welfare, and social welfare as potentially distinguishable and complementary components of the broader construct of animal welfare.

Developing Recommendations for Cumulative Endpoints and Lifetime Use for Research Animals

Research animals are important for scientific advancement, and therefore, their long-term welfare needs to be monitored to not only minimize suffering, but to provide positive affective states and experiences. Currently, there is limited guidance in countries around the world on cumulative and experimental endpoints. This paper aims to explore current opinions and institutional strategies regarding cumulative use and endpoints through a scoping survey and review of current regulations and welfare assessment tools, and ultimately to provide recommendations for assessment of cumulative and lifetime use of research animals. The survey found that only 36% of respondents indicated that their institution had cumulative use endpoint policies in place, but these policies may be informal and/or vary by species. Most respondents supported more specific guidelines but expressed concerns about formal policies that may limit their ability to make case-by-case decisions. The wide diversity in how research animals are used makes it difficult for specific policies to be implemented. Endpoint decisions should be made in an objective manner using standardized welfare assessment tools. Future research should focus on robust, efficient welfare assessment tools that can be used to support planning and recommendations for cumulative endpoints and lifetime use of research and teaching animals.

The importance of considering age when quantifying wild animals' welfare

Wild animals experience different challenges and opportunities as they mature, and this variety of experiences can lead to different levels of welfare characterizing the day-to-day lives of individuals of different ages. At the same time, most wild animals who are born do not survive to adulthood. Individuals who die as juveniles do not simply experience a homogeneous fraction of the lifetimes of older members of their species; rather, their truncated lives may be characterized by very different levels of welfare. Here, I propose the concept of welfare expectancy as a framework for quantifying wild animal welfare at a population level, given individual-level data on average welfare with respect to age. This concept fits conveniently alongside methods of analysis already used in population ecology, such as demographic sensitivity analysis, and is applicable to evaluating the welfare consequences of human interventions and natural pressures that disproportionately affect individuals of different ages. In order to understand better and improve the state of wild animal welfare, more attention should be directed towards young animals and the particular challenges they face.

A System for Monitoring Acoustics to Supplement an Animal Welfare Plan for Bottlenose Dolphins

Animal sounds are commonly used by humans to infer information about their motivations and their health, yet, acoustic data is an underutilized welfare biomarker especially for aquatic animals. Here, we describe an acoustic monitoring system that is being implemented at the U.S. Navy Marine Mammal Program where dolphins live in groups in ocean enclosures in San Diego Bay. A four-element bottom mounted hydrophone array is used to continuously record, detect and localize acoustic detections from this focal group. Software provides users an automated comparison of the current acoustic behavior to group historical data which can be used to identify periods of normal, healthy thriving dolphins, and allows rare instances of deviations from typical behavior to stand out. Variations in a group or individual’s call rates can be correlated with independent veterinary examinations and behavioral observations in order to better assess dolphin health and welfare. Additionally, the monitoring system identifies time periods in which a sound source from San Diego Bay is of high-enough amplitude that the received level at our array is considered a potential concern for the focal animals. These time stamps can be used to identify and potentially mitigate exposures to acoustic sources that may otherwise not be obvious to human listeners. We hope this application inspires zoos and aquaria to innovate and create ways to incorporate acoustic information into their own animal welfare management programs.

Deep Learning-Based Cattle Vocal Classification Model and Real-Time Livestock Monitoring System with Noise Filtering

The priority placed on animal welfare in the meat industry is increasing the importance of understanding livestock behavior. In this study, we developed a web-based monitoring and recording system based on artificial intelligence analysis for the classification of cattle sounds. The deep learning classification model of the system is a convolutional neural network (CNN) model that takes voice information converted to Mel-frequency cepstral coefficients (MFCCs) as input. The CNN model first achieved an accuracy of 91.38% in recognizing cattle sounds. Further, short-time Fourier transform-based noise filtering was applied to remove background noise, improving the classification model accuracy to 94.18%. Categorized cattle voices were then classified into four classes, and a total of 897 classification records were acquired for the classification model development. A final accuracy of 81.96% was obtained for the model. Our proposed web-based platform that provides information obtained from a total of 12 sound sensors provides cattle vocalization monitoring in real time, enabling farm owners to determine the status of their cattle.

Transforming the Adaptation Physiology of Farm Animals through Sensors

Simple Summary

Strategy for the protection and welfare of farm animals, and the sustainable animal production is dependent on the thorough understanding of the adaptation physiology. Real-time, continuous, and precise measurement of the multi-dimensions and complex intricacies of adaptive capacity of farm animals namely the mental, behavioral, and physiological states are possible only through the sensor-based approaches. This paper critically reviews the latest sensor technologies as assessment tools for the adaptation physiology of farm animals and explores their advantages over traditional measurement methods. Digital innovation, diagnostics, genetic testing, biosensors, and wearable animal devices are important tools that enable the development of decision support farming platforms and provides the path for predicting diseases in livestock. Sensor fusion data from a multitude of biochemical, emotional, and physiological functions of the farm animals not only helps to identify the most productive animal but also allows farmers to predict which individual animal may have greater resilience to common diseases. Insights into the cost of adoption of sensor technologies on farms including computing capacity, human resources in training, and the sensor hardware are being discussed.

Abstract

Despite recent scientific advancements, there is a gap in the use of technology to measure signals, behaviors, and processes of adaptation physiology of farm animals. Sensors present exciting opportunities for sustained, real-time, non-intrusive measurement of farm animal behavioral, mental, and physiological parameters with the integration of nanotechnology and instrumentation. This paper critically reviews the sensing technology and sensor data-based models used to explore biological systems such as animal behavior, energy metabolism, epidemiology, immunity, health, and animal reproduction. The use of sensor technology to assess physiological parameters can provide tremendous benefits and tools to overcome and minimize production losses while making positive contributions to animal welfare. Of course, sensor technology is not free from challenges; these devices are at times highly sensitive and prone to damage from dirt, dust, sunlight, color, fur, feathers, and environmental forces. Rural farmers unfamiliar with the technologies must be convinced and taught to use sensor-based technologies in farming and livestock management. While there is no doubt that demand will grow for non-invasive sensor-based technologies that require minimum contact with animals and can provide remote access to data, their true success lies in the acceptance of these technologies by the livestock industry.

Acoustic Description of the Soundscape of a Real-Life Intensive Farm and Its Impact on Animal Welfare: A Preliminary Analysis of Farm Sounds and Bird Vocalisations

Poultry meat is the world's primary source of animal protein due to low cost and is widely eaten at a global level. However, intensive production is required to supply the demand although it generates stress to animals and welfare problems, which have to be reduced or eradicated for the better health of birds. In this study, bird welfare is measured by certain indicators: CO2, temperature, humidity, weight, deaths, food, and water intake. Additionally, we approach an acoustic analysis of bird vocalisations as a possible metric to add to the aforementioned parameters. For this purpose, an acoustic recording and analysis of an entire production cycle of an intensive broiler Ross 308 poultry farm in the Mediterranean area was performed. The acoustic dataset generated was processed to obtain the Equivalent Level (Leq), the mean Peak Frequency (PF), and the PF variation, every 30 min. This acoustical analysis aims to evaluate the relation between traditional indicators (death, weight, and CO2) as well as acoustical metrics (equivalent level impact (Leq) and Peak Frequency) of a complete intensive production cycle. As a result, relation between CO2 and humidity versus Leq was found, as well as decreases in vocalisation when the intake of food and water was large.

Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding

Genomic breeding programs have been paramount in improving the rates of genetic progress of productive efficiency traits in livestock. Such improvement has been accompanied by the intensification of production systems, use of a wider range of precision technologies in routine management practices, and high-throughput phenotyping. Simultaneously, a greater public awareness of animal welfare has influenced livestock producers to place more emphasis on welfare relative to production traits. Therefore, management practices and breeding technologies in livestock have been developed in recent years to enhance animal welfare. In particular, genomic selection can be used to improve livestock social behavior, resilience to disease and other stress factors, and ease habituation to production system changes. The main requirements for including novel behavioral and welfare traits in genomic breeding schemes are: (1) to identify traits that represent the biological mechanisms of the industry breeding goals; (2) the availability of individual phenotypic records measured on a large number of animals (ideally with genomic information); (3) the derived traits are heritable, biologically meaningful, repeatable, and (ideally) not highly correlated with other traits already included in the selection indexes; and (4) genomic information is available for a large number of individuals (or genetically close individuals) with phenotypic records. In this review, we (1) describe a potential route for development of novel welfare indicator traits (using ideal phenotypes) for both genetic and genomic selection schemes; (2) summarize key indicator variables of livestock behavior and welfare, including a detailed assessment of thermal stress in livestock; (3) describe the primary statistical and bioinformatic methods available for large-scale data analyses of animal welfare; and (4) identify major advancements, challenges, and opportunities to generate high-throughput and large-scale datasets to enable genetic and genomic selection for improved welfare in livestock. A wide variety of novel welfare indicator traits can be derived from information captured by modern technology such as sensors, automatic feeding systems, milking robots, activity monitors, video cameras, and indirect biomarkers at the cellular and physiological levels. The development of novel traits coupled with genomic selection schemes for improved welfare in livestock can be feasible and optimized based on recently developed (or developing) technologies. Efficient implementation of genetic and genomic selection for improved animal welfare also requires the integration of a multitude of scientific fields such as cell and molecular biology, neuroscience, immunology, stress physiology, computer science, engineering, quantitative genomics, and bioinformatics.

Spectral entropy of early-life distress calls as an iceberg indicator of chicken welfare

Chicks (Gallus gallus domesticus) make a repetitive, high energy ‘distress’ call when stressed. Distress calls are a catch-all response to a range of environmental stressors, and elicit food calling and brooding from hens. Pharmacological and behavioural laboratory studies link expression of this call with negative affective state. As such, there is an a priori expectation that distress calls on farms indicate not only physical, but emotional welfare. Using whole-house recordings on 12 commercial broiler flocks (n = 25 090–26 510/flock), we show that early life (day 1–4 of placement) distress call rate can be simply and linearly estimated using a single acoustic parameter: spectral entropy. After filtering to remove low-frequency machinery noise, spectral entropy per minute of recording had a correlation of −0.88 with a manual distress call count. In videos collected on days 1–3, age-specific behavioural correlates of distress calling were identified: calling was prevalent (spectral entropy low) when foraging/drinking were high on day 1, but when chicks exhibited thermoregulatory behaviours or were behaviourally asynchronous thereafter. Crucially, spectral entropy was predictive of important commercial and welfare-relevant measures: low median daily spectral entropy predicted low weight gain and high mortality, not only into the next day, but towards the end of production. Further research is required to identify what triggers, and thus could alleviate, distress calling in broiler chicks. However, within the field of precision livestock farming, this work shows the potential for simple descriptors of the overall acoustic environment to be a novel, tractable and real-time ‘iceberg indicator’ of current and future welfare.

Sound Analysis to Predict the Growth of Turkeys

Protocols for manual weighing of turkeys are not practical on turkey farms because of the large body sizes, heavy weights and flighty nature of turkeys. The sounds turkeys make may be a proxy for bird weights, but the relationship between turkey sounds and bird weights has not been studied. The aim of this study was to correlate peak frequency (PF) of vocalization with the age and weight of the bird and examine the possibility using PF to predict the weight of turkeys. The study consisted of four trials in Egypt. Sounds of birds and their weights were recorded for 11 days during the growth period in each trial. A total 2200 sounds were manually analyzed and labelled by extracting individual and general sounds on the basis of the amplitude and frequency of the sound signal. The PF of vocalizations in each trial, as well as in pooled trails, were evaluated to determine the relationship between PF and the age and weight of the turkey. PF exhibited a highly significant negative correlation with the weight and age of the turkeys showing that PF of vocalizations can be used for predicting the weight of turkeys. Further studies are necessary to refine the procedure.