A lot of hype has recently been generated around deep learning, a group of artificial intelligence approaches able to break accuracy records in pattern recognition. Over the course of just a few years, deep learning revolutionized several research fields such as bioinformatics or medicine. Yet such a surge of tools and knowledge is still in its infancy in ecology despite the ever-growing size and the complexity of ecological datasets. Here we performed a literature review of deep learning implementations in ecology to identify its benefits in most ecological disciplines, even in applied ecology, up to decision makers and conservationists alike. We also provide guidelines on useful resources and recommendations for ecologists to start adding deep learning to their toolkit. At a time when automatic monitoring of populations and ecosystems generates a vast amount of data that cannot be processed by humans anymore, deep learning could become a necessity in ecology.

/pdf/applications-for-deep-learning-in-ecology-18vuu7hvv2.pdf

Applications for Deep Learning in Ecology

Bats are an ecologically and taxonomically diverse group accounting for roughly a fifth of mammalian diversity worldwide. Many of the threats bats face (e.g., habitat loss, bushmeat hunting, and climate change) reflect the conservation challenges of our era. However, compared to other mammals and birds, we know significantly less about the population status of most bat species, which makes prioritizing and planning conservation actions challenging. Over a third of bat species assessed by the International Union for Conservation of Nature (IUCN) are considered threatened or data deficient, and well over half of the species have unknown or decreasing population trends. That equals 988 species, or 80% of bats assessed by IUCN, needing conservation or research attention. Delivering conservation to bat species will require sustained efforts to assess population status and trends and address data deficiencies. Successful bat conservation must integrate research and conservation to identify stressors and their solutions and to test the efficacy of actions to stabilize or increase populations. Global and regional networks that connect researchers, conservation practitioners, and local stakeholders to share knowledge, build capacity, and prioritize and coordinate research and conservation efforts, are vital to ensuring sustainable bat populations worldwide.

A review of the major threats and challenges to global bat conservation

1. High-throughput environmental sensing technologies are increasingly central to global monitoring of the ecological impacts of human activities. In particular, the recent boom in passive acoustic sensors has provided efficient, noninvasive, and taxonomically broad means to study wildlife populations and communities, and monitor their responses to environmental change. However, until recently, tech-nological costs and constraints have largely confined research in passive acoustic monitoring (PAM) to a handful of taxonomic groups (e.g., bats, cetaceans, birds), often in relatively small-scale, proof-of-concept studies.2. The arrival of low-cost, open-source sensors is now rapidly expanding access to PAM technologies, making it vital to evaluate where these tools can contribute to broader efforts in ecology and biodiversity research. Here, we synthesise and critically assess the current emerging opportunities and challenges for PAM for ecological assessment and monitoring of both species populations and communities.3. We show that terrestrial and marine PAM applications are advancing rapidly, fa-cilitated by emerging sensor hardware, the application of machine learning inno-vations to automated wildlife call identification, and work towards developing acoustic biodiversity indicators. However, the broader scope of PAM research remains constrained by limited availability of reference sound libraries and open-source audio processing tools, especially for the tropics, and lack of clarity around the accuracy, transferability and limitations of many analytical methods.4. In order to improve possibilities for PAM globally, we emphasise the need for col-laborative work to develop standardised survey and analysis protocols, publicly archived sound libraries, multiyear audio datasets, and a more robust theoretical and analytical framework for monitoring vocalising animal communities.

https://besjournals.onlinelibrary.wiley.com/doi/pdf/10.1111/2041-210X.13101

Emerging opportunities and challenges for passive acoustics in ecological assessment and monitoring

The cost, usability and power efficiency of available wildlife monitoring equipment currently inhibits full ground-level coverage of many natural systems. Developments over the last decade in technology, open science, and the sharing economy promise to bring global access to more versatile and more affordable monitoring tools, to improve coverage for conservation researchers and managers.
Here we describe the development and proof-of-concept of a low-cost, small-sized and low-energy acoustic detector: “AudioMoth.” The device is open-source and programmable, with diverse applications for recording animal calls or human activity at sample rates of up to 384 kHz. We briefly outline two ongoing real-world case studies of large-scale, long-term monitoring for biodiversity and exploitation of natural resources. These studies demonstrate the potential for AudioMoth to enable a substantial shift away from passive continuous recording by individual devices, towards smart detection by networks of devices flooding large and inaccessible ecosystems.
The case studies demonstrate one of the smart capabilities of AudioMoth, to trigger event logging on the basis of classification algorithms that identify specific acoustic events. An algorithm to trigger recordings of the New Forest cicada (Cicadetta montana) demonstrates the potential for AudioMoth to vastly improve the spatial and temporal coverage of surveys for the presence of cryptic animals. An algorithm for logging gunshot events has potential to identify a shotgun blast in tropical rainforest at distances of up to 500 m, extending to 1 km with continuous recording.
AudioMoth is more energy efficient than currently available passive acoustic monitoring devices, giving it considerably greater portability and longevity in the field with smaller batteries. At a build cost of ∼US$43 per unit, AudioMoth has potential for varied applications in large-scale, long-term acoustic surveys. With continuing developments in smart, energy-efficient algorithms and diminishing component costs, we are approaching the milestone of local communities being able to afford to remotely monitor their own natural resources.

https://besjournals.onlinelibrary.wiley.com/doi/epdf/10.1111/2041-210X.12955

AudioMoth: Evaluation of a smart open acoustic device for monitoring biodiversity and the environment

Assessing the presence and abundance of birds is important for monitoring specific species as well as overall ecosystem health. Many birds are most readily detected by their sounds, and thus passive acoustic monitoring is highly appropriate. Yet acoustic monitoring is often held back by practical limitations such as the need for manual configuration, reliance on example sound libraries, low accuracy, low robustness, and limited ability to generalise to novel acoustic conditions. Here we report outcomes from a collaborative data challenge. We present new acoustic monitoring datasets, summarise the machine learning techniques proposed by challenge teams, conduct detailed performance evaluation, and discuss how such approaches to detection can be integrated into remote monitoring projects. Multiple methods were able to attain performance of around 88% AUC (area under the ROC curve), much higher performance than previous general‐purpose methods. With modern machine learning including deep learning, general‐purpose acoustic bird detection can achieve very high retrieval rates in remote monitoring data with no manual recalibration, and no pre‐training of the detector for the target species or the acoustic conditions in the target environment.

Automatic acoustic detection of birds through deep learning : the first bird audio detection challenge

Passive acoustic sensing has emerged as a powerful tool for quantifying anthropogenic impacts on biodiversity, especially for echolocating bat species. To better assess bat population trends there is a critical need for accurate, reliable, and open source tools that allow the detection and classification of bat calls in large collections of audio recordings. The majority of existing tools are commercial or have focused on the species classification task, neglecting the important problem of first localizing echolocation calls in audio which is particularly problematic in noisy recordings. We developed a convolutional neural network based open-source pipeline for detecting ultrasonic, full-spectrum, search-phase calls produced by echolocating bats. Our deep learning algorithms were trained on full-spectrum ultrasonic audio collected along road-transects across Europe and labelled by citizen scientists from www.batdetective.org. When compared to other existing algorithms and commercial systems, we show significantly higher detection performance of search-phase echolocation calls with our test sets. As an example application, we ran our detection pipeline on bat monitoring data collected over five years from Jersey (UK), and compared results to a widely-used commercial system. Our detection pipeline can be used for the automatic detection and monitoring of bat populations, and further facilitates their use as indicator species on a large scale. Our proposed pipeline makes only a small number of bat specific design decisions, and with appropriate training data it could be applied to detecting other species in audio. A crucial novelty of our work is showing that with careful, non-trivial, design and implementation considerations, state-of-the-art deep learning methods can be used for accurate and efficient monitoring in audio.

/pdf/bat-detective-deep-learning-tools-for-bat-acoustic-signal-txnri9rwta.pdf

Bat detective—Deep learning tools for bat acoustic signal detection

Passive acoustic sensing has emerged as a powerful tool for quantifying anthropogenic impacts on biodiversity, especially for echolocating bat species. To better assess bat population trends there is a critical need for accurate, reliable, and open source tools that allow the detection and classification of bat calls in large collections of audio recordings. The majority of existing tools are commercial or have focused on the species classification task, neglecting the important problem of first localizing echolocation calls in audio which is particularly problematic in noisy recordings. We developed a convolutional neural network (CNN) based open-source pipeline for detecting ultrasonic, full-spectrum, search-phase calls produced by echolocating bats (BatDetect). Our deep learning algorithms (CNNFULL and CNNFAST) were trained on full-spectrum ultrasonic audio collected along road-transects across Romania and Bulgaria by citizen scientists as part of the iBats programme and labelled by users of www.batdetective.org. We compared the performance of our system to other algorithms and commercial systems on expert verified test datasets recorded from different sensors and countries. As an example application, we ran our detection pipeline on iBats monitoring data collected over five years from Jersey (UK), and compared results to a widely-used commercial system. Here, we show that both CNNFULL and CNNFAST deep learning algorithms have a higher detection performance (average precision, and recall) of search-phase echolocation calls with our test sets, when compared to other existing algorithms and commercial systems tested. Precision scores for commercial systems were reasonably good across all test datasets (>0.7), but this was at the expense of recall rates. In particular, our deep learning approaches were better at detecting calls in road-transect data, which contained more noisy recordings. Our comparison of CNNFULL and CNNFAST algorithms was favourable, although CNNFAST had a slightly poorer performance, displaying a trade-off between speed and accuracy. Our example monitoring application demonstrated that our open-source, fully automatic, BatDetect CNNFAST pipeline does as well or better compared to a commercial system with manual verification previously used to analyse monitoring data. We show that it is possible to both accurately and automatically detect bat search-phase echolocation calls, particularly from noisy audio recordings. Our detection pipeline enables the automatic detection and monitoring of bat populations, and further facilitates their use as indicator species on a large scale, particularly when combined with automatic species identification. We release our system and datasets to encourage future progress and transparency.

/pdf/bat-detective-deep-learning-tools-for-bat-acoustic-signal-46bqigdugp.pdf

Libby Kinsey

Papers

Bat detective—Deep learning tools for bat acoustic signal detection

Bat Detective - Deep Learning Tools for Bat Acoustic Signal Detection