FuSe: Technologies For Bioacoustic Sensing

Lead Research Organisation: University College London
Department Name: Genetics Evolution and Environment


Biodiversity is facing an unprecedented decline whilst the pressure on the earth's ecosystems continues to grow. Recognising the status of biodiversity and its benefit to human wellbeing, the world's governments committed in 2010 to take effective and urgent action to halt biodiversity loss through the Convention on Biological Diversity's targets. These targets require monitoring to assess progress towards specific goals. Such large-scale biodiversity assessment calls for methods which are able to provide an understanding of large-scale patterns in species' distributions, abundances and changes over time. This relies on surveys to collect data that are representative at a regional to national scale, and robust analysis that is able to provide an informed understanding of species' populations.

As a group, bats (Chiroptera) are particularly challenging to monitor because most are nocturnal, wide-ranging and difficult to identify. Historically the monitoring of bats in temperate regions has focused on intensive site-based visual counts or capture surveys. There is considerable value in these approaches, but it is difficult to confidently infer from these what is happening at a wider population level. Acoustic surveys have been used in the UK to monitor bats for the past few decades (e.g. Bat Conservation Trust's National Bat Monitoring Programme), but it is only very recently that advances in sensor technology and analytical acoustic tools have made it possible to identify and monitor more than a handful of easy to identify species.

Many of the first open-source tools for automatically detecting and identifying bat species from sound recordings were developed from our previous NERC funded research. We developed acoustic reference libraries for European bat species and the first automatic machine learning classifier. We have since built on this work through our recent EPSRC and Zooniverse funded projects, to make use of the latest machine-learning technologies (Convoluted Neural Networks, CNNs) and through this developed an open-source pipeline for the detection of search-phase echolocation calls and species identification.

Despite recent and exciting developments in acoustic species identification, there remain substantial challenges for their cost-effective use within a scalable monitoring tool. A major barrier for deployment at scale is the expense of acoustic sensors, which typically cost up to £1000. As part of this consortium, research at Oxford University has focused on the development of low-cost sensors (http://soundtrap.io), which record uncompressed audio to an SD card. The current sensors are not designed to record at high frequency for bats, but prototype versions, which would cost less than £50 have already been modified and deployed in trials to record bats.

The FuSe (Technologies For Bioacoustic Sensing) research consortium brings together this expertise in bat acoustic analysis (University College London), computer science and open source sensor hardware (Oxford University), with large-scale citizen science (British Trust for Ornithology), and national-level bat population monitoring (Bat Conservation Trust). Integrating cutting edge analytical tools for the species identification of bats with the development of new low cost sensors, and expertise in the interpretation of data collected through large-scale volunteer-based acoustic surveys and bat monitoring, we will create an end-to-end open-source system for the large-scale acoustic monitoring of bat populations. This is a catalytic proposal, which has huge implications for the future of bat and bioacoustic monitoring.

Planned Impact

Through careful working with stakeholder groups and our project partner the Bat Conservation Trust (see Case for Support, Outcomes, Beneficiaries and Impacts) we will co-produce the requirements for data outputs and interactions of the FuSe system. The project will produce substantial benefits for the Bat Conservation Trust, stakeholders and wider public by:

-- Enabling rigorous and sustainable monitoring of bats at national and international scales --

There is a clear need for recent advances in sensor technology and analytical acoustic tools to be implemented into national and international bat monitoring programmes. In the short and medium term by working in partnership with the Bat Conservation Trust the innovations described in this proposal will benefit bat monitoring in the UK by enabling: (1) the monitoring of a greater range of bat species than is currently possible, increasing the number of species for which it is possible to produce robust metrics of status, change and distribution; (2) the collection and processing of much larger amounts of data for a similar level of volunteer effort. This will improve our ability to collect data over longer survey periods and to monitor the rarer bat species. As a longer-term benefit, innovation made possible through this project is likely to adopted by other countries, leading to a step improvement in global bat monitoring and understanding of bats.

-- Providing robust data for wider use and decision making by stakeholders --

Implementing such innovation into national bat monitoring would provide data that will be of immense value to a wide range of stakeholders, including government, statutory nature conservation bodies, local planning authorities, developers, land managers and conservation bodies. In the short and medium term, outputs from the project will be used for a wide range of purposes including for (1) strategic planning; (2) the assessment of favourable conservation status; (3) the condition of protected sites; (4) agri-environment schemes; (4) indicators of environmental quality. In the longer-term, such data will improve our ability to quantify the impact of potential drivers of population change.

-- Inspiring interest, awareness and enthusiasm for bats -

This project will bring science, nature and technology together to harness volunteers' enthusiasm for discovering more about the nocturnal biodiversity in their gardens and local area. By engaging with a much wider audience of volunteers, who will not require previous bat monitoring experience, we will increase interest, understanding and awareness of bats and bat conservation. The longer-term benefit is a public who take greater responsibility for the natural environment and wildlife within it.
Description Our key findings and outputs were:
1. We developed computer algorithms (using machine learning) to identify different UK species of bats from their calls (open source code for detection of calls is published here https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005995 and we are writing up the species identification algorithms into a paper now).
2. We developed the protocols for using a cheap open source acoustic detector (audiomoth - https://www.openacousticdevices.info/) to record bats (published in an internal report for Bat Conservation Trust and we are writing up this for a paper).
3. We developed the sampling methodology and the statistical approach which would be needed to generate robust species abundance trends for bats for the new citizen science survey to be run nationally by The Bat Conservation Trust (published as an internal report for Bat Conservation Trust and we are writing this up for a paper). We found that it was possible to generate statistically robust population trends for many more species of bats using our new approach than can be generated currently. We also reviewed the general challenges and opportunities for using acoustic to monitor biodiversity in a review paper (https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/2041-210X.13101).
4. We developed an online portal for citizen scientists to take part in a survey and processing their data automatically with our algorithms and a reporting tool for their data and the national data (http://britishbatsurvey.com and https://app.bto.org/bat-vis/BritishBatSurvey).
5. We piloted the new survey in Scotland with 15 volunteers in summer 2018 to get feedback on the data pipeline and the online portal and the proposed reporting feedback (http://britishbatsurvey.com).
6. Working with Bat Conservation Trust after the grant has finished, we plan to roll out the survey in South West England in summer 2019.
Exploitation Route These protocols could be rolled out more generally to monitor bats not just for a national survey to generate national biodiversity statistics but also to understand the impact before and after habitat modification in the contruction industry or agriculture. These methods could also be further developed to monitor other species which generate sounds (eg. frogs, birds, insects), or even anthropogenic sounds (impact of car or plane noise).
Sectors Agriculture

Food and Drink


Digital/Communication/Information Technologies (including Software)


URL http://britishbatsurvey.com
Description The results from this award have been used by The Bat Conservation Trust for a new national UK biodiversity monitoring survey. Updates to the models and systems continually improve the monitoring tool.
First Year Of Impact 2018
Sector Digital/Communication/Information Technologies (including Software),Environment
Impact Types Societal

Policy & public services

Title AudioMoth 
Description AudioMoth is a low-cost open-source acoustic sensor. The standard firmware makes scheduled recordings. Custom firmware can implement more sophisticated filtering and detection tasks. The device is completely open-source allowing individual and organisations to customise it to their needs. 
Type Of Material Improvements to research infrastructure 
Year Produced 2019 
Provided To Others? Yes  
Impact The AudioMoth device trialled in this project has been widely distributed. Currently over 10,000 such devices have been manufactured and used by researchers around the world. 
URL https://www.openacousticdevices.info/audiomoth
Title Bat Detective 
Description A deep learning acoustic recognition tool to identify and quantify bat echolocation calls 
Type Of Technology Software 
Year Produced 2018 
Open Source License? Yes  
Impact 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. 
URL http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005995