Periodic Reporting for period 1 - BIOMON (Using passive acoustic monitoring methods to survey birds communities in biodiverse agricultural farmlands in the EU)
Reporting period: 2022-06-01 to 2024-05-31
The European Union's Biodiversity Strategy for 2030, which is a key component of the European Green Deal, highlights the need to stop the loss of biodiversity caused by human activities. To achieve this, it is crucial to develop effective monitoring tools for surveying biodiversity across large areas and over long periods of time. Traditional methods, which rely on expert field surveys, are time-consuming and costly for extensive monitoring. Consequently, researchers are increasingly focusing on new technologies. Much of the research into monitoring vocalizing animals, such as birds, which are often considered good indicators of ecosystem health, focuses on passive acoustic monitoring (PAM) methods. These methods involve collecting acoustic data using autonomous recording units (ARUs), which can then be analyzed to extract ecologically meaningful information about an area of interest. Multiple methods for analyzing acoustic data have been proposed, with the main distinction being whether the analysis seeks to identify the species present or quantify the heterogeneity of the acoustic environment in a given area. Species identification techniques are becoming popular, but their use remains challenging in biodiverse areas with many vocalizing species or species with insufficient training data. An alternative approach has been the use of acoustic indices, which are mathematical formulae that summarize the heterogeneity of an area's acoustic environment. The rationale behind this approach is that biodiverse areas tend to have more complex acoustic environments. Therefore, by quantifying acoustic complexity, we can draw conclusions regarding an area's biodiversity. Multiple studies have assessed the effectiveness of acoustic indices in surveying biodiverse communities, yielding mixed results. BIOMON's overall objective is to overcome current limitations and improve existing state-of-the-art methods for analyzing acoustic data collected by autonomous recording units in order to develop a protocol for monitoring avian species in biodiverse regions.
There have been numerous studies assessing the effectiveness of acoustic indices in monitoring biodiversity, with mixed results. Most research has focused on the independent use of seven acoustic indices, which have been readily available in the literature. However, there are now over 60 such indices developed. Moreover, to improve the indices’ utility in monitoring animal communities, recent research recommended that the indices be combined using appropriate tools. This is a valid suggestion, considering that each index measures different aspects of the acoustic environment and thus carries complementary information. Building on past research and in an effort to improve the use of acoustic indices as monitoring tools, BIOMON uses machine learning algorithms, mainly the random forests regressor, to identify a combined set of indices that are most useful in measuring bird diversity. To improve the method's generalizability, BIOMON uses acoustic and bird data collected at (a) 30 sites in seven subtropical forest nature reserves in Guangxi, China, (b) 24 sites in the Big Scrub lowland rainforest region in Australia, and (c) 60 sites in agricultural and seminatural areas in Cyprus.
BIOMON’s research activities produced the following key findings. First, it was found that the set of indices with the greatest predictive power for estimating bird species richness in each region varies depending on the area's specific soundscape characteristics. This suggests that no index is universally effective across all areas and that researchers and stakeholders interested in implementing a monitoring protocol based on acoustic indices must first identify the set of indices that are most relevant to their region. Second, it was found that several of the indices commonly used in the literature are less useful than other indices not frequently examined. Therefore, it is recommended that for a more effective monitoring protocol, all available indices be first examined to ensure maximum accuracy when using acoustic indices to monitor biodiversity.
A second key research activity performed during BIOMON was the incorporation of the Conformal Prediction framework into the protocol used to monitor biodiversity using acoustic monitoring methods. Current machine learning methods, such as the aforementioned random forest regressor, have the limitation of not providing a measure of the uncertainty associated with the predictions made. This can be overcome using the conformal prediction framework, which is a novel framework that can provide guaranteed coverage prediction intervals. In layman's terms, this means that when using passive acoustic monitoring methods to survey biodiversity, stakeholders can now obtain both an estimation of the number of species present and the associated range of error based on their desired degree of confidence interval. This information is critical for making informed management decisions.
BIOMON’s research activities produced the following key findings. First, it was found that the set of indices with the greatest predictive power for estimating bird species richness in each region varies depending on the area's specific soundscape characteristics. This suggests that no index is universally effective across all areas and that researchers and stakeholders interested in implementing a monitoring protocol based on acoustic indices must first identify the set of indices that are most relevant to their region. Second, it was found that several of the indices commonly used in the literature are less useful than other indices not frequently examined. Therefore, it is recommended that for a more effective monitoring protocol, all available indices be first examined to ensure maximum accuracy when using acoustic indices to monitor biodiversity.
A second key research activity performed during BIOMON was the incorporation of the Conformal Prediction framework into the protocol used to monitor biodiversity using acoustic monitoring methods. Current machine learning methods, such as the aforementioned random forest regressor, have the limitation of not providing a measure of the uncertainty associated with the predictions made. This can be overcome using the conformal prediction framework, which is a novel framework that can provide guaranteed coverage prediction intervals. In layman's terms, this means that when using passive acoustic monitoring methods to survey biodiversity, stakeholders can now obtain both an estimation of the number of species present and the associated range of error based on their desired degree of confidence interval. This information is critical for making informed management decisions.
BIOMON's findings provide a better understanding of how to improve the effectiveness of passive monitoring techniques used to survey bird communities in biodiverse areas according to the areas’ specific soundscape characteristics. Furthermore, BIOMON’s results provide a clear roadmap for incorporating the conformal prediction framework to assess the uncertainty associated with machine learning predictions. Importantly, the framework is useful beyond acoustic monitoring; it can also be used in other ecological applications in which quantifying uncertainty is important and can lead to better conservation management decisions.