Poor performance of acoustic indices as proxies for bird diversity in a fragmented Amazonian landscape

Bicudo, Thiago; Llusia, Diego; Anciães, Marina; Gil, Diego

doi:10.1016/j.ecoinf.2023.102241

Cited by 7 publications

(3 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean width and miscoverage percentages of the generated conformal prediction intervals in each area for the three coverage levels (1-α). the models' imperfect accuracy, as demonstrated by our ndings and earlier research(Bicudo et al, 2023;Buxton et al, 2018a;Sethi et al, 2023), it is critical to have an accurate measure of the uncertainty associated with the predictions for each site in each area. Below, we discuss the models' performance and mention how the CP framework can be used to improve monitoring applications and other ecological applications in general.…”

mentioning

confidence: 88%

“…The effectiveness of acoustic indices in surveying biodiversity has been extensively investigated in a variety of settings (Alcocer et al, 2022;Pan et al, 2024), including their use as proxies for animal species diversity in temperate and tropical regions (Bicudo et al, 2023;Eldridge et al, 2018;Mammides et al, 2017) and as tools for rapid assessments (Rajan et al, 2019;Sueur et al, 2008). Most studies have focused on birds (Alcocer et al, 2022), using the indices to quantify metrics related to species richness, diversity, and abundance, as well as the abundance and diversity of animal vocalizations (Alcocer et al, 2022;Buxton et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel approach for calculating prediction uncertainty when using acoustic indices and machine learning algorithms to monitor animal communities

Mammides,

Huang,

Sree

et al. 2024

Preprint

View full text Add to dashboard Cite

There is a growing interest in using passive acoustic monitoring methods to survey biodiversity. Many studies have investigated the efficacy of acoustic indices in monitoring animal communities, particularly bird species richness, with mixed results. It has been suggested that combining multiple acoustic indices could improve accuracy. To accomplish this, researchers have employed machine learning methods, such as the Random Forest Regression, which are considered more robust in this context. However, most machine learning methods have a limitation in that they do not provide well-calibrated uncertainty quantification measures for their predictions. Quantifying uncertainty with the use of appropriate prediction intervals is of paramount importance for making informed management decisions. In this study, we propose addressing this issue using a Machine Learning framework, called Conformal Prediction, which has been developed to provide guaranteed coverage prediction intervals. Specifically, we examine the application of a recently proposed combination of Conformal Prediction with Gaussian Process Regression using data collected through bird and acoustic surveys at biodiverse sites in Cyprus and Australia. Our goal is to demonstrate how the Conformal Prediction framework can be used to assess the models’ prediction accuracy and associated uncertainty when monitoring biodiversity using acoustic indices and machine learning methods. Moreover, we discuss how the framework can be integrated into a wider range of ecological applications to help make more informed conservation management decisions.

show abstract

mentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

A novel approach for calculating prediction uncertainty when using acoustic indices and machine learning algorithms to monitor animal communities

Mammides,

Huang,

Sree

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In environments with medium or high levels of bird acoustic activity, such as breeding seasons in tropical forests, ADI may have a better performance in predicting bird diversity (Zhao et al, 2019). On the other hand, studies that tested the correlation between ADI and bird acoustic activity showed low correlations (Ferreira et al, 2011;Fuller et al, 2015;Jorge et al, 2018;Bicudo et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Predicting bird diversity through acoustic indices within the Atlantic Forest biodiversity hotspot

Gaspar,

D. A. Scarpelli,

Oliveira

et al. 2023

Front. Remote Sens.

View full text Add to dashboard Cite

The increasing conversion of natural areas for anthropic land use has been a major cause of habitat loss, destabilizing ecosystems and leading to a biodiversity crisis. Passive acoustic sensors open the possibility of remotely sensing fauna on large spatial and temporal scales, improving our understanding of the current state of biodiversity and the effects of human influences. Acoustic indices have been widely used and tested in recent years, with an aim towards understanding the relationship between indices and the acoustic activity of several taxa in different types of environments. However, studies have shown divergent relationships between acoustic indices and the vocal activity of most soniferous taxa. A combination of indices has, in turn, been reported as a promising tool for representing biodiversity in different contexts. We used uni- and bivariate models to test different combinations of 8 common indices in relation to bird assemblage metrics. We recorded twenty-two study sites in Brazil’s Atlantic Forest and three different types of environments in each site (forest, pasture, and swamp). Our results showed that 1) the best acoustic indices for explaining bird richness, abundance, and diversity were Bioacoustic and Acoustic Complexity; 2) the type of environment (forest, pasture, and swamp) influenced the performance of acoustic indices in explaining bird biodiversity, with the highest score model (biggest R2 value) being a combination between Acoustic Diversity and Bioacoustic indices. Our results do support the use of acoustic indices in monitoring the acoustic activity of birds, but combining indices is encouraged since it provided the best results. However, given the divergence we found across environments, we recommend that sets of indices are tested to determine which of them best describe the biodiversity pattern models for a specific habitat. Based on our results, we propose that biodiversity patterns can be predicted through acoustic patterns. However, the level of confidence will depend on the acoustic index used and on focal taxa of interest (i.e., birds, amphibians, insects, and mammals).

show abstract

Acoustic indices as proxies for biodiversity in certified and non-certified cocoa plantations in Indonesia

Dröge,

Prasetyo,

Muys

2024

Environ Monit Assess

View full text Add to dashboard Cite

Poor performance of acoustic indices as proxies for bird diversity in a fragmented Amazonian landscape

Cited by 7 publications

References 73 publications

A novel approach for calculating prediction uncertainty when using acoustic indices and machine learning algorithms to monitor animal communities

A novel approach for calculating prediction uncertainty when using acoustic indices and machine learning algorithms to monitor animal communities

Predicting bird diversity through acoustic indices within the Atlantic Forest biodiversity hotspot

Acoustic indices as proxies for biodiversity in certified and non-certified cocoa plantations in Indonesia

Contact Info

Product

Resources

About