Gillings, S. | Search bioRxiv

bioRxiv2025

Estimating how Site-Level Differences in Acoustic Environments Affect Species Detection by Machine Learning Models

O_LIMachine learning models are vital in species detection from acoustic data, due to the large amount of recordings produced, especially in passive acoustic monitoring studies. However, the acoustic environment of a site can significantly impact the detectability of species using such models, potentially leading to biased estimates of species abundance and distribution. This impact is poorly understood, and current manual validation methods for assessing acoustic detectability are intractable when working with many species, across multiple locations and datasets, due to the intensive time requirements to manually identify false negatives. C_LIO_LIWe introduce a new method, Noise-Augmented Detectability Estimation (NADE), to estimate the impact of site-specific environmental noise on the acoustic detectability of different species. We use vocalisations augmented with noise from the sites themselves to alleviate the need for manual validation of detectability. Our approach produces site- and species-specific estimates of the complex relationship between background noise, vocalisation amplitude, and acoustic detectability when using a machine learning detection model. We evaluate this method using BirdNET on six bird species, in the UK, demonstrating its potential for broader application in acoustic ecology. C_LIO_LIOur results show that there are large differences in the ability of a machine learning model to detect and classify vocalisations across different sites and species. For example: the detectability of loud vocalisations can be 90% at one site and 10% at another; the detectability at a site can be halved during the course of a survey; and that the amplitude of the background noise alone is insufficient to correctly estimate the detectability of a vocalisation. Detectability at a site can also vary considerably by species: a site can have the relatively high detectability for one species but poorer detectability for another. C_LIO_LIBy providing a quantitative measure of how site-specific background noise affects acoustic detectability, NADE could be used to improve the accuracy of species abundance estimates derived from passive acoustic monitoring, helping to identify sites and times where the detectability is likely to be lower. This approach provides a significant step towards making acoustic detectability estimation more feasible, allowing more robust estimates of species abundance and distribution from acoustic data. C_LI

ecology↗

bioRxiv2017

Trait correlates of climatic niche tracking in British birds

Growing evidence indicates that species respond idiosyncratically when exposed to the same changes in climate. As a result, understanding the potential influence of biological traits on species distributional responses is a research priority. Yet, empirical support for hypothesised influences of traits on climate change responses remains equivocal.\n\nIn this paper, we developed a novel approach to determine whether biological traits predict the degree of climatic niche tracking of British breeding birds in response to recent climate change. First, we quantified how well predicted positive and negative changes in probability of presence from climate-based species distribution models agreed with observed local gains and losses in species occupancy - our measure of climatic niche tracking. Second, we examined whether the degree of climatic niche tracking could be predicted by species ecological and life-history traits, as well as phylogenetic relationships.\n\nOverall, British breeding birds displayed a low degree of climatic niche tracking over the period of our study, though this varied substantially among species. Models incorporating traits and phylogeny explained a low proportion of the variation in climatic niche tracking. Nevertheless, we did find statistical evidence that species with lower lifespans tracked their climatic niches more closely, whilst species with a mixed diet displayed a lower degree of climatic niche tracking.\n\nWe present here a tractable approach for quantifying the degree to which observed local range gains and losses can be related to climate redistribution and apply it to British breeding birds. Although we do not find strong evidence that traits predict the degree of climatic niche tracking, we discuss why this is likely to be a consequence of the features of our study system rather than the approach itself. We believe this approach may prove to be useful as datasets of temporal changes in species distributions become increasingly available.

ecology↗