Biology subjects

Mirante, D.

Publications and source records attributed to Mirante, D..

2 recordsLinked to original sources

bioRxiv2025

SANE: an Index of Anthropogenic Noise Levels for Wildlife Research in Terrestrial Ecosystems

O_LIUnderstanding the impact of noise pollution on wildlife is challenging due to the complexity of isolating the anthropogenic components from the soundscape. Soundscape studies usually employ acoustic indices that apply arbitrary thresholds to isolate anthrophony from natural sounds. However, natural and anthropogenic sounds do not always conform to these thresholds, hindering both accuracy and comparability of the resulting indices. While significant progress has been made in automated identification of acoustic events through artificial intelligence-based classifiers, an effective method to quantify anthropogenic acoustic pressure is still lacking. C_LIO_LIWe propose a novel index, the Selective Anthropogenic Noise Exposure (SANE), which leverages BirdNET deep neural network to isolate human-related sounds from recordings. The index consists in the sum of the Median Amplitude Index of all human noise categories, thereby capturing both the intensity and cumulative impact of multiple disturbance events, while also enabling the decomposition of noise level across different categories of disturbance (e.g., traffic, human voices). C_LIO_LIWe test SANEs performance in a real urban setting and through soundscape simulations and compare it with two frequency-based indices and another artificial intelligence-based acoustic index. SANE was effective in describing human noises within areas characterized by different levels of urbanization, improving upon other indices shortcomings. Additionally, SANE was robust at very fine temporal scales, precisely quantifying anthrophony levels for single recordings. Among the indices considered, SANE was the only one that remained insensitive to low-frequency biophony, which confounded both frequency and artificial intelligence-based metrics. C_LIO_LIBy leveraging artificial intelligence-based classifiers ability to detect multiple human-made sound classes, SANE index captures the intensity of anthropogenic noise while being insensitive to non-conforming natural sounds to the traditionally identified anthrophony range. Furthermore, SANE has the potential to assess the relative contribution of different noise types to the overall acoustic pollution, opening new research avenues on the acoustic pollution effects on wildlife in high disturbance contexts. C_LI

ecology↗

bioRxiv2024

Towards an automated protocol for wildlife density estimation using camera-traps

Camera-traps are valuable tools for estimating wildlife population density, and recently developed models enable density estimation without the need for individual recognition. Still, processing and analysis of camera-trap data are extremely time-consuming. While algorithms for automated species classification are becoming more common, they have only served as supporting tools, limiting their true potential in being implemented in ecological analyses without human supervision. Here, we assessed the capability of two camera-trap based models to provide robust density estimates when image classification is carried out by machine learning algorithms. We simulated density estimation with Camera-Traps Distance Sampling (CT-DS) and Random Encounter Model (REM) under different scenarios of automated image classification. We then applied the two models to obtain density estimates of three focal species (roe deer Capreolus capreolus, red fox Vulpes vulpes, and Eurasian badger Meles meles) in a reserve in central Italy. Species detection and classification was carried out both by the user and machine learning algorithms (respectively, MegaDetector and Wildlife Insights), and all outputs were used to estimate density and ultimately compared. Simulation results suggested that the CT-DS model could provide robust density estimates even at poor algorithm performances (down to 50% of correctly classified images), while the REM model is more unpredictable and depends on multiple factors. Density estimates obtained from the MegaDetector output were highly consistent for both models with the manually labelled images. While Wildlife Insights performance differed greatly between species (recall: badger = 0.15; roe deer = 0.56; fox = 0.75), CT-DS estimates did not vary significantly; on the contrary, REM systematically overestimated density, with little overlap in standard errors. We conclude that CT-DS and REM models can be robust to the loss of images when machine learning algorithms are used to identify animals, with the CT-DS being an ideal candidate for applications in a fully unsupervised framework. We propose guidelines to evaluate when and how to integrate machine learning in the analysis of camera-trap data for density estimation, further strengthening the applicability of camera traps as a cost-effective method for density estimation in (spatially and temporally) extensive multi-species monitoring programs.

ecology↗