# Patterns of Vocal Activity of the Chinese Bamboo Partridge Using BirdNET Analyzer

## TL;DR

This study improves bird vocalization recognition using a random forest model, showing better performance than BirdNET for Chinese Bamboo Partridge calls.

## Contribution

The study introduces an improved random forest model for bird vocalization recognition, enhancing accuracy for a regional species.

## Key findings

- The random forest model achieved 75.2% recall and 74.4% precision for Chinese Bamboo Partridge vocalizations.
- BirdNET-Analyzer-XHS had 50.8% precision, outperforming the standard BirdNET-Analyzer.
- Vocal activity peaked around sunrise and sunset, with seasonal peaks in April and May.

## Abstract

Passive acoustic monitoring (PAM) detects bird vocal activities by collecting acoustic data, which is an automatic and non-invasive method for long-term monitoring. PAM generates a significant amount of data, and the automatic recognition of data poses challenges. BirdNET is a free-to-use sound algorithm to identify acoustic data automatically. In this study, we established the BirdNET model based on the local species acoustic data (BirdNET-Analyzer-XHS). Then we established a random forest (RF) classification model based on acoustic features. Finally, we evaluated the ability of BirdNET and RF models to identify the vocalizations of Chinese Bamboo Partridge (Bambusicola thoracicus). The results showed that the recall rate of BirdNET-Analyzer was 16.6%, the precision of BirdNET-Analyzer-XHS was 50.8%, and the recall rate and precision of the RF model were 75.2% and 74.4%, respectively. This study provided a practical method for recognizing the vocalizations of regional species. Based on the identification result, the diurnal and seasonal patterns of vocal activity during the breeding season were analyzed. These findings provide a foundation for applying automatic sound analysis technology to dynamic monitoring and behavioral research on pheasants.

Passive acoustic monitoring (PAM) is an automatic and non-invasive method for long-term monitoring of bird vocal activity. PAM generates a large amount of data, and the automatic recognition of data poses significant challenges. BirdNET is a free-to-use sound algorithm. We evaluated the effectiveness of BirdNET in identifying the vocalizations of Chinese Bamboo Partridge (a Chinese endemic species) and proposed a random forest (RF) method to improve the result based on the detection of BirdNET. The diurnal and seasonal patterns of calling activity were described based on the identification results. The results showed that the recall of BirdNET-Analyzer was 16.6%, the precision of BirdNET-Analyzer-XHS was 50.8%, and the recall and precision of the RF model were 75.2% and 74.4%, respectively. The diurnal vocal activity of the Chinese Bamboo Partridge showed a bimodal pattern, with peaks around sunrise and sunset and low vocal activity during the central hours of the day. The seasonal vocal activity displayed a unimodal pattern, with a peak in vocal activity during April and May. This study used the Chinese Bamboo Partridge as an example and proposes an improved RF model, built on BirdNET recognition results, for species identification, providing a practical approach for recognizing the vocalizations of regional species.