Population Monitoring of the Red Junglefowl Based on Acoustic Signal Recognition Technology

Vocalisation is a crucial means of communication for birds and plays a key role in survival and reproductive success. Individual differences in songs have been used for identification in many animals, but few studies have integrated song individuality into wildlife population monitoring. The male red junglefowl <i>Gallus gallus jabouillei</i> is a tropical forest bird that primarily uses acoustic signals for conspecific communication. From July to August 2020, the calls of 34 pasture-raised red junglefowl were recorded for individual identification based on vocalisations. Fieldwork was conducted from March to May 2021 in the Datian National Nature Reserve, Hainan, China, during which microphone arrays were deployed to record the calls of wild red junglefowl throughout their breeding season. Discriminant function analysis (DFA) was applied to identify pasture-raised red junglefowl individuals, achieving a correct identification rate of 95.7%. Affinity propagation (AP) clustering was used to perform unsupervised clustering based on pairwise syllable similarities, resulting in 34 clusters corresponding to the actual number of individuals, with a correct syllable type recognition rate of 99.4%. Kaleidoscope software was used to extract the call during the breeding period of the wild population of red junglefowl; the precision rate was 80.38%, and the recall rate was 75.85%. Using AP clustering for vocalisation analysis, the estimated population in the core area was approximately 205 male individuals, with a manual verification accuracy of 82.5%. This result is slightly lower than the estimate of 234 individuals obtained using vocal count and random encounter methods. Our study demonstrated the potential of affinity propagation clustering techniques for estimating the population size of wild red junglefowl.