How to translate text using browser tools
19 December 2023 Machine learning reveals that climate, geography, and cultural drift all predict bird song variation in coastal Zonotrichia leucophrys
Jiaying Yang, Bryan C. Carstens, Kaiya L. Provost
Author Affiliations +
Abstract

Previous work has demonstrated that there is extensive variation in the songs of White-crowned Sparrow (Zonotrichia leucophrys) throughout the species range, including between neighboring (and genetically distinct) subspecies Z. l. nuttalli and Z. l. pugetensis. Using a machine learning approach to bioacoustic analysis, we demonstrate that variation in song is correlated with year of recording (representing cultural drift), geographic distance, and climatic differences, but the response is subspecies- and season-specific. Automated machine learning methods of bird song annotation can process large datasets more efficiently, allowing us to examine 1,913 recordings across ∼60 years. We utilize a recently published artificial neural network to automatically annotate White-crowned Sparrow vocalizations. By analyzing differences in syllable usage and composition, we recapitulate the known pattern where Z. l. nuttalli and Z. l. pugetensis have significantly different songs. Our results are consistent with the interpretation that these differences are caused by the changes in characteristics of syllables in the White-crowned Sparrow repertoire. This supports the hypothesis that the evolution of vocalization behavior is affected by the environment, in addition to population structure.

LAY SUMMARY

  • Birdsong is an important behavior because it is critical to bird communication and reproduction.

  • White-crowned Sparrows in western North America are known to use different songs along their range, but it is unknown how those songs vary through space and time.

  • We used machine learning to analyze these songs and found that populations of White-crowned Sparrows can be differentiated based on their songs.

  • Geographic factors exert a greater influence on song evolution in migratory populations, while climate factors are important across all populations.

  • Songs in this species also change through time irrespective of other changes, meaning they are impacted by cultural evolution.

Trabajos anteriores han demostrado que existe una extensa variación en los cantos de Zonotrichia leucophrys en todo el rango de la especie, incluida la variación entre las subespecies vecinas (y genéticamente distintas) Z. l. nuttalli y Z. l. pugetensis. Utilizando un enfoque de aprendizaje automático para el análisis bioacústico, demostramos que la variación en el canto está correlacionada con el año de grabación (que representa la deriva cultural), la distancia geográfica y las diferencias climáticas, pero la respuesta es específica de la subespecie y la temporada. Los métodos automatizados de aprendizaje automático para analizar el canto de las aves pueden procesar sets de datos grandes de manera más eficiente, lo que nos permitió examinar 1,913 grabaciones realizadas a lo largo de ∼60 años. Utilizamos una red neuronal artificial recientemente publicada para analizar automáticamente las vocalizaciones de Z. leucophrys. Al analizar las diferencias en el uso y la composición de las sílabas, recapitulamos el patrón conocido en el que Z. l. nuttalli y Z. l. pugetensis tienen cantos significativamente diferentes. Nuestros resultados son consistentes con la interpretación de que estas diferencias son causadas por los cambios en las características de las sílabas en el repertorio de Z. leucophrys. Esto respalda la hipótesis de que la evolución del comportamiento de vocalización se ve afectada por el ambiente, además del efecto de la estructura poblacional.

Jiaying Yang, Bryan C. Carstens, and Kaiya L. Provost "Machine learning reveals that climate, geography, and cultural drift all predict bird song variation in coastal Zonotrichia leucophrys," Ornithology 141(2), 1-15, (19 December 2023). https://doi.org/10.1093/ornithology/ukad062
Received: 8 March 2023; Accepted: 28 November 2023; Published: 19 December 2023
KEYWORDS
aprendizaje automático
bioacoustics
bioacústica
bird song
canto de aves
clima
Climate
RIGHTS & PERMISSIONS
Get copyright permission
Back to Top