B. C. Carstens

Predicting genetic biodiversity in salamanders using geographic, climatic, and life history traits

This study uses machine learning to predict genetic diversity in salamanders based on geographic, climatic, and life history traits, finding hidden diversity linked to climatic variation.

Bats of a feather: Range characteristics and wing morphology predict phylogeographic breaks in volant vertebrates

The paper identifies factors predicting phylogeographic breaks in bats and birds using range characteristics and wing morphology.

Environmental factors and cultural drift influence song evolution in New World Sparrows

This study uses deep machine learning to analyze New World Sparrows' songs, finding that environmental and cultural factors significantly influence song evolution, comparable to genetic factors.

Machine learning reveals relationships between song, climate, and migration in coastal Zonotrichia leucophrys

This study uses machine learning to analyze White-crowned Sparrow songs and finds that song divergence correlates with environmental factors and migratory status, not geographic distance.

The impacts of transfer learning, phylogenetic distance, and sample size on big-data bioacoustics

This study evaluates how transfer learning, phylogenetic distance, and sample size affect bioacoustic data automation accuracy across ten bird species.

Phylogeographic model selection using convolutional neural networks

This study applies convolutional neural networks to phylogeographic model selection, achieving high accuracy in demographic model identification compared to approximate Bayesian computation.

Predicting amphibian intraspecific diversity with machine learning: Challenges and prospects for integrating traits, geography, and genetic data

The paper uses machine learning to predict intraspecific genetic diversity in amphibians by integrating traits, geography, and genetic data, finding significant phylogenetic signal and lower diversity in northern salamanders.

Disentangling the process of speciation using machine learning

This paper introduces delimitR, a machine learning tool for inferring species boundaries and evaluating speciation processes using genomic data.