Limited expert annotation capacity is a pervasive constraint in biodiversity monitoring. Passive acoustic recorders and camera traps generate data faster than experts can analyse them. Machine learning (ML) models can process these data at scale, but their reliability depends on the quality, quantity, and coverage of labelled samples, so expert time remains a constraint. Active learning (AL) eases this bottleneck by selecting, under a fixed annotation budget, the samples expected to improve a model most, and published evidence shows it can reduce the labels needed to reach a target performance. Monitoring programmes, however, face a broader question: how should a limited expert budget be divided so that model training, validation, and the ecological estimates built on model outputs all remain reliable? Because AL selects samples non-randomly, its labels are unsuitable for validation, calibration, or threshold selection, a tension rarely acknowledged. We synthesise AL research across acoustic and image modalities and identify gaps and opportunities. Most studies evaluate query strategies on pre-labelled benchmarks with simulated annotators; deployments in real monitoring workflows are rare and concentrate on birds and cetaceans. Bats, insects, amphibians, and fish are underrepresented, and multimodal applications remain largely unexplored. Evaluation centres on headline reductions in annotation effort, often without random-sampling baselines, per-class results, or calibration analysis, and rarely accounts for the labels required for validation. We provide a tutorial treatment of the AL loop that makes these budget decisions explicit, and a roadmap towards AL methods that support label-efficient training, validation, and trustworthy downstream ecological inference.

Social relationships are foundational to animal societies, but individual social connections differ hugely in importance and strength. Key relationships, such as those between breeding partners, may be prioritised and more highly invested in by individuals, but a key question is the extent to which social flexibility allows individuals to respond to the loss of these key social relationships. Here, we use a detailed longitudinal dataset of individual breeding and social behaviour in wild great tits (Parus major) to characterise flexibility in social behaviour after the loss of their breeding partner ('widowing'). We show transient increases in two measures of sociality following the widowing event. Individuals' relationships with their replacement partner were initially weaker than those between non-widowed birds, but converged by the breeding season. Hence, we show that birds are robust to the loss of key social relationships and that great tits show a flexible ability to return to social equilibrium. Strong social resilience has implications for the response of populations to change and loss.

Vocal communication is a conserved vertebrate social behavior that begins at birth with the cries of infants. These neonatal vocal signals vary across contexts to elicit parental care that matches inf...

Birdsong produced in non-breeding flocks is shaped by a dynamic interplay between intrinsic reward and social feedback. Studies in cowbirds and starlings suggest that positive affective states and op...

I use birdsong to understand how the brain learns complex skills across molecules, synapses, circuits, behavior, and computation. On the 2026–27 faculty job market.

The Spanish Ministry for Science and Innovation is about to publish a call for pre-doctoral scholarships (FPI) adhered to scientific projects that have been approved for funding in 2026. We invite …

Ovenbirds, electric fish, tree frogs and other regional fauna help neuroscientists ask novel research questions in the field.

ALT:

To serenade with their high-pitched songs, singing mice inflate a throat sac — a use for air sacs seemingly unknown in any other animal.

Note. The below text is a general overview of the sorts of postdocs we often recruit. We are currently recruiting candidates for a 2-year position focusing on auditory perception in aging populations,...

Do you illustrate birds? We are looking for frontispiece illustrators for our journal!

Application Deadline: 12 October 2026, 11:00 am (CET)

Deep learning is transforming the study of animal sound, enabling the automated identification of species, individuals, behaviors, and ecological patterns from large collections of recordings. While bioacoustic machine-learning models are growing more powerful, many biologists—ecologists, behavioral scientists, conservationists—and others working with acoustic data feel unprepared to navigate the computational workflows required to implement them. This article presents practical guidelines covering the full lifecycle of bioacoustic machine learning, including problem definition, data sourcing and annotation, model training, evaluation, deployment, reproducibility, and ethical considerations. Rather than providing a linear checklist, the guidelines outline an iterative framework for building science-led workflows, leveraging transfer learning and open-source tools, evaluating models based on the real-world cost of errors, and addressing domain shift under variable field conditions. Ultimately, this workflow demystifies the software-engineering process, providing a low-barrier and reproducible pathway for researchers applying machine learning to animal sound.

Animal communication behaviors are complex, dynamic, conspicuous, and often critically important for individual fitness as well as sociality. For these reasons, animal communication has been of intere...

Scientists have worked out what is going on inside a dog's brain when it sees a human smiling or scowling.

A phased diploid telomere-to-telomere reference genome for the zebra finch fully resolves its complete somatic chromosome set, recovering 2,710 previously missing or unannotated genes. The assembly al...

-1193

Ecological Entomology, EarlyView.

Listen to birdsong through the ages. Guess the bird. Collect the chorus. Dawn Chorus Quest is a free to play educational game about birds, biodiversity and rewilding.

This chapter analyses if, based on current evidence, vocalisations have construct validity as indicators of emotional valence across species. It then explores the responsiveness and selectivity of vo...