BatNet: a deep learning‐based tool for automated bat species identification from camera trap images

Abstract

Automated monitoring technologies can increase the efficiency of ecological data collection and support data‐driven conservation. Camera traps coupled with infrared light barriers can be used to monitor temperate‐zone bat assemblages at underground hibernacula, where thousands of individuals of multiple species can aggregate in winter. However, the broad‐scale adoption of such photo‐monitoring techniques is limited by the time‐consuming bottleneck of manual image processing. Here, we present BatNet, an open‐source, deep learning‐based tool for automated identification of 13 European bat species from camera trap images. BatNet includes a user‐friendly graphical interface, where it can be retrained to identify new bat species or to create site‐specific models to improve detection accuracy at new sites. Model accuracy was evaluated on images from both trained and untrained sites, and in an ecological context, where community‐ and species‐level metrics (species diversity, relative abundance, and species‐level activity patterns) were compared between human experts and BatNet. At trained sites, model performance was high across all species (F1‐score: 0.98–1). At untrained sites, overall classification accuracy remained high (96.7–98.2%), when camera placement was comparable to the training images (<3 m from the entrance; <45° angle relative to the opening). For atypical camera placements (>3 m or >45° angle), retraining the detector model with 500 site‐specific annotations achieved an accuracy of over 95% at all sites. In the ecological case study, all investigated metrics were nearly identical between human experts and BatNet. Finally, we exemplify the ability to retrain BatNet to identify a new bat species, achieving an F1‐score of 0.99 while maintaining high classification accuracy for all original species. BatNet can be implemented directly to scale up the deployment of camera traps in Europe and enhance bat population monitoring. Moreover, the pretrained model can serve as a baseline for transfer learning to automatize the image‐based identification of bat species worldwide.

Efficacy of machine learning image classification for automated occupancy‐based monitoring

“…We used cameras with an infrared flash, which minimized the risk of cameras being vandalized or stolen. Cameras with a white flash may produce higher quality images that improve accuracy of manual and machine learning classifications for some species (Krivek et al, 2023).…”

Being confident in confidence scores: calibration in deep learning models for camera trap image sequences

“…Secondly, we argue that the integration of machine learning predictions directly into subsequent ecological tasks can be facilitated by achieving calibration. Many ecological downstream tasks (e.g estimating occupancy, abundance or activity patterns) based on deep learning predictions use an arbitrary threshold selection (Lonsinger et al 2023; Krivek et al 2023) to consider that a prediction is correct, or test a series of thresholds to determine the optimal one given known species labels (Whytock, SŚwieżewski, et al 2021; Mitterwallner et al 2023). However, the ultimate goal of using AI is to avoid having to label images.…”

Overcoming biodiversity blindness: Secondary data in primary citizen science observations

“…and BatDetect2 and BatNet for bats (Aodha et al, 2022;Krivek et al, 2023) in sound recordings. Additionally, customised models can be trained on open datasets, for example, FathomNet for marine organisms (Katija et al, 2022), Pl@ntNet for plants and iNaturalist for a range of different species.…”