Refine
Document Type
- Article (8)
Language
- English (8) (remove)
Has Fulltext
- yes (8)
Is part of the Bibliography
- no (8)
Keywords
- Chiroptera (2)
- Automated monitoring (1)
- Bayesian animal model (1)
- Bechstein’s bat (1)
- Bergmann's rule (1)
- Body size (1)
- Climate Change (1)
- Climate change (1)
- Conservation (1)
- Daubenton’s bats (1)
- Demography (1)
- Global warming (1)
- Hibernation phenology (1)
- Hibernation timing (1)
- Longevity (1)
- Myotis daubentonii (1)
- Myotis nattereri (1)
- NAO (1)
- Natterer’s bats (1)
- Social behavior (1)
- Survival (1)
- Temperature (1)
- bat conservation (1)
- behavioural plasticity (1)
- camera trap (1)
- chiroptera (1)
- climate change (1)
- deep learning (1)
- environmental change (1)
- evolutionary potential (1)
- extinction risk (1)
- heritability (1)
- infrared light barrier (1)
- mortality costs (1)
- phenotypic plasticity (1)
- survival analysis (1)
Institute
Publisher
- Wiley (3)
- Springer Nature (2)
- BioMed Central (BMC) (1)
- Nature Publishing Group (1)
- Royal Society (1)
BatNet: a deep learning-based tool for automated bat species identification from camera trap images
(2023)
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.
Whether species can cope with environmental change depends considerably on their life history. Bats have long lifespans and low reproductive rates which make them vulnerable to environmental changes. Global warming causes Bechstein’s bats (Myotis bechsteinii) to produce larger females that face a higher mortality risk. Here, we test whether these larger females are able to offset their elevated mortality risk by adopting a faster life history. We analysed an individual-based 25-year dataset from 331 RFID-tagged wild bats and combine genetic pedigrees with data on survival, reproduction and body size. We find that size-dependent fecundity and age at first reproduction drive the observed increase in mortality. Because larger females have an earlier onset of reproduction and shorter generation times, lifetime reproductive success remains remarkably stable across individuals with different body sizes. Our study demonstrates a rapid shift to a faster pace of life in a mammal with a slow life history.
How well populations can cope with global warming will often depend on the evolutionary potential and plasticity of their temperature-sensitive, fitness-relevant traits. In Bechstein's bats (Myotis bechsteinii), body size has increased over the last decades in response to warmer summers. If this trend continues it may threaten populations as larger females exhibit higher mortality. To assess the evolutionary potential of body size, we applied a Bayesian ‘animal model’ to estimate additive genetic variance, heritability and evolvability of body size, based on a 25-year pedigree of 332 wild females. Both heritability and additive genetic variance were reduced in hot summers compared to average and cold summers, while evolvability of body size was generally low. This suggests that the observed increase in body size was mostly driven by phenotypic plasticity. Thus, if warm summers continue to become more frequent, body size likely increases further and the resulting fitness loss could threaten populations.
Animal species differ considerably in longevity. Among mammals, short-lived species such as shrews have a maximum lifespan of about a year, whereas long-lived species such as whales can live for more than two centuries. Because of their slow pace of life, long-lived species are typically of high conservation concern and of special scientific interest. This applies not only to large mammals such as whales, but also to small-sized bats and mole-rats. To understand the typically complex social behavior of long-lived mammals and protect their threatened populations, field studies that cover substantial parts of a species’ maximum lifespan are required. However, long-term field studies on mammals are an exception because the collection of individualized data requires considerable resources over long time periods in species where individuals can live for decades. Field studies that span decades do not fit well in the current career and funding regime in science. This is unfortunate, as the existing long-term studies on mammals yielded exciting insights into animal behavior and contributed data important for protecting their populations. Here, I present results of long-term field studies on the behavior, demography, and life history of bats, with a particular focus on my long-term studies on wild Bechstein’s bats. I show that long-term studies on individually marked populations are invaluable to understand the social system of bats, investigate the causes and consequences of their extraordinary longevity, and assess their responses to changing environments with the aim to efficiently protect these unique mammals in the face of anthropogenic global change.
Animals often respond to climate change with changes in morphology, e.g., shrinking body size with increasing temperatures, as expected by Bergmann’s rule. Because small body size can have fitness costs for individuals, this trend could threaten populations. Recent studies, however, show that morphological responses to climate change and the resulting fitness consequences cannot be generalized even among related species. In this long-term study, we investigate the interaction between ambient temperature, body size and survival probability in a large number of individually marked wild adult female Natterer’s bats (Myotis nattereri). We compare populations from two geographical regions in Germany with a different climate. In a sliding window analysis, we found larger body sizes in adult females that were raised in warmer summers only in the northern population, but not in the southern population that experienced an overall warmer climate. With a capture-mark-recapture approach, we showed that larger individuals had higher survival rates, demonstrating that weather conditions in early life could have long-lasting fitness effects. The different responses in body size to warmer temperatures in the two regions highlight that fitness-relevant morphological responses to climate change have to be viewed on a regional scale and may affect local populations differently.
Background
Hibernation allows species to conserve energy and thereby bridge unfavorable environmental conditions. At the same time, hibernation imposes substantial ecological and physiological costs. Understanding how hibernation timing differs within and between species can provide insights into the underlying drivers of this trade-off. However, this requires individualized long-term data that are often unavailable. Here, we used automatic monitoring techniques and a reproducible analysis pipeline to assess the individualized hibernation phenology of two sympatric bat species. Our study is based on data of more than 1100 RFID-tagged Daubenton’s bats (Myotis daubentonii) and Natterer’s bats (Myotis nattereri) collected over seven years at a hibernaculum in Germany. We used linear mixed models to analyze species-, sex- and age-specific differences in entrance, emergence and duration of the longest continuous period spent in the hibernaculum.
Results
Overall, Daubenton’s bats entered the hibernaculum earlier and emerged later than Natterer’s bats, resulting in a nearly twice as long hibernation duration. In both species, adult females entered earlier and emerged from hibernation later than adult males. Hibernation duration was shorter for juveniles than adults with the exception of adult male Natterer’s bats whose hibernation duration was shortest of all classes. Finally, hibernation timing differed among years, but yearly variations in entrance and emergence timing were not equally shifted in both species.
Conclusions
Our results suggest that even in sympatric species, and across sex and age classes, hibernation timing may be differentially affected by environmental conditions. This highlights the necessity of using individualized information when studying the impact of changing environments on hibernation phenology.
Hibernation is a widespread adaptation in animals to seasonally changing environmental conditions. In the face of global anthropogenic change, information about plastic adjustments to environmental conditions and associated mortality costs are urgently needed to assess population persistence of hibernating species. Here, we used a five-year data set of 1047 RFID-tagged individuals from two bat species, Myotis nattereri and Myotis daubentonii that were automatically recorded each time they entered or left a hibernaculum. Because the two species differ in foraging strategy and activity pattern during winter, we expected species–specific responses in the timing of hibernation relative to environmental conditions, as well as different mortality costs of early departure from the hibernaculum in spring. Applying mixed-effects modelling, we disentangled population-level and individual-level plasticity in the timing of departure. To estimate mortality costs of early departure, we used both a capture mark recapture analysis and a novel approach that takes into account individual exposure times to mortality outside the hibernaculum. We found that the timing of departure varied between species as well as among and within individuals, and was plastically adjusted to large-scale weather conditions as measured by the NAO (North Atlantic Oscillation) index. Individuals of M. nattereri, which can exploit milder temperatures for foraging during winter, tuned departure more closely to the NAO index than individuals of M. daubentonii, which do not hunt during winter. Both analytical approaches used to estimate mortality costs showed that early departing individuals were less likely to survive until the subsequent hibernation period than individuals that departed later. Overall, our study demonstrates that individuals of long-lived hibernating bat species have the potential to plastically adjust to changing climatic conditions, although the potential for adjustment differs between species.