Albatrosses respond adaptively to climate variability by changing variance in a foraging trait

Patrick, Samantha C.; Martin, Julien G. A.; Ummenhofer, Caroline C.; Corbeau, Alexandre; Weimerskirch, Henri

doi:10.1111/gcb.15735

Cited by 7 publications

(8 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for both species, predictions from models trained on data from both seasons showed similar agreement scores to the predictions made by models trained on data from a single season. Species, types of behaviour performed, and environmental conditions can shape the degree of variability recorded [54][55][56][57][58] . Changes in sea-ice conditions (as in extent and characteristics, for example), might lead Adélie penguins to move differently 59 and perhaps show high variability in behaviour.…”

Section: Discussionmentioning

confidence: 99%

“…In bio-logging and movement ecology, analyses on behavioural variation linked to environmental conditions are carried out primarily on location data, which currently constitute the most extensive animal movement dataset in terms of the number of individuals and species tracked 55 . Accelerometer datasets are also becoming suitable for these analyses 62 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets

Chimienti

Kato

Hicks

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Animal-borne tagging (bio-logging) generates large and complex datasets. In particular, accelerometer tags, which provide information on behaviour and energy expenditure of wild animals, produce high-resolution multi-dimensional data, and can be challenging to analyse. We tested the performance of commonly used artificial intelligence tools on datasets of increasing volume and dimensionality. By collecting bio-logging data across several sampling seasons, datasets are inherently characterized by inter-individual variability. Such information should be considered when predicting behaviour. We integrated both unsupervised and supervised machine learning approaches to predict behaviours in two penguin species. The classified behaviours obtained from the unsupervised approach Expectation Maximisation were used to train the supervised approach Random Forest. We assessed agreement between the approaches, the performance of Random Forest on unknown data and the implications for the calculation of energy expenditure. Consideration of behavioural variability resulted in high agreement (> 80%) in behavioural classifications and minimal differences in energy expenditure estimates. However, some outliers with < 70% of agreement, highlighted how behaviours characterized by signal similarity are confused. We advise the broad bio-logging community, approaching these large datasets, to be cautious when upscaling predictions, as this might lead to less accurate estimates of behaviour and energy expenditure.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets

Chimienti

Kato

Hicks

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…low variance around the new mean of individuals, Figure 1). Although such patterns in the variance provide additional metrics to monitor 53 , they are less likely to contain information about the risk of population collapse; rather, we propose such information lays in the temporal sequence of the different signals.…”

Section: Framework Detailsmentioning

confidence: 95%

A predictive timeline of wildlife population collapse

2023

View full text Add to dashboard Cite

Contemporary rates of biodiversity decline emphasize the need for reliable ecological forecasting, but current methods vary in their ability to predict the declines of real-world populations. Acknowledging that stressors effects start at the individual level, and that it is the sum of these individual-level effects that drives populations to collapse, shifts the focus of predictive ecology away from using predominantly abundance data. Doing so opens new opportunities to develop predictive frameworks that utilize increasingly available multi-dimensional data, which have previously been overlooked for ecological forecasting. Here, we propose that stressed populations will exhibit a predictable sequence of observable changes through time: changes in individuals' behaviour will occur as the first sign of increasing stress, followed by changes in fitness related morphological traits, shifts in the dynamics (e.g. birth rates) of populations, and finally abundance declines. We discuss how monitoring the sequential appearance of these signals may allow us to discern whether a population is increasingly at risk of collapse, or is adapting in the face of environmental change, providing a conceptual framework to develop new forecasting methods which combine multidimensional (e.g. behaviour, morphology, life history and abundance) data.

show abstract

“…low variance around the new mean of individuals, Figure 1). Although such patterns in the variance provide additional metrics to monitor (Patrick et al, 2021), they are less likely to contain information about the risk of population collapse; rather, we propose such information lays in the temporal sequence of the different signals.…”

Section: Framework Detailsmentioning

confidence: 95%

“…Environmental stressors may also increase the variance in behavioural metrics, e.g. poor environmental conditions enhanced the variability of foraging trip duration in young albatrosses (Patrick et al, 2021). Previous experience may also play a critical role in determining an individual's response to stressors.…”

Section: Figure Captionsmentioning

confidence: 99%

Timeline to collapse

Cerini

Childs

Clements

2022

Preprint

View full text Add to dashboard Cite

Contemporary rates of biodiversity decline emphasize the need for reliable ecological forecasting, but current methods vary in their ability to predict the declines of real-world populations. Acknowledging that stressors effects start at the individual level, and that it is the sum of these individual-level effects that drives populations to collapse, shifts the focus of predictive ecology away from using predominantly abundance data. Doing so opens new opportunities to develop predictive frameworks that utilize increasingly available multi-dimensional data, which have previously been overlooked for ecological forecasting. Here, we propose that stressed populations will exhibit a predictable sequence of observable changes through time: (i) changes in individuals' behaviour will occur as the first sign of increasing stress, followed by (ii) changes in fitness related morphological traits, (iii) shifts in the dynamics (e.g. birth rates) of populations, and finally (iv) abundance declines.We discuss how monitoring the sequential appearance of these signals may allow us to discern whether a population is increasingly at risk of collapse, or is adapting in the face of environmental change, providing a conceptual framework to develop new forecasting methods which combine multidimensional (e.g. behaviour, morphology, abundance) data.

show abstract

Albatrosses respond adaptively to climate variability by changing variance in a foraging trait

Cited by 7 publications

References 65 publications

The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets

The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets

A predictive timeline of wildlife population collapse

Timeline to collapse

Contact Info

Product

Resources

About