Search

Prey distribution acts at multiple spatial scales to influence foraging success by predators. The overall distribution of prey may shape foraging ranges, the distance between patches may influence the ability of predators to detect and move between profitable areas, and individual patch characteristics may affect prey capture efficiency., In this study, we assessed relationships between spatially explicit patterns of prey capture by a central place forager, the little penguin (using GPS tracking and accelerometry), and the distribution of aggregations of potential forage fish prey (using boat-based active acoustics) in eastern Australia. We used complementary resource selection functions to estimate the distribution of both prey captures and aggregations across the study area, based on a suite of habitat characteristics., We found that 99% of prey captures by penguins occurred in the top 20 m of the water column. The estimated distribution of prey captures across the study area was similar to the distribution of aggregations above 20 m depth, indicating that penguins effectively matched the local distribution of their prey., The distances between consecutive prey captures followed a bimodal distribution, with means of 8·1 ± 2·2 and 57·4 ± 1·7 m. Based on the length of aggregations and the distances separating aggregations along survey transects, this implies that foraging behaviour occurs on multiple spatial scales corresponding to within-patch and between-patch movements respectively., Morphological characteristics of aggregations above 20 m depth were important for explaining variance in the number of prey caught by penguins in an area, with penguins catching more prey where aggregations were relatively dense, compact and shallow., These results reveal spatially explicit patterns of prey capture, and provide a framework for understanding how features of prey distribution influence prey intake by predators in patchy environments., A is available for this article. [ABSTRACT FROM AUTHOR]

Where, when and how much animals eat provide valuable insights into their ecology. In this paper, we present a comparative analysis between Support Vector Machine (SVM) and Input Delay Neural Network (IDNN) models to identify prey capture events from penguin accelerometry data. A pre-classified dataset of 3D time-series data from back-mounted accelerometers was used. We trained both the models to classify the penguins’ behavior at intervals as either ‘prey handling’ or ‘swimming’. The aim was to determine whether IDNN could achieve the same level of classification accuracy as SVM, but with reduced memory demands. This would enable the IDNN model to be embedded on the accelerometer micro-system itself, and hence reduce the magnitude of the output data to be uploaded. Based on the classification results, this paper provides an analysis of the two models from both an accuracy and applicability point of view. The experimental results show that both models achieve an equivalent accuracy of approx. 85% using the featured data, with a memory demand of 0.5 kB for IDNN and 0.7 Mb for SVM. The raw accelerometer data let us improve the generalizability of the models with a slightly lower accuracy to around 80%. This indicates that the IDNN model can embed on the accelerometer itself, reducing problems associated with raw time-series data retrieval and loss. [ABSTRACT FROM AUTHOR]

Determining where, when and how much animals eat is fundamental to understanding their ecology. We developed a technique to identify a prey capture signature for little penguins from accelerometry, in order to quantify food intake remotely. We categorised behaviour of captive penguins from HD video and matched this to time-series data from back-mounted accelerometers. We then trained a support vector machine (SVM) to classify the penguins' behaviour at 0.3 s intervals as either 'prey handling' or 'swimming'. We applied this model to accelerometer data collected from foraging wild penguins to identify prey capture events. We compared prey capture and non-prey capture dives to test the model predictions against foraging theory. The SVM had an accuracy of 84.95±0.26% (mean ± s.e.) and a false positive rate of 9.82+0.24% when tested on unseen captive data. For wild data, we defined three independent, consecutive prey handling observations as representing true prey capture, with a false positive rate of 0.09%. Dives with prey captures had longer duration and bottom times, were deeper, had faster ascent rates, and had more 'wiggles' and 'dashes' (proxies for prey encounter used in other studies). The mean (±s.e.) number of prey captures per foraging trip was 446.6±66.28. By recording the behaviour of captive animals on HD video and using a supervised machine learning approach, we show that accelerometry signatures can classify the behaviour of wild animals at unprecedentedly fine scales. [ABSTRACT FROM AUTHOR]