Automatic monitoring of wildlife is becoming a critical tool in the field of ecology. In particular, Radio-Frequency IDentification (RFID) is now a widespread technology to assess the phenology, breeding, and survival of many species. While RFID produces massive datasets, no established fast and accurate methods are yet available for this type of data processing. Deep learning approaches have been used to overcome similar problems in other scientific fields and hence might hold the potential to overcome these analytical challenges and unlock the full potential of RFID studies. We present a deep learning workflow, coined "RFIDeep", to derive ecological features, such as breeding status and outcome, from RFID mark-recapture data. To demonstrate the performance of RFIDeep with complex datasets, we used a long-term automatic monitoring of a long-lived seabird that breeds in densely packed colonies, hence with many daily entries and exits. To determine individual breeding status and phenology and for each breeding season, we first developed a one-dimensional convolution neural network (1D-CNN) architecture. Second, to account for variance in breeding phenology and technical limitations of field data acquisition, we built a new data augmentation step mimicking a shift in breeding dates and missing RFID detections, a common issue with RFIDs. Third, to identify the segments of the breeding activity used during classification, we also included a visualisation tool, which allows users to understand what is usually considered a "black box" step of deep learning. With these three steps, we achieved a high accuracy for all breeding parameters: breeding status accuracy = 96.3%; phenological accuracy = 86.9%; breeding success accuracy = 97.3%. RFIDeep has unfolded the potential of artificial intelligence for tracking changes in animal populations, multiplying the benefit of automated mark-recapture monitoring of undisturbed wildlife populations. RFIDeep is an open source code to facilitate the use, adaptation, or enhancement of RFID data in a wide variety of species. In addition to a tremendous time saving for analyzing these large datasets, our study shows the capacities of CNN models to autonomously detect ecologically meaningful patterns in data through visualisation techniques, which are seldom used in ecology.
The properties of competition models where all individuals are identical are relatively well-understood; however, juveniles and adults can experience or generate competition differently. We study here structured competition models in discrete time that allow multiple life history parameters to depend on adult or juvenile population densities. While the properties of such models are less well-known, a numerical study with Ricker density-dependence suggested that when competition coefficients acting on juvenile survival and fertility reflect opposite competitive hierarchies, stage structure could foster coexistence. We revisit and expand those results using models more amenable to mathematical analysis. First, through a Beverton-Holt two-species juvenile-adult model, we obtain analytical expressions explaining how this coexistence emerging from life-history complexity can occur. Second, we show using a community-level sensitivity analysis that such emergent coexistence is robust to perturbations of parameter values. Finally, we ask whether these results extend from two to many species, using simulations. We show that they do not, as coexistence emerging from life-history complexity is only seen for very similar life-history parameters. Such emergent coexistence is therefore not likely to be a key mechanism of coexistence in very diverse ecosystems.
We report observations of alien dandelion (Taraxacum officinale group) consumption in an 15 opportunistic predatory seabird, the brown skua (Stercorarius antarcticus lonnbergi), from a natural 16 population on île Verte within the Kerguelen archipelago. Observations on a nearby island confirm that 17 this behaviour is not specific to our study area, paving the way to future studies investigating whether 18 this consumer innovation prevails in skua populations and results in dietary benefits in skuas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.