ARAmédée Roy

Amédée Roy

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Amédée Roy has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Wind pattern oscillations explain seabird movements at-sea: a nested multiscale approach

    by Amedee Roy, Karine C Delord, Christophe Barbraud, Pascal Terray

    Wind has a strong influence on the flight characteristics, movements, energetics, demography, life-history traits and biogeography of flying animals. With climate change affecting atmospheric circulation patterns at different time scales, understanding the links between wind and animal movements is crucial for predicting its impact on flying biodiversity. Most studies on the relationship between wind and seabird movements have, however, focused on local scales, exploring birds’ perceptive sensitivity to local wind. In this study, we examine low-level wind pattern oscillations in the Southern Indian Ocean at multiple time scales to explain the local- to large-scale movements of the Amsterdam albatross. Adult individuals exhibited smooth trajectories, strongly correlated with seasonal, intra-seasonal or interannual wind oscillations. Conversely, younger individuals displayed more erratic and exploratory movements, often being swept away by eastward moving low-pressure systems at a synoptic time scale. Our results suggest that Amsterdam albatrosses can learn and adapt to the annual and monthly low-level wind climatology and interannual variability of the Southern Indian Ocean. This also highlights the importance of investigating seabird movements in relation to broader-scale wind patterns to support their conservation in a changing climate due to human activities. A robust assessment of regional circulation response to climate change for upcoming decades could help project the impact of climate change on seabird movements and mitigate its effects.

  • Open Access

    Enhanced forecasting of bird nocturnal migration intensity in relation to previous days and synoptic weather patterns

    by Amédée Roy, Thibault Désert, Vincent Delcourt, Cécile Bon, Baptiste Schmid

    Operational bird migration forecast models have recently offered promising perspectives for mitigating the impacts of human activities on avifauna. These models improve on simple phenological expectations by harnessing the intricate relationship between bird movements and weather conditions to forecast migration fluxes days in advance. However, state-of-the-art models face limitations as bird fluxes are often simply modelled as a response to local and instantaneous weather without accounting for previous and synoptic weather patterns. This study focuses on enhancing bird migration forecasts by evaluating the contributions of weather dynamics at various spatial and temporal scales. We use bird vertical density data from 9 French weather radars over 6 years and employ gradient-boosted regression trees for predictions. Dimension reduction tools are used to describe local and continental-scale weather conditions from the previous three days. We also explore the contributions of the different meteorological metrics considered using explainable regression trees tools. Our model improved phenology models by explaining about 1.3 and 2.25 times more additional variance than approaches based on local and instantaneous weather conditions in spring and autumn, respectively. Local and instantaneous weather metrics contributed the most, but they mainly helped identifying nights with low migration. In contrast, weather metrics for previous 3 days were crucial to forecast highest intensity migration events, as they enabled to account for bird accumulation in relation to unfavorable weather locally and remotely. This study enhanced forecast accuracy and contributed to a deeper understanding of the factors influencing bird migration. It enabled the identification local and synoptic weather patterns related to important migration events without a priori knowledge. It is therefore easy to interpret, easy to transfer to other ecological systems, and promising for the accurate forecast of migration peaks. Forecasted peaks can guide conservation efforts, for example by dimming lights for birds at night or by shutting down wind turbines.


  • Open Access

    Machine and deep learning approaches to understand and predict habitat suitability for seabird breeding

    by Antonio Garcia‐Quintas, Amédée Roy, Christophe Barbraud, Hervé Demarcq, Dennis Denis, Sophie Lanco Bertrand

    The way animals select their breeding habitat may have great impacts on individual fitness. This complex process depends on the integration of information on various environmental factors, over a wide range of spatiotemporal scales. For seabirds, breeding habitat selection integrates both land and sea features over several spatial scales. Seabirds explore these features prior to breeding, assessing habitats' quality. However, the information‐gathering and decision‐making process by seabirds when choosing a breeding habitat remains poorly understood. We compiled 49 historical records of larids colonies in Cuba from 1980 to 2020. Then, we predicted potentially suitable breeding sites for larids and assessed their breeding macrohabitat selection, using deep and machine learning algorithms respectively. Using a convolutional neural network and Landsat satellite images we predicted the suitability for nesting of non‐monitored sites of this archipelago. Furthermore, we assessed the relative contribution of 18 land‐ and marine‐based environmental covariates describing macrohabitats at three spatial scales (i.e. 10, 50 and 100 km) using random forests. Convolutional neural network exhibited good performance at training, validation and test (F1‐scores >85%). Sites with higher habitat suitability (p > .75) covered 20.3% of the predicting area. Larids breeding macrohabitats were sites relatively close to main islands, featuring sparse vegetation cover and high chlorophyll‐a concentration at sea in 50 and 100 km around colonies. Lower sea surface temperature at larger spatial scales was determinant to distinguish the breeding from non‐breeding sites. A more comprehensive understanding of the seabird breeding macrohabitats selection can be reached from the complementary use of convolutional neural networks and random forest models. Our analysis provides crucial knowledge in tropical regions that lack complete and regular monitoring of seabirds' breeding sites.


  • Open Access

    Using generative adversarial networks (GAN) to simulate central‐place foraging trajectories

    by Amédée Roy, Ronan Fablet, Sophie Lanco Bertrand

    Miniature electronic devices have recently enabled ecologists to document relatively large amounts of animal trajectories. Modelling such trajectories may contribute to explaining the mechanisms underlying observed behaviours and to clarifying ecological processes at the scale of the population by simulating multiple trajectories. Existing approaches to animal movement modelling have mainly addressed the first objective, and are often limited when used for simulation purposes. Individual‐based models generally rely on ad hoc formulation and their empirical parametrization lacks generability, while random walks based on mathematically sound statistical inference typically consist of first‐order Markovian models calibrated at the local scale which may lead to overly simplistic description and simulation of animal trajectories. We investigate a recent deep learning tool—generative adversarial networks (GAN)—to simulate animal trajectories. GANs consist of a pair of deep neural networks that aim to capture the data distribution of some experimental dataset. They enable the generation of new instances of data that share statistical properties. This study aims at identifying relevant deep network architectures to simulate central‐place foraging trajectories, as well as at evaluating GANs drawbacks and benefits over classical methods, such as state‐switching hidden Markov models (HMM). We demonstrate the outstanding ability of deep convolutional GANs to simulate and to capture medium‐ to large‐scale properties of seabird foraging trajectories. GAN‐derived synthetic trajectories reproduced the Fourier spectral density of observed trajectories better than those simulated using HMMs. However, unlike HMMs, GANs do not adequately capture local‐scale descriptive statistics, such as step speed distributions. GANs provide a new likelihood‐free approach to calibrate complex stochastic processes and thus open new research avenues for animal movement modelling. We discuss the potential uses of GANs in movement ecology and future developments to better capture local‐scale features. In this context, embedding HMM‐based priors in GAN schemes appears as a promising research direction.


  • Open Access

    Deep inference of seabird dives from GPS-only records: Performance and generalization properties

    by Amédée Roy, Sophie Lanco Bertrand, Ronan Fablet

    At-sea behaviour of seabirds have received significant attention in ecology over the last decades as it is a key process in the ecology and fate of these populations. It is also, through the position of top predator that these species often occupy, a relevant and integrative indicator of the dynamics of the marine ecosystems they rely on. Seabird trajectories are recorded through the deployment of GPS, and a variety of statistical approaches have been tested to infer probable behaviours from these location data. Recently, deep learning tools have shown promising results for the segmentation and classification of animal behaviour from trajectory data. Yet, these approaches have not been widely used and investigation is still needed to identify optimal network architecture and to demonstrate their generalization properties. From a database of about 300 foraging trajectories derived from GPS data deployed simultaneously with pressure sensors for the identification of dives, this work has benchmarked deep neural network architectures trained in a supervised manner for the prediction of dives from trajectory data. It first confirms that deep learning allows better dive prediction than usual methods such as Hidden Markov Models. It also demonstrates the generalization properties of the trained networks for inferring dives distribution for seabirds from other colonies and ecosystems. In particular, convolutional networks trained on Peruvian boobies from a specific colony show great ability to predict dives of boobies from other colonies and from distinct ecosystems. We further investigate accross-species generalization using a transfer learning strategy known as ‘fine-tuning’. Starting from a convolutional network pre-trained on Guanay cormorant data reduced by two the size of the dataset needed to accurately predict dives in a tropical booby from Brazil. We believe that the networks trained in this study will provide relevant starting point for future fine-tuning works for seabird trajectory segmentation.


  • Open Access

    Generative Adversarial Networks (GAN) for the simulation of central-place foraging trajectories

    by Amédée Roy, Sophie Lanco Bertrand, Ronan Fablet

    A bstract: Miniature electronic device such as GPS have enabled ecologists to document relatively large amount of animal trajectories. Modeling such trajectories may attempt (1) to explain mechanisms underlying observed behaviors and (2) to elucidate ecological processes at the population scale by simulating multiple trajectories. Existing approaches to animal movement modeling mainly addressed the first objective and they are yet soon limited when used for simulation. Individual-based models based on ad-hoc formulation and empirical parametrization lack of generability, while state-space models and stochastic differential equations models, based on rigorous statistical inference, consist in 1st order Markovian models calibrated at the local scale which can lead to overly simplistic description of trajectories. We introduce a ‘state-of-the-art’ tool from artificial intelligence - Generative Adversarial Networks (GAN) - for the simulation of animal trajectories. GAN consist in a pair of deep neural networks that aim at capturing the data distribution of some experimental dataset, and that enable the generation of new instances of data that share statistical similarity. In this study, we aim on one hand to identify relevant deep networks architecture for simulating central-place foraging trajectories and on the second hand to evaluate GAN benefits over classical methods such as state-switching Hidden Markov Models (HMM). We demonstrate the outstanding ability of GAN to simulate ‘realistic’ seabirds foraging trajectories. In particular, we show that deep convolutional networks are more efficient than LSTM networks and that GAN-derived synthetic trajectories reproduce better the Fourier spectral density of observed trajectories than those simulated using HMM. Therefore, unlike HMM, GAN capture the variability of large-scale descriptive statistics such as foraging trips distance, duration and tortuosity. GAN offer a relevant alternative to existing approaches to modeling animal movement since it is calibrated to reproduce multiple scales at the same time, thus freeing ecologists from the assumption of first-order markovianity. GAN also provide an ultra-flexible and robust framework that could further take environmental conditions, social interactions or even bio-energetics model into account and tackle a wide range of key challenges in movement ecology.


  • Did the animal move? A cross-wavelet approach to geolocation data reveals year-round whereabouts of a resident seabird

    by Amédée Roy, Karine Delord, Guilherme T. Nunes, Christophe Barbraud, Leandro Bugoni, Sophie Lanco-Bertrand


  • Open Access

    Deep inference of seabird dives from GPS-only records: performance and generalization properties

    by Amédée Roy, Sophie Lanco Bertrand, Ronan Fablet

    A bstract: At-sea behaviour of seabirds have received significant attention in ecology over the last decades as it is a key process in the ecology and fate of these populations. It is also, through the position of top predator that these species often occupy, a relevant and integrative indicator of the dynamics of the marine ecosystems they rely on. Seabird trajectories are recorded through the deployment of GPS, and a variety of statistical approaches have been tested to infer probable behaviours from these location data. Recently, deep learning tools have shown promising results for the segmentation and classification of animal behaviour from trajectory data. Yet, these approaches have not been widely used and investigation is still needed to identify optimal network architecture and to demonstrate their generalization properties. From a database of about 300 foraging trajectories derived from GPS data deployed simultaneously with pressure sensors for the identification of dives, this work has benchmarked deep neural network architectures trained in a supervised manner for the prediction of dives from trajectory data. It first confirms that deep learning allows better dive prediction than usual methods such as Hidden Markov Models. It also demonstrates the generalization properties of the trained networks for inferring dives distribution for seabirds from other colonies and ecosystems. In particular, convolutional networks trained on Peruvian boobies from a specific colony show great ability to predict dives of boobies from other colonies and from distinct ecosystems. We further investigate accross-species generalization using a transfer learning strategy known as ‘fine-tuning’. Starting from a convolutional network pre-trained on Guanay cormorant data reduced by two the size of the dataset needed to accurately predict dives in a tropical booby from Brazil. We believe that the networks trained in this study will provide relevant starting point for future fine-tuning works for seabird trajectory segmentation. To make easier such applications, we share online the different models we trained on the considered datasets ( https://github.com/AmedeeRoy/BirdDL/models ). Author Summary: Over the last decades, the use of miniaturized electronic devices enabled the tracking of many wide-ranging animal species. The deployment of GPS has notably informed on migratory, habitat and foraging strategies of numerous seabird species. A key challenge in movement ecology is to identify specific behavioural patterns (e.g. travelling, resting, foraging) through the observed movement data. In this work, we address the inference of seabird diving behaviour from GPS data using deep learning methods. We demonstrate the performance of deep networks to accurately identify movement patterns from GPS data over state-of-the-art tools, and we illustrate their great accross-species generalization properties (i.e. the ability to generalize prediction from one seabird species to aother). Our results further supports the relevance of deep learning schemes as ‘ready-to-use’ tools which could be used by ecologists to segmentate animal trajectories on new (small) datasets, including when these datasets do not include groundtruthed labelled data for a supervised training.


  • Open Access

    Did The Animal Move? A Cross-Wavelet Approach to Qeolocation Data Reveals Year-Round Whereabouts of A Resident Seabird

    by Amédée Roy, Karine Delord, Guilherme T. Nunes, Christophe Barbraud, Leandro Bugoni, Sophie Lanco-Bertrand

    Considerable progress in our understanding of long-distance migration has been achieved thanks to the use of small lightweight geolocator devices (GLS). Errors of geolocation are however important, difficult to estimate, have a complex structure leading to poor precision and accuracy. Thus, the study of short-distance migrants or resident birds remains challenging. Here we aimed at elucidating the sex-specific marine space uses of a resident tropical seabird, the masked booby ( Sula dactylatra ) over the full annual life cycle at the Fernando de Noronha archipelago (Brazil), using GLS and synchronicity analyses between movement and saltwater immersion data. Masked boobies (n = 31) showed a resident behaviour over their entire annual cycle. We inferred from the wavelet analysis that birds traveled way and back from the colony on consecutive trips of short length (~ 2-4 days) and short range (~ 100-300 km) from the east of the colony. Duration and range of trips depended on the sex of the individual and on the time of the year. Trip duration increased gradually from the end of the breeding period to the post-breeding period, probably due to the release of the central-place breeding constraints. During the pre-breeding period, females had farther ranges eastward and spent more time in water than males. Despite inherent limits of light-based geolocation, synchronicity analysis of geolocation data revealed year round whereabouts of the resident tropical masked booby and sex-specific movement behaviour, which could be used more broadly to investigate resident or short-migrants animal movement based on GLS data.