Biology subjects

Christin, S.

Publications and source records attributed to Christin, S..

3 recordsLinked to original sources

bioRxiv2024

The collective application of shorebird tracking data to conservation

Addressing urgent conservation issues, like the drastic declines of North American migratory birds, requires creative, evidence-based, efficient, and collaborative approaches. Over 50% of monitored North American shorebird populations have lost over 50% of their abundance since 1980. To address these declines, we developed a partnership of scientists and practitioners called the Shorebird Science and Conservation Collective (hereinafter "the Collective"). Here, we present this successful case study as an example for others engaged in translational science. The Collective acts as an intermediary whereby dedicated staff collate and analyze data contributions from scientists to support knowledge requests from conservation practitioners. Data contributions from 74 organizations include over 6.7 million shorebird locations forming movement paths of 3,345 individuals representing 36 species tracked across the Americas. We describe the founding and structure of the Collective and conservation activities we supported in our first two years. As the volume of scientific data on animal movements continues to grow, groups like the Collective can be vital liaisons to rapidly integrate and interpret research to support conservation action.

ecology↗

bioRxiv2022

Introducing Mouffet, a unified framework to make model creation easier and more reproducible

O_LIBiological and ecological models are being increasingly used to explain the natural world. Model creation is an iterative process requiring two steps: training and evaluating the models. However, this process can become complex when multiple models are trained and evaluated at the same time. Besides, development steps can be lost, reducing the reproducibility of model creation. C_LIO_LIWe introduce Mouffet, an open-source Python framework that aims to make model creation easier, more robust, and more reproducible. It provides a set of configuration files and high-level Python interfaces that help managing data, training, and evaluating models. To improve reproducibility, every step of the model creation process, including the options used, are saved. C_LIO_LIMouffet introduces the notion of scenarios that allow users to define multiple training or evaluation tasks in a single configuration file. This not only facilitates model creation but enables users to define experimental plans to study the effect of selected parameters on training or evaluation. C_LIO_LIWhile initially developed for deep learning models, Mouffet is independent of the implementation of the models. Therefore, it could be successfully used to compare different modelling approaches. Besides, its ease of use makes it a choice tool for ecologists, even when not familiar with complex model creation. C_LI

ecology↗

bioRxiv2018

Applications for deep learning in ecology

A lot of hype has recently been generated around deep learning, a group of artificial intelligence approaches able to break accuracy records in pattern recognition. Over the course of just a few years, deep learning revolutionized several research fields such as bioinformatics or medicine. Yet such a surge of tools and knowledge is still in its infancy in ecology despite the ever-growing size and the complexity of ecological datasets. Here we performed a literature review of deep learning implementations in ecology to identify its benefits in most ecological disciplines, even in applied ecology, up to decision makers and conservationists alike. We also provide guidelines on useful resources and recommendations for ecologists to start adding deep learning to their toolkit. At a time when automatic monitoring of populations and ecosystems generates a vast amount of data that cannot be processed by humans anymore, deep learning could become a necessity in ecology.

ecology↗