We are pleased to announce our Machine Learning Virtual Issue is now online.
This collection of MEE articles showcases exciting advances and applications of machine learning (ML) across a wide range of ecological and evolutionary disciplines.
From the analysis of reef structure and tree crowns, to species and individual animal identification, biological overlap, content analysis, biodiversity assessment and counting animals, ML automates the extraction of meaningful information from large digital collections.
Our Associate Editors Arthur Porto, Marta Vidal-Garcia, Miguel Acevedo, Theoni Photopoulou and Sarab Sethi curated this virtual issue by selecting their favourite MEE articles that use machine learning. Find out below why these papers were chosen, and how they are helping to progress research in ecology and evolution.
Sequencing ultraconserved DNA for phylogenetic research is a hot topic in evolution right now. As the name implies, Ultraconserved Elements (UCEs) are regions of the genome that are nearly identical among distantly related organisms. They can provide useful information for difficult phylogenetic questions. The list of advantages is long – among others, UCEs are:
phylogenetically informative on different timescales.
A key reason for the method’s success is the developers’ commitment to full transparency, active tutoring, and willingness to help next-gen sequencing newbies like me to get started. Help is just a github-issue post away.
Five years ago at Evolution 2014, ‘The Dark Side of Phylogenetics’ symposium (organised by Natalie Cooper) explored some of the issues with phylogenetic comparative methods (PCMs). This year at Evolution 2019, Michael Landis and Rosana Zenil-Ferguson are organising a contrasting ‘Bright Side of Phylogenetics‘ spotlight session (featuring Michael Matschiner). They aim to promote research that has overcome these pitfalls and that explores innovations in phylogenetics. Clearly they found our lack of faith disturbing.
Natalie and Michael have created a Virtual Issue to complement the spotlight session: Phylogenetics and Comparative Methods: The Bright and Dark Sides. It highlights recent Methods in Ecology and Evolution papers that feature either the ‘Bright Side’ or ‘Dark Side’ of phylogenetics and comparative methods. This Virtual Issue also highlights the diversity of researchers around the world working on these exciting questions. We hope you have a good feeling about it! Continue reading →
At a time when data is everywhere, and data science is being talked about as the future in different fields, a method that produces huge amounts of multimedia data is camera-trapping. We need ways to manage these kinds of media data efficiently. ViXeN is an attempt to do just that.
Camera traps have been a game-changer for ecological studies, especially those involving mammals in the wild. This has resulted in an increasing amount of camera trap datasets. However, the tools to manage camera trap data tend to be very specific and customised for images. They typically come with stringent data organisation requirements. There’s a growing amount of multimedia datasets and a lack of tools that can manage several types of media data.
In ‘ViXeN: An open‐source package for managing multimedia data’ we try to fix this visible gap. Camera trap management is a very specific a use-case. We thought that the field was missing general-purpose tools, capable of handling a variety of media data and formats, that were also free and open source. ViXeN was born from this idea. It stands for View eXtract aNnotate (media data). The name is also an ode to the canids I was studying at the time which included two species of foxes.
The latest Methods in Ecology and Evolution Virtual Issue – ‘Integrating Evolution and Ecology‘ – is in honour of the late Isabelle Olivieri (1957-2016): an international, interdisciplinary and ground-breaking biologist. It was edited by Louise Johnson and James Bullock and features papers on topics she researched, and in many cases pioneered. But it might perhaps have been more difficult to find 15 Methods papers on areas outside of Isabelle’s research interests!
Isabelle was the first Professor of Population Genetics at Montpellier, a past President of the European Society for Evolutionary Biology (2007-2009), and a member of the European Molecular Biology Organization. She spanned subject boundaries as easily as she collaborated across geographical borders. Her publications range through metapopulation and dispersal ecology, host-parasite coevolution, life history, invasive species and conservation ecology. In keeping with this breadth of interests, she also combined theory easily with experiment, and worked with a wide range of study systems from mites to Medicago. Continue reading →
Datasets used by quantitative ecologists are getting more and more complex. So we need more complex models, such as hierarchical and complex spatial models. Typically, Bayesian approaches such as Markov chain Monte Carlo have been used. But these methods can be slow, making it infeasible to fit some models.
Statistical and quantitative methods within ecology have increased substantially in recent years. This rise can be attributed both to the growing need to address global environmental change issues, as well as the increase in data sources to address these challenges. Continue reading →
Working on FLightR, the package for analysis of data obtained from solar geolocation tracking devices, we were haunted by the unpleasant feeling of investing in technology which will soon be out of date. Until now solar geolocators have been popular in ornithological studies. This is because they’re small, light-weight (< 1/3 g) tracking devices that can be deployed even on miniature birds, such as swallows and warblers. They’ve also been the longest-lasting data loggers, with the most storage space and, of course, the most affordable ones.
Are Solar Geolocators Finished?
There are apparent drawbacks of using this technique though. To begin with, solar geolocation simply does not work for some species. You can’t use it to study birds living in dense tropical forests or in cavities, because of the light-pattern bias. For the same reason, it doesn’t provide fantastic results in light-polluted areas. Data from geolocators cannot be retrieved remotely, and this is why you need to have high recapture rates for the species you’re studying. Continue reading →
Today, we’re pleased to announce that we’re launching a new article type for Methods in Ecology and Evolution: Practical Tools. Like our Applications articles, Practical Tools will be short papers(up to 3000 words). They’ll focus on new field techniques, equipment or lab protocols. From this point forward, our Applications papers will solely focus on software and code.
Practical tools need to clearly demonstrate how tools designed for specific systems or problems can be adapted for more general use. Online supporting information can include specific instructions, especially for building equipment. You can find some examples of Applications that would now fit into this article type here and here.
The standard approach to quantifying natural selection, developed by Lande and Arnold, does not allow for comparable metrics between linear (i.e. selection on the mean phenotype) and nonlinear (i.e. selection on all other aspects of the phenotypic distribution, including variance and the number of modes) selection gradients. Jonathan Henshaw’s winning submission provides the first integrated measure of the strength of selection that applies across qualitatively different selection regimes (e.g. directional, stabilizing or disruptive selection). Continue reading →