Understanding Deep Learning

Post provided by Sylvain Christin

We have now entered the era of artificial intelligence. In just a few years, the number of applications using AI has grown tremendously, from self-driving cars to recommendations from your favourite streaming provider. Almost every major research field is now using AI. Behind all this, there is one constant: the reliance, in one way or another, on deep learning. Thanks to its power and flexibility, this new subset of AI approach is now everywhere, even in ecology we show in ‘Applications for deep learning in ecology’.

But what is deep learning exactly? What makes it so special?

Deep Learning: The Basics

Deep learning is a set of methods based on representation learning: a way for machines to automatically detect how to classify data from raw examples. This means they can detect features in data by themselves, without any prior knowledge of the system. While some models can learn without any supervision (i.e. they can learn to detect and classify objects without knowing anything about them) so far these models are outperformed by supervised models. Supervised models require labelled data to train. So, if we want the model to detect cars in pictures, it will need examples with cars in them to learn to recognise them.

Continue reading

Bats aren’t just for Halloween: Insectivorous Bats in North America

Post provided by CHLOE ROBINSON (@CVROBINSON92)

The Hoary bat (Lasiurus cinereus) is the most widespread bat in the US. ©Veronica Zamora-Gutierrez

Hello! This is my first post as Blog Editor for Methods in Ecology and Evolution and I’m thrilled to be starting with an exciting, thought-provoking topic in the wake of Halloween. But first, let me introduce myself. I currently work as a Postdoctoral Fellow and Project Manager in the Hajibabaei Lab at the Centre for Biodiversity Genomics (University of Guelph, ON, Canada) and my undergraduate and postgraduate degrees are both from Swansea University (UK). My research background is largely focused around the application of environmental DNA (i.e. free DNA found in natural environments) to detect and monitor aquatic species and answer ecological questions through both single-species detection and DNA metabarcoding.

At the moment, I’m working on the STREAM project, which combines community-based monitoring with DNA metabarcoding to gain a better understanding of freshwater health across Canada. One of my favourite parts about being in this position is the opportunity to get involved with other research being conducted in the Hajibabaei Lab. This is how I branched out into the wonderful world of bat ecology. Continue reading

Transparent Peer Review at Methods in Ecology and Evolution

©Matt Clark

We’re starting a new initiative to make our peer review process more open and visible. If you submit a manuscript to Methods in Ecology and Evolution from today onwards, you’ll be able to choose to make the review process transparent.

But what does that actually mean? How will the process work? And why are we doing it?

Keep reading to find out!

How Does Transparent Peer Review Work?

When you submit a manuscript to Methods in Ecology and Evolution, you’ll be asked if you’d like to be part of our transparent peer review model (every manuscript will be included by default, but you can opt out). If you choose to stay with the transparent peer review model and your manuscript is published, the peer reviewers’ reports, your responses, and the editors’ decisions will be published alongside your final article. You can see an example of how this might look here. Continue reading

‘Tis the Season for Modelling Mortalities

Post provided by ELIE GURARIE

A warning: Halloween is nigh, and the following post contains graphic real-life imagery of maggot-eaten eye-sockets and deadly pianos. Read on… if you dare!

A Death in the Woods 

In the vast and often frozen boreal forest of northern Canada there is a slow-burning forensic investigation into a death. The victim: a woodland caribou, an iconic species that is threatened or endangered throughout its range.

Kyle Joly

The scene is very much made for TV neo-Scandinavian neo-noir. From a not-too-luxurious regional office in the town of Fort Smith, just north of the Alberta border, over a steaming cup of coffee, world-weary biologist Allicia Kelly – who’s seen it all and then some – is monitoring the movements of collared animals on her computer screen. It’s the middle of May. The females, nearly all pregnant, are scattering to higher ground to find suitably cozy and secluded sites to calve. All is as peaceful and idyllic as a bunch of blips on a computer screen can be.

But then (cue slightly unsettling dissonance in the soundtrack) one of the little blips seems to have stopped moving. Kelly raises her eyebrow, tells herself to keep an eye out. A moment later she makes the call: “Team, we’ve got another ringer … let’s roll!Continue reading

A Move Towards Trait-Data Democracy: Creating the Ecological Trait-Data Standard Vocabulary

Post provided by FLORIAN D. SCHNEIDER

The past ten years brought a major game changer to ecological community and ecosystems research: functional trait data. This has shifted the focus from assessing and analysing ecosystems by not just the quantities of species but also those species’ qualities. Functional trait data can give us major insights into how communities are composed and how species assemblages evolve under certain environmental pressures. They also link community composition to ecosystem functioning and provide a framework for the assessment of communities across trophic levels and functional groups. Continue reading

aKIDemic Life: Empowering You to Navigate Life and Work

Post provided by Kirsty Nash

Most researchers I know are passionately invested in their research. Work consumes a significant amount of their focus, energy and time. But, researchers are so much more than that! Most of us have a life outside work that involves family, friends, even the odd hobby (if this isn’t the case and your life is purely about work, then read this).

Balancing or, more precisely, juggling the different parts of life can be taxing. Often academics and researchers face the competing demands of caring responsibilities, and the need to attend conferences, go on field trips or relocate for the next fixed-term contract. There are lots of resources out there to help researchers balance their home and work life, but, let’s be honest, who has the time to search for those resources?

This is where aKIDemic Life comes in. aKIDemic Life is a website built by academics for academics to empower parents and carers to navigate life and work. We curate free advice, tools and training, using the experience of researchers who have been through it. We want you to know that you’re not alone and to be able to quickly find the help you need, whatever your story. Continue reading

Reconnecting the Web of Life: Rewiring and Network Robustness

Post provided by VINICIUS A. G. BASTAZINI, JEF VIZENTIN-BUGONI and JINELLE H. SPERRY

Esta publicação no blogue também está disponível em português

Species Loss and Cascading Effects

Scale-throated Hermit (Phaethornis eurynome). ©Pedro Lorenzo.

Scale-throated Hermit (Phaethornis eurynome). ©Pedro Lorenzo.

Minimising the effects the ongoing Anthropocene mass extinction has become one of the main challenges of our era. The data suggest that the current rate of species loss is 100–1,000 greater than the background rates seen in the geological record. “But does it really matter if species are lost?” This question has permeated social and political debates. It’s usually used to demean conservation efforts. But it has also intrigued conservation scientists.

We know that species don’t occur alone in their environment. They’re entangled by their interactions, forming complex networks. In these networks the loss of one species may result in the loss of other species that depend on it. This process is known as co-extinction. Estimates of the magnitude of past and future extinction rates have often failed to account for the interdependence among species and the consequences of primary species loss on other species though. Continue reading

Religando a rede da vida: Reconexões de interações e a robustez de redes ecológicas

Postagem fornecida por VINICIUS A. G. BASTAZINI, JEF VIZENTIN-BUGONI and JINELLE H. SPERRY

This post is also available in English

Perda de espécies e efeitos em cascata

Scale-throated Hermit (Phaethornis eurynome). ©Pedro Lorenzo.

Rabo-branco-de-garganta-rajada (Phaethornis eurynome). ©Pedro Lorenzo.

Minimizar os efeitos do atual processo de extinção em massa do Antropoceno se tornou um dos principais desafios da nossa era. Os dados sugerem que a taxa atual de perda de espécies é 100-1.000 vezes maior do que as taxas de fundo observadas no registro geológico. “Mas realmente importa se uma espécie é perdida?” Essa questão que permeia os debates sociais e políticos, geralmente para desqualificar os esforços de conservação, também tem intrigado os cientistas da conservação.

Sabemos que as espécies não ocorrem sozinhas em seu ambiente. Elas estão  interligadas por suas interações ecológicas, formando redes complexas. Nessas redes, a perda de uma espécie pode resultar em um efeito dominó, culminando na perda secundária de outras espécies. Esse processo é conhecido como co-extinção. As estimativas da magnitude das taxas de extinção passadas e futuras muitas vezes falharam em explicar a interdependência entre as espécies e as conseqüências da perda primaria de espécies. Continue reading

Researchers Use Drones to Weigh Whales

Below is a press release about the Methods in Ecology and Evolution article ‘Estimating body mass of free‐living whales using aerial photogrammetry and 3D volumetrics‘ taken from the British Ecological Society.

A southern right whale female rolling on her side and exposing her lateral side to the surface while gently touching her calf. ©Fredrik Christiansen

Researchers have devised a way to accurately estimate the weight of free-living whales using only aerial images taken by drones. By measuring the body length, width and height of free-living southern right whales photographed by drones, researchers were able to develop a model that accurately calculated the body volume and mass of the whales.

Because of their large size and aquatic life, previously the only way to obtain data on the body mass of whales was to weigh dead or stranded individuals.

The innovative method can be used to learn more about the physiology and ecology of whales. “Knowing the body mass of free-living whales opens up new avenues of research. We will now be able to look at the growth of known aged individuals to calculate their body mass increase over time and the energy requirements for growth. We will also be able to look at the daily energy requirements of whales and calculate how much prey they need to consume.” said Assistant Professor Fredrik Christiansen from Aarhus Institute of Advanced Studies in Denmark and lead author of the study. Continue reading