Applications for deep learning in ecology

By Sylvain Christin, É. Hervet, Nicolas Lecomte. 2018

557 citations recorded by the source corpus.

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.

Subfields: Developmental Biology, Ecological Modeling, Ecology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Developmental Biology

In Ecological Modeling

In Ecology

Citations in the corpus

Perspectives in machine learning for wildlife conservation (2021, background): “and actionable ecological insights (35) and is an increasingly popular approach in ecology (36, 37), especially due to increased computational power and rapid software advances of the last ten years.”
SLEAP: A deep learning system for multi-animal pose tracking (2022, methodology): “Methods for pose estimation, the task of predicting the location of animal parts in images, have grown in popularity as a state-of-the-art requirement for behavioral quantification across disciplines including neuroscience 3 and ecology 4 .”
Machine learning and deep learning—A review for ecologists (2022, background): “Several reviews have highlighted the potential of the recent advances in DL (Borowiec et al., 2022; Christin et al., 2019; Tuia et al., 2022 ; Wäldchen & Mäder, 2018 ), particularly for processing ecological data such as species recognition from video and audio analysis (Aodha et al., 2018 ; e.g.…”
Comparing sample bias correction methods for species distribution modeling using virtual species (2021, background): “…over explanation has been a trend in ecology over the past several decades (Clark et al. 2001, Evans et al. 2012, Houlahan et al. 2017, Maris et al. 2018) and has led to substantial developments in predictive ecology, such as machine learning methods (Christin et al. 2019, Rammer and Seidl 2019).”