Deep learning as a tool for ecology and evolution

Abstract

Deep learning is driving recent advances behind many everyday technologies, including speech and image recognition, natural language processing and autonomous driving. It is also gaining popularity in biology, where it has been used for automated species identification, environmental monitoring, ecological modelling, behavioural studies, DNA sequencing and population genetics and phylogenetics, among other applications. Deep learning relies on artificial neural networks for predictive modelling and excels at recognizing complex patterns. In this review we synthesize 818 studies using deep learning in the context of ecology and evolution to give a discipline‐wide perspective necessary to promote a rethinking of inference approaches in the field. We provide an introduction to machine learning and contrast it with mechanistic inference, followed by a gentle primer on deep learning. We review the applications of deep learning in ecology and evolution and discuss its limitations and efforts to overcome them. We also provide a practical primer for biologists interested in including deep learning in their toolkit and identify its possible future applications. We find that deep learning is being rapidly adopted in ecology and evolution, with 589 studies (64%) published since the beginning of 2019. Most use convolutional neural networks (496 studies) and supervised learning for image identification but also for tasks using molecular data, sounds, environmental data or video as input. More sophisticated uses of deep learning in biology are also beginning to appear. Operating within the machine learning paradigm, deep learning can be viewed as an alternative to mechanistic modelling. It has desirable properties of good performance and scaling with increasing complexity, while posing unique challenges such as sensitivity to bias in input data. We expect that rapid adoption of deep learning in ecology and evolution will continue, especially in automation of biodiversity monitoring and discovery and inference from genetic data. Increased use of unsupervised learning for discovery and visualization of clusters and gaps, simplification of multi‐step analysis pipelines, and integration of machine learning into graduate and postgraduate training are all likely in the near future.

Machine learning pipeline extracts biologically significant data automatically from avian monitoring videos

“…Machine learning approaches are becoming widely used in ecology in recent years (Borowiec et al, 2021). Here, we presented an excellent case study of machine learning assisted data collection that can obtain biologically meaningful results in existing datasets without further manual intervention.…”

“…Recent advances in deep learning (Borowiec et al, 2021) and computer vision (Weinstein, 2018a) allow quick and reliable information to be extracted from field data (Valletta et al, 2017). For example, machine learning methods have been successfully applied to solve problems with species identification (see Wäldchen and Mäder, 2018), bird song complexity measurement (see Pearse et al, 2018;Priyadarshani et al, 2018), social behaviour measurement (see Robie et al, 2017), and individual identification (Bogucki et al, 2019;Ferreira et al, 2020;Körschens et al, 2018;Schofield et al, 2019).…”

“…Since computing resources are much cheaper than human-labour, such approaches have immense potential in reducing the financial and time costs of data collection, evidenced by a recent increase in popularity for ecological applications (Borowiec et al, 2021;Tuia et al, 2022).…”

Field‐based adipose tissue quantification in sea turtles using bioelectrical impedance spectroscopy validated with CT scans and deep learning

“…Calibration of the BIS device was conducted by using deep learning, which enabled the automated adipose tissue identification and quantification. Deep learning approaches in ecology facilitate the classification, regression, and modeling of data (Borowiec et al, 2022 ). For example, deep learning has been used to identify, classify, and estimate the density of individuals, populations, and species (Christin et al, 2019 ).…”

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

“…Biological models have become an essential tool to better understand our world (Jackson et al, 2000; Shoemaker et al, 2021). They are now becoming more and more numerous and sophisticated, even more so with the recent progress made in machine learning, and especially deep learning (Borowiec et al, 2022; Christin et al, 2019; Guo et al, 2020). Such fast evolution, however, introduces challenges that make the creation and comparison of new models difficult, hampering their reproducibility and research potential.…”