Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 249

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

Deep learning as a tool for ecology and evolution

Open access
Borowiec, Marek L., Dikow, Rebecca B., Frandsen, Paul B., McKeeken, Alexander, Valentini, Gabriele, White, Alexander E. · 2022 · Methods in Ecology and Evolution

Published version of a preprint

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1111/2041-210x.13901

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 217

  1. Abadi M., 2016, TensorFlow: A system for large‐scale machine learning, OSDI, 16, 265
  2. 10.1093/molbev/msaa038 · DOI
  3. Alvi M. S. Zisserman A. &Nellåker C.(2018).Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings.CoRR abs/1809.02169 · DOI · Paper page
  4. 10.1016/j.image.2020.115917 · DOI
  5. Badirli S. Picard C. J. Mohler G. Akata Z. &Dundar M.(2021).Classifying the unknown: Identification of insects by deep open‐set Bayesian learning.bioRxiv 2021.09.15.460492. · DOI
  6. 10.1098/rspb.2007.0458 · doi:10.1098/rspb.2007.0458
  7. 10.7717/peerj.8225 · DOI · Paper page
  8. 10.1038/s41467-020-18441-5 · DOI · Paper page
  9. 10.1007/BF00028502 · DOI
  10. 10.1073/pnas.2020596117 · DOI
  11. 10.7554/eLife.54507 · DOI
  12. Battey C. J. Coffing G. C. &Kern A. D.(2020).Visualizing population structure with variational autoencoders.bioRxiv e248278. · doi:10.1101/2020.08.12.248278
  13. 10.1073/pnas.1907375117 · DOI · Paper page
  14. 10.1093/genetics/162.4.2025 · DOI · Paper page
  15. 10.1016/j.ecoinf.2013.11.002 · DOI · Paper page
  16. 10.1109/TPAMI.2013.50 · DOI · Paper page
  17. 10.1016/j.ecoinf.2020.101137 · DOI
  18. 10.1038/s41598-019-47335-w · DOI
  19. 10.1111/j.1365-294X.2010.04690.x · DOI · Paper page
  20. Blischak P. D. Barker M. S. &Gutenkunst R. N.(2020).Chromosome‐scale inference of hybrid speciation and admixture with convolutional neural networks.bioRxiv 2020.06.29.159673. · doi:10.1101/2020.06.29.159673
  21. 10.1002/cyto.990150403 · DOI
  22. Boer M. J. &Vos R. A.(2018).Taxonomic classfification of ants (Formicidae) from images using deep learning.bioRxiv 407452. · DOI
  23. 10.1111/cobi.13226 · DOI
  24. 10.1371/journal.pone.0178751 · DOI · Paper page
  25. 10.1146/annurev-ecolsys-110316-022659 · DOI
  26. 10.1093/sysbio/syy019 · DOI
  27. 10.1109/ICCV48922.2021.00018 · DOI
  28. Cao K. Wei C. Gaidon A. Arechiga N. &Ma T.(2019).Learning imbalanced datasets with label‐distribution‐aware margin loss.arXiv 1906.07413.
  29. 10.1016/j.ecoinf.2021.101252 · DOI
  30. 10.1186/s12862-017-1014-z · DOI · Paper page
  31. 10.1126/sciadv.aba3274 · DOI
  32. Chege H. N.(2020).Rapid prototyping of species classifiers using deep learning: A guide for non‐experts.https://doi.org/10.22541/au.158316446.65534248 · DOI
  33. 10.1146/annurev-biodatasci-092820-114757 · DOI · Paper page
  34. 10.1002/ece3.6152 · DOI
  35. 10.1016/j.biocon.2019.108269 · DOI
  36. 10.1186/s13040-017-0155-3 · DOI · Paper page
  37. 10.1007/s10201-009-0275-7 · DOI
  38. Choi T., 2021, Proceedings of the AAAI Conference on Artificial Intelligence
  39. Chollet F., 2021, Deep learning with python
  40. Chollet F., 2018, Deep learning with R
  41. 10.1016/S0304-3800(01)00305-2 · DOI
  42. 10.1111/2041-210X.13494 · DOI
  43. 10.1002/ece3.6840 · DOI
  44. Collobert R., 2011, BigLearn, NIPS workshop
  45. Cortes C. Gonzalvo X. Kuznetsov V. Mohri M. &Yang S.(2017).AdaNet: Adaptive structural learning of artificial neural networks.arXiv 1607.01097.
  46. 10.1371/journal.pntd.0008904 · DOI
  47. 10.1111/nph.14855 · DOI · Paper page
  48. Das S., 2018, Nature read in black and White: Decolonial approaches to interpreting natural history, Journal of Natural Science Collections, 6, 4
  49. 10.2110/palo.2019.102 · DOI
  50. 10.1016/j.ympev.2019.106562 · DOI
  51. Dosovitskiy A. Beyer L. Kolesnikov A. Weissenborn D. Zhai X. Unterthiner T. Dehghani M. Minderer M. Heigold G. Gelly S. Uszkoreit J. &Houlsby N.(2020).An image is worth 16x16 words: Transformers for image recognition at scale.arXiv 2010.11929.
  52. Duhart C., 2019, 36th International Conference on Machine Learning, Long Beach
  53. 10.1038/s41562-019-0619-1 · DOI · Paper page
  54. 10.1016/j.ecoinf.2021.101500 · DOI
  55. 10.1111/2041-210X.13768 · DOI
  56. Falbel D., 2021, torch: Tensors and neural networks with ‘GPU’ acceleration
  57. 10.1038/s41592-018-0261-2 · DOI · Paper page
  58. 10.23919/EUSIPCO.2018.8553542 · DOI
  59. 10.1525/bio.2013.63.11.8 · doi:10.1525/bio.2013.63.11.8
  60. 10.1186/1472-6947-12-8 · DOI · Paper page
  61. 10.3390/biomimetics5010008 · DOI
  62. 10.1093/molbev/msy224 · DOI · Paper page
  63. 10.1111/1755-0998.13427 · DOI
  64. 10.1016/j.beproc.2018.01.008 · DOI
  65. 10.1099/00222615-40-3-170 · doi:10.1099/00222615-40-3-170
  66. 10.3390/s17092022 · DOI · Paper page
  67. 10.3389/fpls.2019.01321 · DOI
  68. 10.1016/j.compag.2020.105627 · DOI
  69. 10.7554/eLife.58145 · DOI
  70. Géron A., 2019, Hands‐on machine learning with Scikit‐learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems
  71. 10.1007/978-3-540-28650-9_5 · DOI · Paper page
  72. 10.1016/S0304-3800(01)00324-6 · DOI · Paper page
  73. Glassner A., 2021, Deep learning: A visual approach
  74. Goodfellow I., 2016, Deep learning
  75. Grandini M. Bagli E. &Visani G.(2020).Metrics for multi‐class classification: An overview.arXiv 2008.05756.
  76. Graving J. M. &Couzin I. D.(2020).VAE‐SNE: A deep generative model for simultaneous dimensionality reduction and clustering.bioRxiv 2020.07.17.207993. · DOI
  77. 10.1111/2041-210X.13132 · DOI
  78. 10.1016/j.tree.2015.12.007 · DOI
  79. 10.1038/34899 · DOI · Paper page
  80. 10.1038/s41598-019-50795-9 · DOI · Paper page
  81. 10.7554/eLife.48571 · DOI · Paper page
  82. Guo C., 2017, International conference on machine learning, 1321
  83. 10.1007/s11430-019-9584-9 · DOI
  84. Guyon I., 2008, Feature extraction: Foundations and applications
  85. 10.1111/2041-210X.12000 · DOI
  86. 10.1016/j.compind.2018.02.016 · DOI · Paper page
  87. 10.1002/ece3.5921 · DOI
  88. 10.1137/1.9781611976236.18 · DOI
  89. 10.1534/g3.119.400596 · DOI
  90. 10.1126/science.1736360 · DOI · Paper page
  91. 10.1111/2041-210X.13827 · DOI
  92. 10.1111/j.1095-8312.1999.tb01880.x · doi:10.1111/j.1095-8312.1999.tb01880.x
  93. Howard J., 2020, Deep learning for coders with fastai and PyTorch
  94. Howard J. &Gugger S.(2020b).fastai: A layered API for deep learning.arXiv 2002.04688. · DOI · Paper page
  95. 10.1073/pnas.2002545117 · DOI · Paper page
  96. 10.1029/2019PA003612 · DOI
  97. 10.1016/j.ecoinf.2021.101486 · DOI
  98. 10.1016/S0304-3800(01)00300-3 · DOI
  99. 10.1016/j.ecolmodel.2007.09.029 · DOI
  100. 10.1145/2647868.2654889 · DOI · Paper page
  101. Jiang Y. Balaban M. Zhu Q. &Mirarab S.(2021).DEPP: Deep learning enables extending species trees using single genes.bioRxiv 2021.01.22.427808. · DOI
  102. 10.3390/sym13091599 · doi:10.3390/sym13091599
  103. 10.1111/ele.13462 · DOI
  104. 10.1016/j.ecoinf.2014.01.004 · DOI
  105. 10.1145/3411764.3445250 · DOI
  106. 10.1023/A:1012460413855 · DOI · Paper page
  107. Kang B. Xie S. Rohrbach M. Yan Z. Gordo A. Feng J. &Kalantidis Y.(2019).Decoupling representation and classifier for long‐tailed recognition.arXiv 1910.09217.
  108. 10.1002/rse2.146 · DOI
  109. Kern A. D., 2018, diploS/HIC: An updated approach to classifying selective sweeps, G3: Gemes, Genomes, Genetics, 8, 1959, 10.1534/g3.118.200262 · DOI
  110. 10.1038/ncomms12521 · DOI
  111. 10.1109/CVPR.2019.00922 · DOI · Paper page
  112. 10.1016/j.compbiomed.2011.04.008 · DOI
  113. 10.1093/sysbio/syab048 · DOI
  114. Kluyver T., 2016, Positioning and power in academic publishing: Players, agents and agendas, 87
  115. Körschens M. Barz B. &Denzler J.(2018).Towards automatic identification of elephants in the wild.arXiv 1812.04418.
  116. 10.3390/f12010066 · DOI
  117. 10.1007/s11831-021-09660-0 · doi:10.1007/s11831-021-09660-0
  118. 10.1371/journal.pcbi.1009803 · DOI
  119. 10.1086/285289 · DOI · Paper page
  120. 10.1016/j.compag.2019.105114 · DOI
  121. 10.1016/j.rse.2020.111953 · DOI
  122. 10.1016/j.jag.2020.102163 · DOI · Paper page
  123. 10.1016/j.ecoinf.2021.101217 · DOI
  124. 10.1007/978-3-319-10602-1_48 · DOI · Paper page
  125. 10.1016/j.sedgeo.2020.105790 · DOI
  126. 10.1109/CVPR.2019.00264 · DOI · Paper page
  127. 10.1186/s40317-019-0175-5 · DOI
  128. 10.3389/fpls.2021.760139 · DOI
  129. 10.1038/s41477-020-00834-5 · DOI
  130. 10.1038/s41467-020-19105-0 · DOI
  131. 10.1080/02705060.2011.635883 · DOI
  132. 10.1109/ACCESS.2020.3042337 · DOI
  133. 10.1371/journal.pone.0192011 · DOI
  134. 10.1016/j.neuron.2020.09.017 · DOI · Paper page
  135. 10.1038/s41598-019-44565-w · DOI
  136. 10.1038/s42256-021-00393-0 · DOI
  137. Miele V. Dussert G. Cucchi T. &Renaud S.(2020).Deep learning for species identification of modern and fossil rodent molars.bioRxiv 2020.08.20.259176. · DOI
  138. 10.1111/2041-210X.13577 · DOI
  139. 10.1016/j.scitotenv.2019.135160 · DOI
  140. Montserrat D. M. Bustamante C. &Ioannidis A.(2019).Class‐conditional VAE‐GAN for local‐ancestry simulation.arXiv 1911.13220.
  141. 10.1109/ICASSP40776.2020.9053662 · DOI
  142. 10.1016/j.anbehav.2006.12.028 · DOI · Paper page
  143. 10.1038/s41596-019-0176-0 · DOI · Paper page
  144. 10.1145/3341525.3393997 · doi:10.1145/3341525.3393997
  145. 10.1016/j.ecoinf.2021.101275 · DOI
  146. 10.1111/2041-210X.13504 · DOI · Paper page
  147. 10.1073/pnas.1719367115 · DOI · Paper page
  148. O'Connor R., 2022, PyTorch vs TensorFlow in 2022
  149. 10.2307/j.ctvcm4hnd · DOI
  150. Ouellette T. W. Shaw J. &Awadalla P.(2021).Using image‐based haplotype alignments to map global adaptation of SARS‐CoV‐2.bioRxiv. · DOI
  151. 10.1038/s41598-020-57875-1 · DOI
  152. 10.1038/nbt.3313 · DOI · Paper page
  153. Paszke A., 2019, Advances in neural information processing systems, 8026
  154. 10.1038/s41592-018-0234-5 · DOI · Paper page
  155. Pereira T. D. Tabris N. Li J. Ravindranath S. Papadoyannis E. S. Wang Z. Y. Turner D. M. McKenzie‐Smith G. Kocher S. D. Falkner A. L. Shaevitz J. W. &Murthy M.(2020).SLEAP: Multi‐animal pose tracking.bioRxiv 2020.08.31.276246. · DOI
  156. Perez M. F. Bonatelli I. A. S. Romeiro‐Brito M. Franco F. F. Taylor N. P. Zappi D. C. &Moraes E. M.(2020).Coalescent‐based species delimitation meets deep learning: Insights from a highly fragmented cactus system.bioRxiv e424219. · doi:10.1101/2020.12.23.424219
  157. 10.3390/s22020633 · DOI
  158. 10.1118/1.3578605 · DOI · Paper page
  159. 10.1111/jav.01447 · DOI · Paper page
  160. 10.1111/2041-210X.13495 · DOI
  161. 10.3389/fpls.2019.00272 · DOI · Paper page
  162. 10.3389/fpls.2019.01327 · DOI
  163. Raschka S.(2018).Model evaluation model selection and algorithm selection in machine learning.arXiv 1811.12808.
  164. 10.1038/ng0508-491 · DOI · Paper page
  165. Rumelhart D. E., 1995, Backpropagation: Theory, architectures, and applications, chapter 1, 1
  166. 10.13031/aim.201900477 · doi:10.13031/aim.201900477
  167. Sanchez T. Cury J. Charpiat G. &Jay F.(2020).Deep learning for population size history inference: Design comparison and combination with approximate Bayesian computation.bioRxiv. · DOI
  168. 10.1126/science.aay4497 · DOI · Paper page
  169. 10.1111/2041-210X.13133 · DOI · Paper page
  170. 10.3897/BDJ.5.e21139 · DOI
  171. 10.1111/2041-210X.13712 · DOI
  172. Sharif Razavian A., 2014, Proceedings of the IEEE conference on computer vision and pattern recognition workshops
  173. 10.1371/journal.pcbi.1004845 · DOI · Paper page
  174. Shu L. Xu H. &Liu B.(2018).Unseen class discovery in open‐world classification.arXiv 1801.05609.
  175. 10.3389/frobt.2018.00066 · DOI
  176. 10.1007/b98952 · DOI · Paper page
  177. Srinivasan K. Duvvur V. &Hess D.(2018).Prediction of algal blooms in the Great Lakes through a convolution neural network of remote sensing data.bioRxiv e450551. · DOI
  178. Stevens E., 2020, Deep learning with PyTorch
  179. 10.1111/2041-210X.13103 · DOI · Paper page
  180. 10.1098/rstb.2021.0063 · DOI
  181. 10.1109/WACV45572.2020.9093624 · DOI
  182. 10.3389/fevo.2021.762173 · DOI
  183. 10.1007/s10489-020-02075-7 · DOI
  184. 10.1093/sysbio/syz060 · DOI
  185. 10.1038/s41598-019-45301-0 · DOI
  186. 10.1093/gigascience/giy037 · DOI · Paper page
  187. 10.1111/2041-210X.13335 · DOI · Paper page
  188. The Theano Development Team Al‐Rfou R. Alain G. Almahairi A. Angermueller C. Bahdanau D. Ballas N. Bastien F. Bayer J. Belikov A. Belopolsky A. Bengio Y. Bergeron A. Bergstra J. Bisson V. Snyder J. B. Bouchard N. Boulanger‐Lewandowski N. Bouthillier X. …Zhang Y.(2016).Theano: A python framework for fast computation of mathematical expressions.arXiv 1605.02688.
  189. 10.1186/s12859-019-2927-x · DOI
  190. 10.1186/s12862-016-0827-5 · DOI
  191. 10.1093/sysbio/syz014 · DOI · Paper page
  192. 10.1016/j.jneumeth.2019.108536 · DOI
  193. Van der Maaten L., 2008, Visualizing data using t‐SNE, Journal of Machine Learning Research, 9, 2579
  194. Vaswani A. Shazeer N. Parmar N. Uszkoreit J. Jones L. Gomez A. N. Kaiser L. &Polosukhin I.(2017).Attention is all you need. InProceedings in 31st conference on neural information processing systems (NIPS 2017).NeurIPS.
  195. 10.3390/s22020497 · DOI
  196. 10.1016/j.ecoinf.2018.09.007 · DOI · Paper page
  197. 10.1111/2041-210X.13075 · DOI · Paper page
  198. 10.1016/S0304-3800(01)00299-X · DOI
  199. 10.1002/ps.6383 · DOI
  200. 10.2481/dsj.007-020 · DOI

200 of 217 shown

Cited by

See all 249

Metadata

Authors
Borowiec, M. L., Dikow, R. B., Frandsen, P. B., McKeeken, A., Valentini, G., & White, A. E.
Venue
Methods in Ecology and Evolution
Publisher
Wiley
Published
2022-06-13
Volume
13
Issue
8
Pages
1640-1660
ISSN
2041-210X (ISSN-L)
OpenAlex
W4281728047
Cited by
249
References
47
FWCI
17.04
Type
journal article
Language
en
Open access
hybrid
Funders
National Institute of Food and Agriculture (2021‐67021‐34253)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.