1
|
Kulikov N, Derakhshandeh F, Mayer C. Machine learning can be as good as maximum likelihood when reconstructing phylogenetic trees and determining the best evolutionary model on four taxon alignments. Mol Phylogenet Evol 2024; 200:108181. [PMID: 39209046 DOI: 10.1016/j.ympev.2024.108181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Revised: 07/15/2024] [Accepted: 08/26/2024] [Indexed: 09/04/2024]
Abstract
Phylogenetic tree reconstruction with molecular data is important in many fields of life science research. The gold standard in this discipline is the phylogenetic tree reconstruction based on the Maximum Likelihood method. In this study, we present neural networks to predict the best model of sequence evolution and the correct topology for four sequence alignments of nucleotide or amino acid sequence data. We trained neural networks with different architectures using simulated alignments for a wide range of evolutionary models, model parameters and branch lengths. By comparing the accuracy of model and topology prediction of the trained neural networks with Maximum Likelihood and Neighbour Joining methods, we show that for quartet trees, the neural network classifier outperforms the Neighbour Joining method and is in most cases as good as the Maximum Likelihood method to infer the best model of sequence evolution and the best tree topology. These results are consistent for nucleotide and amino acid sequence data. We also show that our method is superior for model selection than previously published methods based on convolutionary networks. Furthermore, we found that neural network classifiers are much faster than the IQ-TREE implementation of the Maximum Likelihood method. Our results show that neural networks could become a true competitor for the Maximum Likelihood method in phylogenetic reconstructions.
Collapse
Affiliation(s)
- Nikita Kulikov
- Molecular Evolutionary Biology, Department of Biology, Hamburg University, Germany; Leibniz Institute for the Analysis of Biodiversity Change (LIB), Germany.
| | - Fatemeh Derakhshandeh
- Leibniz Institute for the Analysis of Biodiversity Change (LIB), Germany; Medical Faculty, Heidelberg University, Germany
| | - Christoph Mayer
- Leibniz Institute for the Analysis of Biodiversity Change (LIB), Germany
| |
Collapse
|
2
|
Owens AF, Hockings KJ, Imron MA, Madhusudhana S, Mariaty, Setia TM, Sharma M, Maimunah S, Van Veen FJF, Erb WM. Automated detection of Bornean white-bearded gibbon (Hylobates albibarbis) vocalizations using an open-source framework for deep learning. THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA 2024; 156:1623-1632. [PMID: 39248557 DOI: 10.1121/10.0028268] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Accepted: 07/30/2024] [Indexed: 09/10/2024]
Abstract
Passive acoustic monitoring is a promising tool for monitoring at-risk populations of vocal species, yet, extracting relevant information from large acoustic datasets can be time-consuming, creating a bottleneck at the point of analysis. To address this, an open-source framework for deep learning in bioacoustics to automatically detect Bornean white-bearded gibbon (Hylobates albibarbis) "great call" vocalizations in a long-term acoustic dataset from a rainforest location in Borneo is adapted. The steps involved in developing this solution are described, including collecting audio recordings, developing training and testing datasets, training neural network models, and evaluating model performance. The best model performed at a satisfactory level (F score = 0.87), identifying 98% of the highest-quality calls from 90 h of manually annotated audio recordings and greatly reduced analysis times when compared to a human observer. No significant difference was found in the temporal distribution of great call detections between the manual annotations and the model's output. Future work should seek to apply this model to long-term acoustic datasets to understand spatiotemporal variations in H. albibarbis' calling activity. Overall, a roadmap is presented for applying deep learning to identify the vocalizations of species of interest, which can be adapted for monitoring other endangered vocalizing species.
Collapse
Affiliation(s)
- A F Owens
- Department of Earth and Environmental Science, Faculty of Environment, Science and Economy, University of Exeter, Penryn, TR10 9FE, United Kingdom
| | - Kimberley J Hockings
- Centre for Ecology and Conservation, Faculty of Environment, Science and Economy, University of Exeter, Penryn, TR10 9FE, United Kingdom
| | - Muhammed Ali Imron
- Faculty of Forestry, Universitas Gadjah Mada, Yogyakarta, 55281, Indonesia
| | - Shyam Madhusudhana
- Centre for Marine Science and Technology, Curtin University, Perth, Western Australia, 6102, Australia
- K. Lisa Yang Center for Conservation Bioacoustics, Cornell Laboratory of Ornithology, Cornell University, Ithaca, New York 14850, USA
| | - Mariaty
- Fakultas Kehutanan dan Pertanian, Universitas Muhammadiyah Palangka Raya, Palangka Raya, 73111, Indonesia
| | - Tatang Mitra Setia
- Department of Biology, Faculty of Biology and Agriculture, Universitas Nasional, Jakarta, 12520, Indonesia
| | - Manmohan Sharma
- Department of Earth and Environmental Science, Faculty of Environment, Science and Economy, University of Exeter, Penryn, TR10 9FE, United Kingdom
| | - Siti Maimunah
- Fakultas Kehutanan, Instiper Yogyakarta, Yogyakarta, 55281, Indonesia
| | - F J F Van Veen
- Department of Earth and Environmental Science, Faculty of Environment, Science and Economy, University of Exeter, Penryn, TR10 9FE, United Kingdom
| | - Wendy M Erb
- K. Lisa Yang Center for Conservation Bioacoustics, Cornell Laboratory of Ornithology, Cornell University, Ithaca, New York 14850, USA
| |
Collapse
|
3
|
Landis MJ, Thompson A. phyddle: software for phylogenetic model exploration with deep learning. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.08.06.606717. [PMID: 39149349 PMCID: PMC11326143 DOI: 10.1101/2024.08.06.606717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/17/2024]
Abstract
Many realistic phylogenetic models lack tractable likelihood functions, prohibiting their use with standard inference methods. We present phyddle, a pipeline-based toolkit for performing phylogenetic modeling tasks using likelihood-free deep learning approaches. phyddle coordinates modeling tasks through five analysis steps (Simulate, Format, Train, Estimate, and Plot) that transform raw phylogenetic datasets as input into numerical and visualized model-based output. Benchmarks show that phyddle accurately performs a range of inference tasks, such as estimating macroevolutionary parameters, selecting among continuous trait evolution models, and passing coverage tests for epidemiological models, even for models that lack tractable likelihoods. phyddle has a flexible command-line interface, making it easy to integrate deep learning approaches for phylogenetics into research workflows. Learn more about phyddle at https://phyddle.org.
Collapse
Affiliation(s)
- Michael J. Landis
- Department of Biology, Washington University, St. Louis, MO, 63110, USA
| | - Ammon Thompson
- Participant in an education program sponsored by U.S. Department of Defense (DOD)
| |
Collapse
|
4
|
Karbstein K, Kösters L, Hodač L, Hofmann M, Hörandl E, Tomasello S, Wagner ND, Emerson BC, Albach DC, Scheu S, Bradler S, de Vries J, Irisarri I, Li H, Soltis P, Mäder P, Wäldchen J. Species delimitation 4.0: integrative taxonomy meets artificial intelligence. Trends Ecol Evol 2024; 39:771-784. [PMID: 38849221 DOI: 10.1016/j.tree.2023.11.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Revised: 10/20/2023] [Accepted: 11/08/2023] [Indexed: 06/09/2024]
Abstract
Although species are central units for biological research, recent findings in genomics are raising awareness that what we call species can be ill-founded entities due to solely morphology-based, regional species descriptions. This particularly applies to groups characterized by intricate evolutionary processes such as hybridization, polyploidy, or asexuality. Here, challenges of current integrative taxonomy (genetics/genomics + morphology + ecology, etc.) become apparent: different favored species concepts, lack of universal characters/markers, missing appropriate analytical tools for intricate evolutionary processes, and highly subjective ranking and fusion of datasets. Now, integrative taxonomy combined with artificial intelligence under a unified species concept can enable automated feature learning and data integration, and thus reduce subjectivity in species delimitation. This approach will likely accelerate revising and unraveling eukaryotic biodiversity.
Collapse
Affiliation(s)
- Kevin Karbstein
- Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, 07745 Jena, Germany.
| | - Lara Kösters
- Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, 07745 Jena, Germany
| | - Ladislav Hodač
- Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, 07745 Jena, Germany
| | - Martin Hofmann
- Technical University of Ilmenau, Institute for Computer and Systems Engineering, 98693 Ilmenau, Germany
| | - Elvira Hörandl
- University of Göttingen, Albrecht-von-Haller Institute for Plant Sciences, Department of Systematics, Biodiversity and Evolution of Plants (with Herbarium), 37073 Göttingen, Germany
| | - Salvatore Tomasello
- University of Göttingen, Albrecht-von-Haller Institute for Plant Sciences, Department of Systematics, Biodiversity and Evolution of Plants (with Herbarium), 37073 Göttingen, Germany
| | - Natascha D Wagner
- University of Göttingen, Albrecht-von-Haller Institute for Plant Sciences, Department of Systematics, Biodiversity and Evolution of Plants (with Herbarium), 37073 Göttingen, Germany
| | - Brent C Emerson
- Institute of Natural Products and Agrobiology (IPNA-CSIC), Island Ecology and Evolution Research Group, 38206 La Laguna, Tenerife, Canary Islands, Spain
| | - Dirk C Albach
- Carl von Ossietzky-Universität Oldenburg, Institute of Biology and Environmental Science, 26129 Oldenburg, Germany
| | - Stefan Scheu
- University of Göttingen, Johann-Friedrich-Blumenbach Institute of Zoology and Anthropology, 37073 Göttingen, Germany; University of Göttingen, Centre of Biodiversity and Sustainable Land Use (CBL), 37073 Göttingen, Germany
| | - Sven Bradler
- University of Göttingen, Johann-Friedrich-Blumenbach Institute of Zoology and Anthropology, 37073 Göttingen, Germany
| | - Jan de Vries
- University of Göttingen, Institute for Microbiology and Genetics, Department of Applied Bioinformatics, 37077 Göttingen, Germany; University of Göttingen, Campus Institute Data Science (CIDAS), 37077 Göttingen, Germany; University of Göttingen, Göttingen Center for Molecular Biosciences (GZMB), Department of Applied Bioinformatics, 37077 Göttingen, Germany
| | - Iker Irisarri
- Leibniz Institute for the Analysis of Biodiversity Change (LIB), Centre for Molecular Biodiversity Research, Phylogenomics Section, Museum of Nature, 20146 Hamburg, Germany
| | - He Li
- Eastern China Conservation Centre for Wild Endangered Plant Resources, Chenshan Botanical Garden, 201602 Shanghai, China
| | - Pamela Soltis
- University of Florida, Florida Museum of Natural History, 32611 Gainesville, USA
| | - Patrick Mäder
- Technical University of Ilmenau, Institute for Computer and Systems Engineering, 98693 Ilmenau, Germany; German Centre for Integrative Biodiversity Research (iDiv), Halle-Jena-Leipzig, Puschstrasse 4, 04103 Leipzig, Germany; Friedrich Schiller University Jena, Faculty of Biological Sciences, Institute of Ecology and Evolution, Philosophenweg 16, 07743 Jena, Germany
| | - Jana Wäldchen
- Max Planck Institute for Biogeochemistry, Department of Biogeochemical Integration, 07745 Jena, Germany; German Centre for Integrative Biodiversity Research (iDiv), Halle-Jena-Leipzig, Puschstrasse 4, 04103 Leipzig, Germany
| |
Collapse
|
5
|
Graham KK, Glaum P, Hartert J, Gibbs J, Tucker E, Isaacs R, Valdovinos FS. A century of wild bee sampling: historical data and neural network analysis reveal ecological traits associated with species loss. Proc Biol Sci 2024; 291:20232837. [PMID: 39137885 PMCID: PMC11321864 DOI: 10.1098/rspb.2023.2837] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 05/28/2024] [Accepted: 07/16/2024] [Indexed: 08/15/2024] Open
Abstract
We analysed the wild bee community sampled from 1921 to 2018 at a nature preserve in southern Michigan, USA, to study long-term community shifts in a protected area. During an intensive survey in 1972 and 1973, Francis C. Evans detected 135 bee species. In the most recent intensive surveys conducted in 2017 and 2018, we recorded 90 species. Only 58 species were recorded in both sampling periods, indicating a significant shift in the bee community. We found that the bee community diversity, species richness and evenness were all lower in recent samples. Additionally, 64% of the more common species exhibited a more than 30% decline in relative abundance. Neural network analysis of species traits revealed that extirpation from the reserve was most likely for oligolectic ground-nesting bees and kleptoparasitic bees, whereas polylectic cavity-nesting bees were more likely to persist. Having longer phenological ranges also increased the chance of persistence in polylectic species. Further analysis suggests a climate response as bees in the contemporary sampling period had a more southerly overall distribution compared to the historic community. Results exhibit the utility of both long-term data and machine learning in disentangling complex indicators of bee population trajectories.
Collapse
Affiliation(s)
- Kelsey K. Graham
- USDA-ARS-PWA Pollinating Insect Research Unit, Logan, UT84341, USA
- Department of Entomology, Michigan State University, East Lansing, MI48824, USA
| | - Paul Glaum
- Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI48109, USA
- Department of Environmental Science and Policy, University of California, Davis, CA95616, USA
- Waterborne Environmental, Leesburg, VA20175, USA
| | - Joseph Hartert
- Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI48109, USA
| | - Jason Gibbs
- Department of Entomology, University of Manitoba, Winnipeg, Manitoba, Canada R3T 2N2
| | - Erika Tucker
- Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI48109, USA
- Milwaukee Public Museum, Milwaukee, WI53233, USA
- Biodiversity Outreach Network, Flagstaff, AZ86001, USA
| | - Rufus Isaacs
- Department of Entomology, Michigan State University, East Lansing, MI48824, USA
| | - Fernanda S. Valdovinos
- Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI48109, USA
- Department of Environmental Science and Policy, University of California, Davis, CA95616, USA
| |
Collapse
|
6
|
Simović P, Milosavljević A, Stojanović K, Radenković M, Savić-Zdravković D, Predić B, Petrović A, Božanić M, Milošević D. Automated identification of aquatic insects: A case study using deep learning and computer vision techniques. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 935:172877. [PMID: 38740196 DOI: 10.1016/j.scitotenv.2024.172877] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 04/27/2024] [Indexed: 05/16/2024]
Abstract
Deep learning techniques have recently found application in biodiversity research. Mayflies (Ephemeroptera), stoneflies (Plecoptera) and caddisflies (Trichoptera), often abbreviated as EPT, are frequently used for freshwater biomonitoring due to their large numbers and sensitivity to environmental changes. However, the morphological identification of EPT species is a challenging but fundamental task. Morphological identification of these freshwater insects is therefore not only extremely time-consuming and costly, but also often leads to misjudgments or generates datasets with low taxonomic resolution. Here, we investigated the application of deep learning to increase the efficiency and taxonomic resolution of biomonitoring programs. Our database contains 90 EPT taxa (genus or species level), with the number of images per category ranging from 21 to 300 (16,650 in total). Upon completion of training, a CNN (Convolutional Neural Network) model was created, capable of automatically classifying these taxa into their appropriate taxonomic categories with an accuracy of 98.7 %. Our model achieved a perfect classification rate of 100 % for 68 of the taxa in our dataset. We achieved noteworthy classification accuracy with morphologically closely related taxa within the training data (e.g., species of the genus Baetis, Hydropsyche, Perla). Gradient-weighted Class Activation Mapping (Grad-CAM) visualized the morphological features responsible for the classification of the treated species in the CNN models. Within Ephemeroptera, the head was the most important feature, while the thorax and abdomen were equally important for the classification of Plecoptera taxa. For the order Trichoptera, the head and thorax were almost equally important. Our database is recognized as the most extensive aquatic insect database, notably distinguished by its wealth of included categories (taxa). Our approach can help solve long-standing challenges in biodiversity research and address pressing issues in monitoring programs by saving time in sample identification.
Collapse
Affiliation(s)
- Predrag Simović
- Department of Biology and Ecology, Faculty of Science, University of Kragujevac, Radoja Domanovića 12, 34000 Kragujevac, Serbia.
| | - Aleksandar Milosavljević
- Faculty of Electronic Engineering, University of Niš, Aleksandra Medvedeva 14, 18000 Niš, Serbia.
| | - Katarina Stojanović
- Department of Zoology, Faculty of Biology, University of Belgrade, Studentski trg 16, Belgrade, Serbia.
| | - Milena Radenković
- Department of Biology and Ecology, Faculty of Science, University of Kragujevac, Radoja Domanovića 12, 34000 Kragujevac, Serbia.
| | - Dimitrija Savić-Zdravković
- Department of Biology and Ecology, Faculty of Sciences and Mathematics, University of Niš, Višegradska 33, 18000 Niš, Serbia.
| | - Bratislav Predić
- Faculty of Electronic Engineering, University of Niš, Aleksandra Medvedeva 14, 18000 Niš, Serbia.
| | - Ana Petrović
- Department of Biology and Ecology, Faculty of Science, University of Kragujevac, Radoja Domanovića 12, 34000 Kragujevac, Serbia.
| | - Milenka Božanić
- Department of Zoology, Faculty of Biology, University of Belgrade, Studentski trg 16, Belgrade, Serbia.
| | - Djuradj Milošević
- Department of Biology and Ecology, Faculty of Sciences and Mathematics, University of Niš, Višegradska 33, 18000 Niš, Serbia.
| |
Collapse
|
7
|
Dayrell RLC, Begemann L, Ott T, Poschlod P. DiasMorph: a dataset of morphological traits and images of Central European diaspores. Sci Data 2024; 11:781. [PMID: 39013933 PMCID: PMC11252285 DOI: 10.1038/s41597-024-03607-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Accepted: 07/04/2024] [Indexed: 07/18/2024] Open
Abstract
We present DiasMorph, a dataset of images and traits of diaspores from 1,442 taxa in 519 genera, and 96 families from Central Europe, totalling 94,214 records. The dataset was constructed following a standardised and reproducible image analysis method. The image dataset consists of diaspores against a high-contrast background, enabling a simple and efficient segmentation process. The quantitative traits records go beyond traditional morphometric measurements, and include colour and contour features, which are made available for the first time in a large dataset. These measurements correspond to individual diaspores, an input currently unavailable in traits databases, and allow for several approaches to explore the morphological traits of these species. Additionally, information regarding the presence and absence of appendages and structures both in the images and diaspores of the assessed taxa is also included. By making these data available, we aim to encourage initiatives to advance on new tools for diaspore identification, further our understanding of morphological traits functions, and provide means for the continuous development of image analyses applications.
Collapse
Affiliation(s)
- Roberta L C Dayrell
- Faculty of Biology and Preclinical Medicine, University of Regensburg, Universitätsstraße 31, Regensburg, D-93053, Germany.
- Royal Botanic Gardens, Kew, Wakehurst, Ardingly, Haywards Heath, West Sussex, RH17 6TN, UK.
| | - Lina Begemann
- Faculty of Biology and Preclinical Medicine, University of Regensburg, Universitätsstraße 31, Regensburg, D-93053, Germany
| | - Tankred Ott
- Faculty of Biology and Preclinical Medicine, University of Regensburg, Universitätsstraße 31, Regensburg, D-93053, Germany
| | - Peter Poschlod
- Faculty of Biology and Preclinical Medicine, University of Regensburg, Universitätsstraße 31, Regensburg, D-93053, Germany
| |
Collapse
|
8
|
Hoyal Cuthill JF, Guttenberg N, Huertas B. Male and female contributions to diversity among birdwing butterfly images. Commun Biol 2024; 7:774. [PMID: 38951581 PMCID: PMC11217504 DOI: 10.1038/s42003-024-06376-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Accepted: 05/23/2024] [Indexed: 07/03/2024] Open
Abstract
Machine learning (ML) newly enables tests for higher inter-species diversity in visible phenotype (disparity) among males versus females, predictions made from Darwinian sexual selection versus Wallacean natural selection, respectively. Here, we use ML to quantify variation across a sample of > 16,000 dorsal and ventral photographs of the sexually dimorphic birdwing butterflies (Lepidoptera: Papilionidae). Validation of image embedding distances, learnt by a triplet-trained, deep convolutional neural network, shows ML can be used for automated reconstruction of phenotypic evolution achieving measures of phylogenetic congruence to genetic species trees within a range sampled among genetic trees themselves. Quantification of sexual disparity difference (male versus female embedding distance), shows sexually and phylogenetically variable inter-species disparity. Ornithoptera exemplify high embedded male image disparity, diversification of selective optima in fitted multi-peak OU models and accelerated divergence, with cases of extreme divergence in allopatry and sympatry. However, genus Troides shows inverted patterns, including comparatively static male embedded phenotype, and higher female than male disparity - though within an inferred selective regime common to these females. Birdwing shapes and colour patterns that are most phenotypically distinctive in ML similarity are generally those of males. However, either sex can contribute majoritively to observed phenotypic diversity among species.
Collapse
Affiliation(s)
| | | | - Blanca Huertas
- Department of Science, Natural History Museum, London, UK
| |
Collapse
|
9
|
Shirali H, Hübner J, Both R, Raupach M, Reischl M, Schmidt S, Pylatiuk C. Image-based recognition of parasitoid wasps using advanced neural networks. INVERTEBR SYST 2024; 38:IS24011. [PMID: 38838190 DOI: 10.1071/is24011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Accepted: 05/08/2024] [Indexed: 06/07/2024]
Abstract
Hymenoptera has some of the highest diversity and number of individuals among insects. Many of these species potentially play key roles as food sources, pest controllers and pollinators. However, little is known about the diversity and biology and ~80% of the species have not yet been described. Classical taxonomy based on morphology is a rather slow process but DNA barcoding has already brought considerable progress in identification. Innovative methods such as image-based identification and automation can further speed up the process. We present a proof of concept for image data recognition of a parasitic wasp family, the Diapriidae (Hymenoptera), obtained as part of the GBOL III project. These tiny (1.2-4.5mm) wasps were photographed and identified using DNA barcoding to provide a solid ground truth for training a neural network. Taxonomic identification was used down to the genus level. Subsequently, three different neural network architectures were trained, evaluated and optimised. As a result, 11 different genera of diaprids and one mixed group of 'other Hymenoptera' can be classified with an average accuracy of 96%. Additionally, the sex of the specimen can be classified automatically with an accuracy of >97%.
Collapse
Affiliation(s)
- Hossein Shirali
- Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany
| | - Jeremy Hübner
- Zoologische Staatssammlung München, Münchhausenstraße 21, D-81247 Munich, Germany
| | - Robin Both
- Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany
| | - Michael Raupach
- Zoologische Staatssammlung München, Münchhausenstraße 21, D-81247 Munich, Germany
| | - Markus Reischl
- Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany
| | - Stefan Schmidt
- Deceased. Formerly at Zoologische Staatssammlung München, Münchhausenstraße 21, D-81247 Munich, Germany
| | - Christian Pylatiuk
- Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany
| |
Collapse
|
10
|
Crowson M, Williams J, Sharma J, Pettorelli N. Challenges for monitoring artificial turf expansion with satellite remote sensing. ENVIRONMENTAL MONITORING AND ASSESSMENT 2024; 196:580. [PMID: 38805109 DOI: 10.1007/s10661-024-12724-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Accepted: 05/17/2024] [Indexed: 05/29/2024]
Abstract
Urban green spaces are central components of urban ecosystems, providing refuge for wildlife while helping 'future proof' cities against climate change. Conversion of urban green spaces to artificial turf has become increasingly popular in various developed countries, such as the UK, leading to reduced urban ecosystem services delivery. To date, there is no established satellite remote sensing method for reliably detecting and mapping artificial turf expansion at scale. We here assess the combined use of very high-resolution multispectral satellite imagery and classical, open source, supervised classification approaches to map artificial lawns in a typical British city. Both object-based and pixel-based classifications struggled to reliably detect artificial turf, with large patches of artificial turf not being any more reliably identified than small patches of artificial turf. As urban ecosystems are increasingly recognised for their key contributions to human wellbeing and health, the poor performance of these standard methods highlights the urgency of developing and applying new, easily accessible approaches for the monitoring of these important ecosystems.
Collapse
Affiliation(s)
- Merry Crowson
- Institute of Zoology, Zoological Society of London, Regent's Park, London, NW1 4RY, UK
- Department of Geography and Environmental Science, University of Reading, Reading, RG6 6UR, UK
| | - Jake Williams
- Institute of Zoology, Zoological Society of London, Regent's Park, London, NW1 4RY, UK
- Department of Life Sciences, Imperial College London, Buckhurst Road, Ascot, SL5 7PY, UK
| | - James Sharma
- Institute of Zoology, Zoological Society of London, Regent's Park, London, NW1 4RY, UK
| | - Nathalie Pettorelli
- Institute of Zoology, Zoological Society of London, Regent's Park, London, NW1 4RY, UK.
| |
Collapse
|
11
|
Spiesman BJ, Gratton C, Gratton E, Hines H. Deep learning for identifying bee species from images of wings and pinned specimens. PLoS One 2024; 19:e0303383. [PMID: 38805521 PMCID: PMC11132477 DOI: 10.1371/journal.pone.0303383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Accepted: 04/23/2024] [Indexed: 05/30/2024] Open
Abstract
One of the most challenging aspects of bee ecology and conservation is species-level identification, which is costly, time consuming, and requires taxonomic expertise. Recent advances in the application of deep learning and computer vision have shown promise for identifying large bumble bee (Bombus) species. However, most bees, such as sweat bees in the genus Lasioglossum, are much smaller and can be difficult, even for trained taxonomists, to identify. For this reason, the great majority of bees are poorly represented in the crowdsourced image datasets often used to train computer vision models. But even larger bees, such as bumble bees from the B. vagans complex, can be difficult to separate morphologically. Using images of specimens from our research collections, we assessed how deep learning classification models perform on these more challenging taxa, qualitatively comparing models trained on images of whole pinned specimens or on images of bee forewings. The pinned specimen and wing image datasets represent 20 and 18 species from 6 and 4 genera, respectively, and were used to train the EfficientNetV2L convolutional neural network. Mean test precision was 94.9% and 98.1% for pinned and wing images respectively. Results show that computer vision holds great promise for classifying smaller, more difficult to identify bees that are poorly represented in crowdsourced datasets. Images from research and museum collections will be valuable for expanding classification models to include additional species, which will be essential for large scale conservation monitoring efforts.
Collapse
Affiliation(s)
- Brian J. Spiesman
- Department of Entomology, Kansas State University, Manhattan, Kansas, United States of America
| | - Claudio Gratton
- Department of Entomology, University of Wisconsin–Madison, Madison, Wisconsin, United States of America
| | - Elena Gratton
- Department of Entomology, University of Illinois Urbana-Champaign, Champaign, Illinois, United States of America
| | - Heather Hines
- Department of Entomology, Penn State University, State College, Pennsylvania, United States of America
| |
Collapse
|
12
|
Sittinger M, Uhler J, Pink M, Herz A. Insect detect: An open-source DIY camera trap for automated insect monitoring. PLoS One 2024; 19:e0295474. [PMID: 38568922 PMCID: PMC10990185 DOI: 10.1371/journal.pone.0295474] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2023] [Accepted: 02/28/2024] [Indexed: 04/05/2024] Open
Abstract
Insect monitoring is essential to design effective conservation strategies, which are indispensable to mitigate worldwide declines and biodiversity loss. For this purpose, traditional monitoring methods are widely established and can provide data with a high taxonomic resolution. However, processing of captured insect samples is often time-consuming and expensive, which limits the number of potential replicates. Automated monitoring methods can facilitate data collection at a higher spatiotemporal resolution with a comparatively lower effort and cost. Here, we present the Insect Detect DIY (do-it-yourself) camera trap for non-invasive automated monitoring of flower-visiting insects, which is based on low-cost off-the-shelf hardware components combined with open-source software. Custom trained deep learning models detect and track insects landing on an artificial flower platform in real time on-device and subsequently classify the cropped detections on a local computer. Field deployment of the solar-powered camera trap confirmed its resistance to high temperatures and humidity, which enables autonomous deployment during a whole season. On-device detection and tracking can estimate insect activity/abundance after metadata post-processing. Our insect classification model achieved a high top-1 accuracy on the test dataset and generalized well on a real-world dataset with captured insect images. The camera trap design and open-source software are highly customizable and can be adapted to different use cases. With custom trained detection and classification models, as well as accessible software programming, many possible applications surpassing our proposed deployment method can be realized.
Collapse
Affiliation(s)
- Maximilian Sittinger
- Julius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Biological Control, Dossenheim, Germany
| | - Johannes Uhler
- Julius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Biological Control, Dossenheim, Germany
| | - Maximilian Pink
- Julius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Biological Control, Dossenheim, Germany
| | - Annette Herz
- Julius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Biological Control, Dossenheim, Germany
| |
Collapse
|
13
|
Raju C, Elpa DP, Urban PL. Automation and Computerization of (Bio)sensing Systems. ACS Sens 2024; 9:1033-1048. [PMID: 38363106 PMCID: PMC10964247 DOI: 10.1021/acssensors.3c01887] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 12/21/2023] [Accepted: 01/29/2024] [Indexed: 02/17/2024]
Abstract
Sensing systems necessitate automation to reduce human effort, increase reproducibility, and enable remote sensing. In this perspective, we highlight different types of sensing systems with elements of automation, which are based on flow injection and sequential injection analysis, microfluidics, robotics, and other prototypes addressing specific real-world problems. Finally, we discuss the role of computer technology in sensing systems. Automated flow injection and sequential injection techniques offer precise and efficient sample handling and dependable outcomes. They enable continuous analysis of numerous samples, boosting throughput, and saving time and resources. They enhance safety by minimizing contact with hazardous chemicals. Microfluidic systems are enhanced by automation to enable precise control of parameters and increase of analysis speed. Robotic sampling and sample preparation platforms excel in precise execution of intricate, repetitive tasks such as sample handling, dilution, and transfer. These platforms enhance efficiency by multitasking, use minimal sample volumes, and they seamlessly integrate with analytical instruments. Other sensor prototypes utilize mechanical devices and computer technology to address real-world issues, offering efficient, accurate, and economical real-time solutions for analyte identification and quantification in remote areas. Computer technology is crucial in modern sensing systems, enabling data acquisition, signal processing, real-time analysis, and data storage. Machine learning and artificial intelligence enhance predictions from the sensor data, supporting the Internet of Things with efficient data management.
Collapse
Affiliation(s)
- Chamarthi
Maheswar Raju
- Department of Chemistry, National
Tsing Hua University 101, Section 2, Kuang-Fu Rd., Hsinchu 300044, Taiwan
| | - Decibel P. Elpa
- Department of Chemistry, National
Tsing Hua University 101, Section 2, Kuang-Fu Rd., Hsinchu 300044, Taiwan
| | - Pawel L. Urban
- Department of Chemistry, National
Tsing Hua University 101, Section 2, Kuang-Fu Rd., Hsinchu 300044, Taiwan
| |
Collapse
|
14
|
Adjei KP, Finstad AG, Koch W, O'Hara RB. Modelling heterogeneity in the classification process in multi-species distribution models can improve predictive performance. Ecol Evol 2024; 14:e11092. [PMID: 38455149 PMCID: PMC10918728 DOI: 10.1002/ece3.11092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Revised: 02/12/2024] [Accepted: 02/18/2024] [Indexed: 03/09/2024] Open
Abstract
Species distribution models and maps from large-scale biodiversity data are necessary for conservation management. One current issue is that biodiversity data are prone to taxonomic misclassifications. Methods to account for these misclassifications in multi-species distribution models have assumed that the classification probabilities are constant throughout the study. In reality, classification probabilities are likely to vary with several covariates. Failure to account for such heterogeneity can lead to biased prediction of species distributions. Here, we present a general multi-species distribution model that accounts for heterogeneity in the classification process. The proposed model assumes a multinomial generalised linear model for the classification confusion matrix. We compare the performance of the heterogeneous classification model to that of the homogeneous classification model by assessing how well they estimate the parameters in the model and their predictive performance on hold-out samples. We applied the model to gull data from Norway, Denmark and Finland, obtained from the Global Biodiversity Information Facility. Our simulation study showed that accounting for heterogeneity in the classification process increased the precision of true species' identity predictions by 30% and accuracy and recall by 6%. Since all the models in this study accounted for misclassification of some sort, there was no significant effect of accounting for heterogeneity in the classification process on the inference about the ecological process. Applying the model framework to the gull dataset did not improve the predictive performance between the homogeneous and heterogeneous models (with parametric distributions) due to the smaller misclassified sample sizes. However, when machine learning predictive scores were used as weights to inform the species distribution models about the classification process, the precision increased by 70%. We recommend multiple multinomial regression to be used to model the variation in the classification process when the data contains relatively larger misclassified samples. Machine learning prediction scores should be used when the data contains relatively smaller misclassified samples.
Collapse
Affiliation(s)
- Kwaku Peprah Adjei
- Department of Mathematical SciencesNorwegian University of Science and TechnologyTrondheimNorway
- Center for Biodiversity DynamicsNorwegian University of Science and TechnologyTrondheimNorway
- Norwegian Institute for Nature ResearchTrondheimNorway
| | - Anders Gravbrøt Finstad
- Center for Biodiversity DynamicsNorwegian University of Science and TechnologyTrondheimNorway
- Department of Natural HistoryNorwegian University of Science and TechnologyTrondheimNorway
| | - Wouter Koch
- Center for Biodiversity DynamicsNorwegian University of Science and TechnologyTrondheimNorway
- Norwegian Biodiversity Information CentreTrondheimNorway
| | - Robert Brian O'Hara
- Department of Mathematical SciencesNorwegian University of Science and TechnologyTrondheimNorway
- Center for Biodiversity DynamicsNorwegian University of Science and TechnologyTrondheimNorway
| |
Collapse
|
15
|
Hernández-López R, Travieso-González CM. Reptile Identification for Endemic and Invasive Alien Species Using Transfer Learning Approaches. SENSORS (BASEL, SWITZERLAND) 2024; 24:1372. [PMID: 38474908 DOI: 10.3390/s24051372] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Revised: 01/29/2024] [Accepted: 02/17/2024] [Indexed: 03/14/2024]
Abstract
The Canary Islands are considered a hotspot of biodiversity and have high levels of endemicity, including endemic reptile species. Nowadays, some invasive alien species of reptiles are proliferating with no control in different parts of the territory, creating a dangerous situation for the ecosystems of this archipelago. Despite the fact that the regional authorities have initiated actions to try to control the proliferation of invasive species, the problem has not been solved as it depends on sporadic sightings, and it is impossible to determine when these species appear. Since no studies for automatically identifying certain species of reptiles endemic to the Canary Islands have been found in the current state-of-the-art, from the Signals and Communications Department of the Las Palmas de Gran Canaria University (ULPGC), we consider the possibility of developing a detection system based on automatic species recognition using deep learning (DL) techniques. So this research conducts an initial identification study of some species of interest by implementing different neural network models based on transfer learning approaches. This study concludes with a comparison in which the best performance is achieved by integrating the EfficientNetV2B3 base model, which has a mean Accuracy of 98.75%.
Collapse
Affiliation(s)
- Ruymán Hernández-López
- Signals and Communications Department (DSC), Institute for Technological Development and Innovation in Communications (IDeTIC), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, Spain
| | - Carlos M Travieso-González
- Signals and Communications Department (DSC), Institute for Technological Development and Innovation in Communications (IDeTIC), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, Spain
| |
Collapse
|
16
|
Dalbosco Dell'Aglio D, Rivas-Sánchez DF, Wright DS, Merrill RM, Montgomery SH. The Sensory Ecology of Speciation. Cold Spring Harb Perspect Biol 2024; 16:a041428. [PMID: 38052495 PMCID: PMC10759811 DOI: 10.1101/cshperspect.a041428] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2023]
Abstract
In this work, we explore the potential influence of sensory ecology on speciation, including but not limited to the concept of sensory drive, which concerns the coevolution of signals and sensory systems with the local environment. The sensory environment can influence individual fitness in a variety of ways, thereby affecting the evolution of both pre- and postmating reproductive isolation. Previous work focused on sensory drive has undoubtedly advanced the field, but we argue that it may have also narrowed our understanding of the broader influence of the sensory ecology on speciation. Moreover, the clearest examples of sensory drive are largely limited to aquatic organisms, which may skew the influence of contributing factors. We review the evidence for sensory drive across environmental conditions, and in this context discuss the importance of more generalized effects of sensory ecology on adaptive behavioral divergence. Finally, we consider the potential of rapid environmental change to influence reproductive barriers related to sensory ecologies. Our synthesis shows the importance of sensory conditions for local adaptation and divergence in a range of behavioral contexts and extends our understanding of the interplay between sensory ecology and speciation.
Collapse
Affiliation(s)
- Denise Dalbosco Dell'Aglio
- School of Biological Science, University of Bristol, Bristol BS8 1TQ, United Kingdom
- Smithsonian Tropical Research Institute, Gamboa 0843-03092, Panama
| | - David F Rivas-Sánchez
- School of Biological Science, University of Bristol, Bristol BS8 1TQ, United Kingdom
| | - Daniel Shane Wright
- Faculty of Biology, Division of Evolutionary Biology, LMU Munich, 82152 Planegg-Martinsried, Germany
| | - Richard M Merrill
- Smithsonian Tropical Research Institute, Gamboa 0843-03092, Panama
- Faculty of Biology, Division of Evolutionary Biology, LMU Munich, 82152 Planegg-Martinsried, Germany
| | - Stephen H Montgomery
- School of Biological Science, University of Bristol, Bristol BS8 1TQ, United Kingdom
- Smithsonian Tropical Research Institute, Gamboa 0843-03092, Panama
| |
Collapse
|
17
|
Cantwell-Jones A, Tylianakis JM, Larson K, Gill RJ. Using individual-based trait frequency distributions to forecast plant-pollinator network responses to environmental change. Ecol Lett 2024; 27:e14368. [PMID: 38247047 DOI: 10.1111/ele.14368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 01/02/2024] [Accepted: 01/04/2024] [Indexed: 01/23/2024]
Abstract
Determining how and why organisms interact is fundamental to understanding ecosystem responses to future environmental change. To assess the impact on plant-pollinator interactions, recent studies have examined how the effects of environmental change on individual interactions accumulate to generate species-level responses. Here, we review recent developments in using plant-pollinator networks of interacting individuals along with their functional traits, where individuals are nested within species nodes. We highlight how these individual-level, trait-based networks connect intraspecific trait variation (as frequency distributions of multiple traits) with dynamic responses within plant-pollinator communities. This approach can better explain interaction plasticity, and changes to interaction probabilities and network structure over spatiotemporal or other environmental gradients. We argue that only through appreciating such trait-based interaction plasticity can we accurately forecast the potential vulnerability of interactions to future environmental change. We follow this with general guidance on how future studies can collect and analyse high-resolution interaction and trait data, with the hope of improving predictions of future plant-pollinator network responses for targeted and effective conservation.
Collapse
Affiliation(s)
- Aoife Cantwell-Jones
- Georgina Mace Centre for The Living Planet, Department of Life Sciences, Silwood Park, Imperial College London, Ascot, UK
| | - Jason M Tylianakis
- Georgina Mace Centre for The Living Planet, Department of Life Sciences, Silwood Park, Imperial College London, Ascot, UK
- Bioprotection Aotearoa, School of Biological Sciences, Private Bag 4800, University of Canterbury, Christchurch, New Zealand
| | - Keith Larson
- Climate Impacts Research Centre, Department of Ecology and Environmental Sciences, Umeå University, Umeå, Sweden
| | - Richard J Gill
- Georgina Mace Centre for The Living Planet, Department of Life Sciences, Silwood Park, Imperial College London, Ascot, UK
| |
Collapse
|
18
|
Huang X, Rymbekova A, Dolgova O, Lao O, Kuhlwilm M. Harnessing deep learning for population genetic inference. Nat Rev Genet 2024; 25:61-78. [PMID: 37666948 DOI: 10.1038/s41576-023-00636-3] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/11/2023] [Indexed: 09/06/2023]
Abstract
In population genetics, the emergence of large-scale genomic data for various species and populations has provided new opportunities to understand the evolutionary forces that drive genetic diversity using statistical inference. However, the era of population genomics presents new challenges in analysing the massive amounts of genomes and variants. Deep learning has demonstrated state-of-the-art performance for numerous applications involving large-scale data. Recently, deep learning approaches have gained popularity in population genetics; facilitated by the advent of massive genomic data sets, powerful computational hardware and complex deep learning architectures, they have been used to identify population structure, infer demographic history and investigate natural selection. Here, we introduce common deep learning architectures and provide comprehensive guidelines for implementing deep learning models for population genetic inference. We also discuss current challenges and future directions for applying deep learning in population genetics, focusing on efficiency, robustness and interpretability.
Collapse
Affiliation(s)
- Xin Huang
- Department of Evolutionary Anthropology, University of Vienna, Vienna, Austria.
- Human Evolution and Archaeological Sciences (HEAS), University of Vienna, Vienna, Austria.
| | - Aigerim Rymbekova
- Department of Evolutionary Anthropology, University of Vienna, Vienna, Austria
- Human Evolution and Archaeological Sciences (HEAS), University of Vienna, Vienna, Austria
| | - Olga Dolgova
- Integrative Genomics Laboratory, CIC bioGUNE - Centro de Investigación Cooperativa en Biociencias, Derio, Biscaya, Spain
| | - Oscar Lao
- Institute of Evolutionary Biology, CSIC-Universitat Pompeu Fabra, Barcelona, Spain.
| | - Martin Kuhlwilm
- Department of Evolutionary Anthropology, University of Vienna, Vienna, Austria.
- Human Evolution and Archaeological Sciences (HEAS), University of Vienna, Vienna, Austria.
| |
Collapse
|
19
|
Ahrens D. Species Diagnosis and DNA Taxonomy. Methods Mol Biol 2024; 2744:33-52. [PMID: 38683310 DOI: 10.1007/978-1-0716-3581-0_2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/01/2024]
Abstract
The use of DNA has helped to improve and speed up species identification and delimitation. However, it also provides new challenges to taxonomists. Incongruence of outcome from various markers and delimitation methods, bias from sampling and skewed species distribution, implemented models, and the choice of methods/priors may mislead results and also may, in conclusion, increase elements of subjectivity in species taxonomy. The lack of direct diagnostic outcome from most contemporary molecular delimitation approaches and the need for a reference to existing and best sampled trait reference systems reveal the need for refining the criteria of species diagnosis and diagnosability in the current framework of nomenclature codes and good practices to avoid nomenclatorial instability, parallel taxonomies, and consequently more and new taxonomic impediment.
Collapse
Affiliation(s)
- Dirk Ahrens
- Museum A. Koenig Bonn, Leibniz Institute for the Analysis of Biodiversity Change, Bonn, Germany.
| |
Collapse
|
20
|
Lambert S, Voznica J, Morlon H. Deep Learning from Phylogenies for Diversification Analyses. Syst Biol 2023; 72:1262-1279. [PMID: 37556735 DOI: 10.1093/sysbio/syad044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2022] [Revised: 06/20/2023] [Accepted: 08/08/2023] [Indexed: 08/11/2023] Open
Abstract
Birth-death (BD) models are widely used in combination with species phylogenies to study past diversification dynamics. Current inference approaches typically rely on likelihood-based methods. These methods are not generalizable, as a new likelihood formula must be established each time a new model is proposed; for some models, such a formula is not even tractable. Deep learning can bring solutions in such situations, as deep neural networks can be trained to learn the relation between simulations and parameter values as a regression problem. In this paper, we adapt a recently developed deep learning method from pathogen phylodynamics to the case of diversification inference, and we extend its applicability to the case of the inference of state-dependent diversification models from phylogenies associated with trait data. We demonstrate the accuracy and time efficiency of the approach for the time-constant homogeneous BD model and the Binary-State Speciation and Extinction model. Finally, we illustrate the use of the proposed inference machinery by reanalyzing a phylogeny of primates and their associated ecological role as seed dispersers. Deep learning inference provides at least the same accuracy as likelihood-based inference while being faster by several orders of magnitude, offering a promising new inference approach for the deployment of future models in the field.
Collapse
Affiliation(s)
- Sophia Lambert
- Institut de Biologie de l'École Normale Supérieure, École Normale Supérieure, CNRS, INSERM, Université Paris Sciences et Lettres, 46 Rue d'Ulm, 75005 Paris, France
- Institute of Ecology and Evolution, Department of Biology, 5289 University of Oregon, Eugene, OR 97403, USA
| | - Jakub Voznica
- Institut Pasteur, Université Paris Cité, Unité Bioinformatique Evolutive, 25-28 Rue du Dr Roux, 75015 Paris, France
- Unité de Biologie Computationnelle, USR 3756 CNRS, 25-28 Rue du Dr Roux, 75015 Paris, France
| | - Hélène Morlon
- Institut de Biologie de l'École Normale Supérieure, École Normale Supérieure, CNRS, INSERM, Université Paris Sciences et Lettres, 46 Rue d'Ulm, 75005 Paris, France
| |
Collapse
|
21
|
Alexander Pyron R. Unsupervised machine learning for species delimitation, integrative taxonomy, and biodiversity conservation. Mol Phylogenet Evol 2023; 189:107939. [PMID: 37804960 DOI: 10.1016/j.ympev.2023.107939] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Revised: 09/25/2023] [Accepted: 10/04/2023] [Indexed: 10/09/2023]
Abstract
Integrative taxonomy, combining data from multiple axes of biologically relevant variation, is a major goal of systematics. Ideally, such taxonomies will derive from similarly integrative species-delimitation analyses. Yet, most current methods rely solely or primarily on molecular data, with other layers often incorporated only in a post hoc qualitative or comparative manner. A major limitation is the difficulty of devising quantitative parametric models linking different datasets in a unified ecological and evolutionary framework. Machine Learning (ML) methods offer flexibility in this arena by easily learning high-dimensional associations between observations (e.g., individual specimens) across a wide array of input features (e.g., genetics, geography, environment, and phenotype) to delimit statistically meaningful clusters. Here, I implement an unsupervised method using Self-Organizing (or "Kohonen") Maps (SOMs) for such purposes. Recent extensions called "SuperSOMs" can integrate multiple layers, each of which exerts independent influence on a two-dimensional output grid via empirically estimated weights. The grid cells are then delimited into K distinct units that can be interpreted as species or other entities. I show empirical examples in salamanders (Desmognathus) and snakes (Storeria) with layers representing alleles, space, climate, and traits. Simulations reveal that the SuperSOM approach can detect K = 1, tends not to over-split, reflects contributions from all layers, and limits large layers (e.g., genetic matrices) from overwhelming other datasets, desirable properties addressing major concerns from previous studies. Finally, I suggest that these and similar methods could integrate conservation-relevant layers such as population trends and human encroachment to delimit management units from an explicitly quantitative framework grounded in the ecology and evolution of species limits and boundaries.
Collapse
Affiliation(s)
- R Alexander Pyron
- Department of Biological Sciences, The George Washington University, Washington, DC 20052 USA.
| |
Collapse
|
22
|
Ling MH, Ivorra T, Heo CC, Wardhana AH, Hall MJR, Tan SH, Mohamed Z, Khang TF. Machine learning analysis of wing venation patterns accurately identifies Sarcophagidae, Calliphoridae and Muscidae fly species. MEDICAL AND VETERINARY ENTOMOLOGY 2023; 37:767-781. [PMID: 37477152 DOI: 10.1111/mve.12682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Accepted: 07/03/2023] [Indexed: 07/22/2023]
Abstract
In medical, veterinary and forensic entomology, the ease and affordability of image data acquisition have resulted in whole-image analysis becoming an invaluable approach for species identification. Krawtchouk moment invariants are a classical mathematical transformation that can extract local features from an image, thus allowing subtle species-specific biological variations to be accentuated for subsequent analyses. We extracted Krawtchouk moment invariant features from binarised wing images of 759 male fly specimens from the Calliphoridae, Sarcophagidae and Muscidae families (13 species and a species variant). Subsequently, we trained the Generalized, Unbiased, Interaction Detection and Estimation random forests classifier using linear discriminants derived from these features and inferred the species identity of specimens from the test samples. Fivefold cross-validation results show a 98.56 ± 0.38% (standard error) mean identification accuracy at the family level and a 91.04 ± 1.33% mean identification accuracy at the species level. The mean F1-score of 0.89 ± 0.02 reflects good balance of precision and recall properties of the model. The present study consolidates findings from previous small pilot studies of the usefulness of wing venation patterns for inferring species identities. Thus, the stage is set for the development of a mature data analytic ecosystem for routine computer image-based identification of fly species that are of medical, veterinary and forensic importance.
Collapse
Affiliation(s)
- Min Hao Ling
- Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Malaysia
| | - Tania Ivorra
- Department of Medical Microbiology and Parasitology, Faculty of Medicine, Universiti Teknologi MARA (UiTM), Sungai Buloh, Selangor, Malaysia
- Department of Environmental Sciences and Natural Resources, University of Alicante, Alicante, Spain
| | - Chong Chin Heo
- Department of Medical Microbiology and Parasitology, Faculty of Medicine, Universiti Teknologi MARA (UiTM), Sungai Buloh, Selangor, Malaysia
| | - April Hari Wardhana
- Research Center for Veterinary Science, The National Research and Innovation Agency, Bogor, Indonesia
- Faculty of Veterinary Medicine, Airlangga University, Surabaya, Indonesia
| | | | - Siew Hwa Tan
- International Department of Dipterology, Kuala Lumpur Laboratory, Kuala Lumpur, Malaysia
- Institute of Biological Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Malaysia
| | - Zulqarnain Mohamed
- Institute of Biological Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Malaysia
| | - Tsung Fei Khang
- Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur, Malaysia
- Universiti Malaya Centre for Data Analytics, Universiti Malaya, Kuala Lumpur, Malaysia
| |
Collapse
|
23
|
Panigrahi S, Maski P, Thondiyath A. Real-time biodiversity analysis using deep-learning algorithms on mobile robotic platforms. PeerJ Comput Sci 2023; 9:e1502. [PMID: 37705641 PMCID: PMC10495972 DOI: 10.7717/peerj-cs.1502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Accepted: 07/04/2023] [Indexed: 09/15/2023]
Abstract
Ecological biodiversity is declining at an unprecedented rate. To combat such irreversible changes in natural ecosystems, biodiversity conservation initiatives are being conducted globally. However, the lack of a feasible methodology to quantify biodiversity in real-time and investigate population dynamics in spatiotemporal scales prevents the use of ecological data in environmental planning. Traditionally, ecological studies rely on the census of an animal population by the "capture, mark and recapture" technique. In this technique, human field workers manually count, tag and observe tagged individuals, making it time-consuming, expensive, and cumbersome to patrol the entire area. Recent research has also demonstrated the potential for inexpensive and accessible sensors for ecological data monitoring. However, stationary sensors collect localised data which is highly specific on the placement of the setup. In this research, we propose the methodology for biodiversity monitoring utilising state-of-the-art deep learning (DL) methods operating in real-time on sample payloads of mobile robots. Such trained DL algorithms demonstrate a mean average precision (mAP) of 90.51% in an average inference time of 67.62 milliseconds within 6,000 training epochs. We claim that the use of such mobile platform setups inferring real-time ecological data can help us achieve our goal of quick and effective biodiversity surveys. An experimental test payload is fabricated, and online as well as offline field surveys are conducted, validating the proposed methodology for species identification that can be further extended to geo-localisation of flora and fauna in any ecosystem.
Collapse
Affiliation(s)
- Siddhant Panigrahi
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India
| | - Prajwal Maski
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India
| | - Asokan Thondiyath
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India
| |
Collapse
|
24
|
Pantel JH, Becks L. Statistical methods to identify mechanisms in studies of eco-evolutionary dynamics. Trends Ecol Evol 2023; 38:760-772. [PMID: 37437547 DOI: 10.1016/j.tree.2023.03.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2022] [Revised: 03/28/2023] [Accepted: 03/30/2023] [Indexed: 07/14/2023]
Abstract
While the reciprocal effects of ecological and evolutionary dynamics are increasingly recognized as an important driver for biodiversity, detection of such eco-evolutionary feedbacks, their underlying mechanisms, and their consequences remains challenging. Eco-evolutionary dynamics occur at different spatial and temporal scales and can leave signatures at different levels of organization (e.g., gene, protein, trait, community) that are often difficult to detect. Recent advances in statistical methods combined with alternative hypothesis testing provides a promising approach to identify potential eco-evolutionary drivers for observed data even in non-model systems that are not amenable to experimental manipulation. We discuss recent advances in eco-evolutionary modeling and statistical methods and discuss challenges for fitting mechanistic models to eco-evolutionary data.
Collapse
Affiliation(s)
- Jelena H Pantel
- Ecological Modelling, Faculty of Biology, University of Duisburg-Essen, Universitätsstraße 2, 45117 Essen, Germany.
| | - Lutz Becks
- University of Konstanz, Aquatic Ecology and Evolution, Limnological Institute University of Konstanz Mainaustraße 252 78464, Konstanz/Egg, Germany
| |
Collapse
|
25
|
Batz P, Will T, Thiel S, Ziesche TM, Joachim C. From identification to forecasting: the potential of image recognition and artificial intelligence for aphid pest monitoring. FRONTIERS IN PLANT SCIENCE 2023; 14:1150748. [PMID: 37538063 PMCID: PMC10396399 DOI: 10.3389/fpls.2023.1150748] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 06/26/2023] [Indexed: 08/05/2023]
Abstract
Insect monitoring has gained global public attention in recent years in the context of insect decline and biodiversity loss. Monitoring methods that can collect samples over a long period of time and independently of human influences are of particular importance. While these passive collection methods, e.g. suction traps, provide standardized and comparable data sets, the time required to analyze the large number of samples and trapped specimens is high. Another challenge is the necessary high level of taxonomic expertise required for accurate specimen processing. These factors create a bottleneck in specimen processing. In this context, machine learning, image recognition and artificial intelligence have emerged as promising tools to address the shortcomings of manual identification and quantification in the analysis of such trap catches. Aphids are important agricultural pests that pose a significant risk to several important crops and cause high economic losses through feeding damage and transmission of plant viruses. It has been shown that long-term monitoring of migrating aphids using suction traps can be used to make, adjust and improve predictions of their abundance so that the risk of plant viruses spreading through aphids can be more accurately predicted. With the increasing demand for alternatives to conventional pesticide use in crop protection, the need for predictive models is growing, e.g. as a basis for resistance development and as a measure for resistance management. In this context, advancing climate change has a strong influence on the total abundance of migrating aphids as well as on the peak occurrences of aphids within a year. Using aphids as a model organism, we demonstrate the possibilities of systematic monitoring of insect pests and the potential of future technical developments in the subsequent automated identification of individuals through to the use of case data for intelligent forecasting models. Using aphids as an example, we show the potential for systematic monitoring of insect pests through technical developments in the automated identification of individuals from static images (i.e. advances in image recognition software). We discuss the potential applications with regard to the automatic processing of insect case data and the development of intelligent prediction models.
Collapse
Affiliation(s)
- Philipp Batz
- ALM – Adaptiv Lernende Maschinen – Gesellschaft mit beschränkter Haftung (GmbH), Nisterau, Germany
| | - Torsten Will
- Institute for Resistance Research and Stress Tolerance, Julius Kühn-Institute, Federal Research Centre for Cultivated Plants, Quedlinburg, Germany
| | - Sebastian Thiel
- ALM – Adaptiv Lernende Maschinen – Gesellschaft mit beschränkter Haftung (GmbH), Nisterau, Germany
| | - Tim Mark Ziesche
- Institute for Resistance Research and Stress Tolerance, Julius Kühn-Institute, Federal Research Centre for Cultivated Plants, Quedlinburg, Germany
| | - Christoph Joachim
- Institute for Plant Protection in Field Crops and Grassland, Julius Kühn-Institute, Federal Research Centre for Cultivated Plants, Braunschweig, Germany
| |
Collapse
|
26
|
Wang J, Mao Y, Gao X, Zhang Y. Recurrence risk stratification for locally advanced cervical cancer using multi-modality transformer network. Front Oncol 2023; 13:1100087. [PMID: 36874136 PMCID: PMC9978213 DOI: 10.3389/fonc.2023.1100087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Accepted: 02/01/2023] [Indexed: 02/18/2023] Open
Abstract
Objectives Recurrence risk evaluation is clinically significant for patients with locally advanced cervical cancer (LACC). We investigated the ability of transformer network in recurrence risk stratification of LACC based on computed tomography (CT) and magnetic resonance (MR) images. Methods A total of 104 patients with pathologically diagnosed LACC between July 2017 and December 2021 were enrolled in this study. All patients underwent CT and MR scanning, and their recurrence status was identified by the biopsy. We randomly divided patients into training cohort (48 cases, non-recurrence: recurrence = 37: 11), validation cohort (21 cases, non-recurrence: recurrence = 16: 5), and testing cohort (35 cases, non-recurrence: recurrence = 27: 8), upon which we extracted 1989, 882 and 315 patches for model's development, validation and evaluation, respectively. The transformer network consisted of three modality fusion modules to extract multi-modality and multi-scale information, and a fully-connected module to perform recurrence risk prediction. The model's prediction performance was assessed by six metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, f1-score, sensitivity, specificity and precision. Univariate analysis with F-test and T-test were conducted for statistical analysis. Results The proposed transformer network is superior to conventional radiomics methods and other deep learning networks in both training, validation and testing cohorts. Particularly, in testing cohort, the transformer network achieved the highest AUC of 0.819 ± 0.038, while four conventional radiomics methods and two deep learning networks got the AUCs of 0.680 ± 0.050, 0.720 ± 0.068, 0.777 ± 0.048, 0.691 ± 0.103, 0.743 ± 0.022 and 0.733 ± 0.027, respectively. Conclusions The multi-modality transformer network showed promising performance in recurrence risk stratification of LACC and may be used as an effective tool to help clinicians make clinical decisions.
Collapse
Affiliation(s)
- Jian Wang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, China.,Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, Guangdong, China
| | - Yixiao Mao
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, China.,Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, Guangdong, China
| | - Xinna Gao
- Department of Radiation Oncology, Southern Medical University Nanfang Hospital, Guangzhou, Guangdong, China
| | - Yu Zhang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, China.,Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, Guangdong, China
| |
Collapse
|
27
|
Kophamel S, Ward LC, Konovalov DA, Mendez D, Ariel E, Cassidy N, Bell I, Balastegui Martínez MT, Munns SL. Field-based adipose tissue quantification in sea turtles using bioelectrical impedance spectroscopy validated with CT scans and deep learning. Ecol Evol 2022; 12:e9610. [PMID: 36523527 PMCID: PMC9748411 DOI: 10.1002/ece3.9610] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Accepted: 11/23/2022] [Indexed: 12/15/2022] Open
Abstract
Loss of adipose tissue in vertebrate wildlife species is indicative of decreased nutritional and health status and is linked to environmental stress and diseases. Body condition indices (BCI) are commonly used in ecological studies to estimate adipose tissue mass across wildlife populations. However, these indices have poor predictive power, which poses the need for quantitative methods for improved population assessments. Here, we calibrate bioelectrical impedance spectroscopy (BIS) as an alternative approach for assessing the nutritional status of vertebrate wildlife in ecological studies. BIS is a portable technology that can estimate body composition from measurements of body impedance and is widely used in humans. BIS is a predictive technique that requires calibration using a reference body composition method. Using sea turtles as model organisms, we propose a calibration protocol using computed tomography (CT) scans, with the prediction equation being: adipose tissue mass (kg) = body mass - (-0.03 [intercept] - 0.29 * length2/resistance at 50 kHz + 1.07 * body mass - 0.11 * time after capture). CT imaging allows for the quantification of body fat. However, processing the images manually is prohibitive due to the extensive time requirement. Using a form of artificial intelligence (AI), we trained a computer model to identify and quantify nonadipose tissue from the CT images, and adipose tissue was determined by the difference in body mass. This process enabled estimating adipose tissue mass from bioelectrical impedance measurements. The predictive performance of the model was built on 2/3 samples and tested against 1/3 samples. Prediction of adipose tissue percentage had greater accuracy when including impedance parameters (mean bias = 0.11%-0.61%) as predictor variables, compared with using body mass alone (mean bias = 6.35%). Our standardized BIS protocol improves on conventional body composition assessment methods (e.g., BCI) by quantifying adipose tissue mass. The protocol can be applied to other species for the validation of BIS and to provide robust information on the nutritional and health status of wildlife, which, in turn, can be used to inform conservation decisions at the management level.
Collapse
Affiliation(s)
- Sara Kophamel
- College of Public Health, Medical and Veterinary SciencesJames Cook UniversityTownsvilleQueenslandAustralia
| | - Leigh C. Ward
- School of Chemistry and Molecular BiosciencesThe University of QueenslandSt LuciaQueenslandAustralia
| | - Dmitry A. Konovalov
- College of Science and EngineeringJames Cook UniversityTownsvilleQueenslandAustralia
| | - Diana Mendez
- Australian Institute of Tropical Health and MedicineTownsvilleQueenslandAustralia
| | - Ellen Ariel
- College of Public Health, Medical and Veterinary SciencesJames Cook UniversityTownsvilleQueenslandAustralia
| | - Nathan Cassidy
- North Queensland X‐Ray ServicesTownsvilleQueenslandAustralia
| | - Ian Bell
- Department of Environment and ScienceQueensland GovernmentTownsvilleQueenslandAustralia
| | | | - Suzanne L. Munns
- College of Public Health, Medical and Veterinary SciencesJames Cook UniversityTownsvilleQueenslandAustralia
| |
Collapse
|
28
|
Sanchez T, Bray EM, Jobic P, Guez J, Letournel AC, Charpiat G, Cury J, Jay F. dnadna: a deep learning framework for population genetics inference. Bioinformatics 2022; 39:6851140. [PMID: 36445000 PMCID: PMC9825738 DOI: 10.1093/bioinformatics/btac765] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2021] [Revised: 10/30/2022] [Accepted: 11/28/2022] [Indexed: 11/30/2022] Open
Abstract
MOTIVATION We present dnadna, a flexible python-based software for deep learning inference in population genetics. It is task-agnostic and aims at facilitating the development, reproducibility, dissemination and re-usability of neural networks designed for population genetic data. RESULTS dnadna defines multiple user-friendly workflows. First, users can implement new architectures and tasks, while benefiting from dnadna utility functions, training procedure and test environment, which saves time and decreases the likelihood of bugs. Second, the implemented networks can be re-optimized based on user-specified training sets and/or tasks. Newly implemented architectures and pre-trained networks are easily shareable with the community for further benchmarking or other applications. Finally, users can apply pre-trained networks in order to predict evolutionary history from alternative real or simulated genetic datasets, without requiring extensive knowledge in deep learning or coding in general. dnadna comes with a peer-reviewed, exchangeable neural network, allowing demographic inference from SNP data, that can be used directly or retrained to solve other tasks. Toy networks are also available to ease the exploration of the software, and we expect that the range of available architectures will keep expanding thanks to community contributions. AVAILABILITY AND IMPLEMENTATION dnadna is a Python (≥3.7) package, its repository is available at gitlab.com/mlgenetics/dnadna and its associated documentation at mlgenetics.gitlab.io/dnadna/.
Collapse
Affiliation(s)
| | | | - Pierre Jobic
- Université Paris-Saclay, CNRS UMR 9015, INRIA, Laboratoire Interdisciplinaire des Sciences du Numérique, 91400 Orsay, France
- ENS Paris-Saclay, 91190 Gif-sur-Yvette, France
| | - Jérémy Guez
- Université Paris-Saclay, CNRS UMR 9015, INRIA, Laboratoire Interdisciplinaire des Sciences du Numérique, 91400 Orsay, France
- UMR7206 Eco-Anthropologie, Muséum National d’Histoire Naturelle, CNRS, Université de Paris, 75016 Paris, France
| | - Anne-Catherine Letournel
- Université Paris-Saclay, CNRS UMR 9015, INRIA, Laboratoire Interdisciplinaire des Sciences du Numérique, 91400 Orsay, France
| | - Guillaume Charpiat
- Université Paris-Saclay, CNRS UMR 9015, INRIA, Laboratoire Interdisciplinaire des Sciences du Numérique, 91400 Orsay, France
| | - Jean Cury
- To whom correspondence should be addressed. or
| | - Flora Jay
- To whom correspondence should be addressed. or
| |
Collapse
|
29
|
Abstract
AbstractRapid advances in hardware and software, accompanied by public- and private-sector investment, have led to a new generation of data-driven computational tools. Recently, there has been a particular focus on deep learning—a class of machine learning algorithms that uses deep neural networks to identify patterns in large and heterogeneous datasets. These developments have been accompanied by both hype and scepticism by ecologists and others. This review describes the context in which deep learning methods have emerged, the deep learning methods most relevant to ecosystem ecologists, and some of the problem domains they have been applied to. Deep learning methods have high predictive performance in a range of ecological contexts, leveraging the large data resources now available. Furthermore, deep learning tools offer ecosystem ecologists new ways to learn about ecosystem dynamics. In particular, recent advances in interpretable machine learning and in developing hybrid approaches combining deep learning and mechanistic models provide a bridge between pure prediction and causal explanation. We conclude by looking at the opportunities that deep learning tools offer ecosystem ecologists and assess the challenges in interpretability that deep learning applications pose.
Collapse
|