{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T01:28:33Z","timestamp":1792459713604,"version":"4.5.0"},"reference-count":105,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003510","name":"Ministry of Education and Research","doi-asserted-by":"publisher","award":["01IS20062"],"award-info":[{"award-number":["01IS20062"]}],"id":[{"id":"10.13039\/501100003510","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005908","name":"BMEL","doi-asserted-by":"publisher","award":["2819NA106"],"award-info":[{"award-number":["2819NA106"]}],"id":[{"id":"10.13039\/501100005908","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013549","name":"German Federal Ministry for the Environment, Nature Conservation and Nuclear Safety","doi-asserted-by":"publisher","award":["67KI2086"],"award-info":[{"award-number":["67KI2086"]}],"id":[{"id":"10.13039\/501100013549","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>DNA analyses have revolutionized species identification and taxonomic work. Yet, persistent challenges arise from little differentiation among and considerable variation within species, particularly among closely related groups. While images are commonly used as an alternative modality for automated identification tasks, their usability is limited by the same concerns. An integrative strategy, fusing molecular and image data through deep learning, holds significant promise for fine-grained species identification. However, a systematic overview and rigorous statistical testing concerning molecular and image preprocessing and fusion techniques, including practical advice for biologists, are missing so far. We introduce a deep learning scheme that integrates both molecular and image data for species identification. Initially, we systematically assess and compare three different DNA arrangements (aligned, unaligned, single nucleotide polymorphism-reduced) and two encoding methods (fractional, ordinal). Additionally, DL networks are used to extract visual and molecular features, and we propose strategies for fusing this information. Specifically, we investigate three strategies: 1) fusing directly after feature extraction, 2) fusing features that passed through a fully connected layer after feature extraction, and 3) fusing the output scores of both unimodal models. We systematically and statistically evaluate these strategies for 4 eukaryotic datasets, including 2 plant (Asteraceae, Poaceae) and 2 animal families (Lycaenidae, Coccinellidae) using Leave-One-Out Cross-Validation. In addition, we developed an approach to understand molecular- and image-specific identification failure. Aligned sequences with nucleotides encoded using fractional one-hot vectors achieved the highest identification accuracy among DNA data preprocessing techniques in all four datasets. Fusing molecular and visual features directly after feature extraction yielded the best results for three out of four datasets (52\u201399%). Overall, combining DNA with image data significantly increased accuracy in three out of four datasets, with plant datasets showing the most substantial improvement (Asteraceae: +19%, Poaceae: +13.6%). Even for Lycaenidae with high identification accuracy based on molecular data (&amp;gt;96%), a statistically significant improvement (+2.1%) was observed. Detailed analysis of confusion rates between and within genera shows that DNA alone tends to identify the genus correctly but often fails to recognize the species. The failure to resolve species is alleviated by including image data in the training. This increase in resolution hints at a hierarchical role of modalities in which molecular data coarsely group the specimens to then be guided toward a more fine-grained identification by the connected image. We systematically showed and explained, for the first time, that optimizing the preprocessing and integration of molecular and image data offers significant benefits, particularly for genetically similar and morphologically indistinguishable species, enhancing species identification by reducing modality-specific failure rates and information gaps. Our results can inform integration efforts for various organism groups, improving automated identification across a wide range of eukaryotic species.<\/jats:p>","DOI":"10.1093\/sysbio\/syaf026","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T07:31:30Z","timestamp":1744270290000},"source":"Crossref","is-referenced-by-count":7,"title":["Data Fusion for Integrative Species Identification using Deep Learning"],"prefix":"10.1093","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7913-2377","authenticated-orcid":false,"given":"Lara M","family":"K\u00f6sters","sequence":"first","affiliation":[{"name":"Biogeochemical Integration, Max-Planck-Institute for Biogeochemistry , 07745 Jena ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1424-6557","authenticated-orcid":false,"given":"Kevin","family":"Karbstein","sequence":"additional","affiliation":[{"name":"Biogeochemical Integration, Max-Planck-Institute for Biogeochemistry , 07745 Jena ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-3317","authenticated-orcid":false,"given":"Martin","family":"Hofmann","sequence":"additional","affiliation":[{"name":"Data-Intensive Systems and Visualization Group (dAI.SY), Technical University Ilmenau , 98693 Ilmenau ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-1317","authenticated-orcid":false,"given":"Ladislav","family":"Hoda\u010d","sequence":"additional","affiliation":[{"name":"Biogeochemical Integration, Max-Planck-Institute for Biogeochemistry , 07745 Jena ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6871-2707","authenticated-orcid":false,"given":"Patrick","family":"M\u00e4der","sequence":"additional","affiliation":[{"name":"Data-Intensive Systems and Visualization Group (dAI.SY), Technical University Ilmenau , 98693 Ilmenau ,","place":["Germany"]},{"name":"German Centre for Integrative Biodiversity Research (iDiv), Halle-Jena-Leipzig , 04103 Leipzig ,","place":["Germany"]},{"name":"Faculty of Biological Sciences, Friedrich Schiller University Jena , 07745 Jena ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2631-1531","authenticated-orcid":false,"given":"Jana","family":"W\u00e4ldchen","sequence":"additional","affiliation":[{"name":"Biogeochemical Integration, Max-Planck-Institute for Biogeochemistry , 07745 Jena ,","place":["Germany"]},{"name":"German Centre for Integrative Biodiversity Research (iDiv), Halle-Jena-Leipzig , 04103 Leipzig ,","place":["Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"key":"2025111910421324300_bib1","doi-asserted-by":"crossref","first-page":"e1846485","DOI":"10.1155\/2022\/1846485","article-title":"Pragmatic applications and universality of DNA barcoding for substantial organisms at species level: a review to explore a way forward","volume":"2022","author":"Ahmed","year":"2022","journal-title":"Biomed Res. Int."},{"key":"2025111910421324300_bib2","doi-asserted-by":"crossref","first-page":"107939","DOI":"10.1016\/j.ympev.2023.107939","article-title":"Unsupervised machine learning for species delimitation, integrative taxonomy, and biodiversity conservation","volume":"189","author":"Alexander Pyron","year":"2023","journal-title":"Mol. Phylogenet. Evol."},{"key":"2025111910421324300_bib3","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol."},{"key":"2025111910421324300_bib4","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1111\/2041-210X.14104","article-title":"Classifying the unknown: insect identification with deep hierarchical Bayesian learning","volume":"14","author":"Badirli","year":"2023","journal-title":"Met. Ecol. Evol."},{"key":"2025111910421324300_bib5","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.biosystemseng.2019.04.007","article-title":"Influence of image quality on the identification of psyllids using convolutional neural networks","volume":"182","author":"Barbedo","year":"2019","journal-title":"Biosyst. Eng."},{"key":"2025111910421324300_bib6","doi-asserted-by":"crossref","first-page":"22169","DOI":"10.1073\/pnas.1011841108","article-title":"Herbaria are a major frontier for species discovery","volume":"107","author":"Bebber","year":"2010","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2025111910421324300_bib7","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/978-1-0716-0997-2_8","article-title":"Plant DNA barcoding principles and limits: a case study in the genus Vanilla","volume-title":"Molecular plant taxonomy: methods and protocols","author":"Besse","year":"2021"},{"key":"2025111910421324300_bib8","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1002\/edn3.74","article-title":"Maximizing fish detection with eDNA metabarcoding","volume":"2","author":"Bessey","year":"2020","journal-title":"Environm. DNA"},{"key":"2025111910421324300_bib9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12864-020-06892-5","article-title":"Machine learning based imputation techniques for estimating phylogenetic trees from incomplete distance matrices","volume":"21","author":"Bhattacharjee","year":"2020","journal-title":"BMC Genomics"},{"key":"2025111910421324300_bib10","doi-asserted-by":"crossref","first-page":"133","DOI":"10.3897\/zookeys.209.3178","article-title":"No specimen left behind: industrial scale digitization of natural history collections","volume":"209","author":"Blagoderov","year":"2012","journal-title":"ZooKeys"},{"key":"2025111910421324300_bib11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-020-03920-9","article-title":"Flora capture: a citizen science application for collecting structured plant observations","volume":"21","author":"Boho","year":"2020","journal-title":"BMC Bioinform."},{"key":"2025111910421324300_bib12","doi-asserted-by":"crossref","first-page":"1640","DOI":"10.1111\/2041-210X.13901","article-title":"Deep learning as a tool for ecology and evolution","volume":"13","author":"Borowiec","year":"2022","journal-title":"Methods Ecol. Evol."},{"key":"2025111910421324300_bib13","doi-asserted-by":"crossref","first-page":"e0178751","DOI":"10.1371\/journal.pone.0178751","article-title":"DeepNano: deep recurrent neural networks for base calling in MinION nanopore reads","volume":"12","author":"Bo\u017ea","year":"2017","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib14","doi-asserted-by":"crossref","first-page":"e0169515","DOI":"10.1371\/journal.pone.0169515","article-title":"Testing the efficacy of DNA barcodes for identifying the vascular plants of Canada","volume":"12","author":"Braukmann","year":"2017","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib15","volume-title":"LOOCV for evaluating machine learning algorithms","author":"Brownlee","year":"2020"},{"key":"2025111910421324300_bib16","doi-asserted-by":"crossref","first-page":"101017","DOI":"10.1016\/j.ecoinf.2019.101017","article-title":"Image-based species identification of wild bees using convolutional neural networks","volume":"55","author":"Buschbacher","year":"2020","journal-title":"Ecol. Inform."},{"key":"2025111910421324300_bib17","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"Camacho","year":"2009","journal-title":"BMC Bioinform."},{"key":"2025111910421324300_bib18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12862-017-1014-z","article-title":"Going deeper in the automated identification of Herbarium specimens","volume":"17","author":"Carranza-Rojas","year":"2017","journal-title":"BMC Evol. Biol."},{"key":"2025111910421324300_bib19","doi-asserted-by":"crossref","first-page":"3643","DOI":"10.1109\/CVPR42600.2020.00370","article-title":"Assessing image quality issues for real-world problems","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA","author":"Chiu","year":"2020"},{"key":"2025111910421324300_bib20","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","article-title":"The variant call format and VCFtools","volume":"27","author":"Danecek","year":"2011","journal-title":"Bioinformatics"},{"key":"2025111910421324300_bib21","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1111\/j.1095-8312.2005.00503.x","article-title":"Towards integrative taxonomy","volume":"85","author":"Dayrat","year":"2005","journal-title":"Biol. J. Linn. Soc."},{"key":"2025111910421324300_bib22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s13592-022-00918-5","article-title":"Image recognition using convolutional neural networks for classification of honey bee subspecies","volume":"53","author":"De Nart","year":"2022","journal-title":"Apidologie"},{"key":"2025111910421324300_bib23","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"ImageNet: a large-scale hierarchical image database","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA","author":"Deng","year":"2009"},{"key":"2025111910421324300_bib24","doi-asserted-by":"crossref","first-page":"106562","DOI":"10.1016\/j.ympev.2019.106562","article-title":"A demonstration of unsupervised machine learning in species delimitation","volume":"139","author":"Derkarabetian","year":"2019","journal-title":"Mol. Phylogenet. Evol."},{"key":"2025111910421324300_bib25","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1111\/2041-210X.14041","article-title":"Standardized nuclear markers improve and homogenize species delimitation in Metazoa","volume":"14","author":"Dietz","year":"2023","journal-title":"Methods Ecol. Evol."},{"key":"2025111910421324300_bib26","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1111\/1755-0998.12185","article-title":"Discriminating plants using the DNA barcode rbcLb: an appraisal based on a large data set","volume":"14","author":"Dong","year":"2014","journal-title":"Mol. Ecol. Resour."},{"key":"2025111910421324300_bib27","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/j.1600-0587.2012.07348.x","article-title":"Collinearity: a review of methods to deal with it and a simulation study evaluating their performance","volume":"36","author":"Dormann","year":"2013","journal-title":"Ecography"},{"key":"2025111910421324300_bib28","doi-asserted-by":"crossref","first-page":"102612","DOI":"10.1016\/j.pocean.2021.102612","article-title":"Automated classification of fauna in seabed photographs: the impact of training and validation dataset size, with considerations for the class imbalance","volume":"196","author":"Durden","year":"2021","journal-title":"Prog. Oceanogr."},{"key":"2025111910421324300_bib29","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1111\/j.1755-0998.2009.02652.x","article-title":"Are plant species inherently harder to discriminate than animal species using DNA barcoding markers? Mol","volume":"9","author":"Fazekas","year":"2009","journal-title":"Ecol. Resour."},{"key":"2025111910421324300_bib30","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1186\/s12859-018-2182-6","article-title":"Deep learning models for bacteria taxonomic classification of metagenomic data","volume":"19","author":"Fiannaca","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2025111910421324300_bib31","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1002\/rse2.352","article-title":"Gray whale detection in satellite imagery using deep learning","volume":"9","author":"Green","year":"2023","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"2025111910421324300_bib32","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1093\/sysbio\/sys038","article-title":"A unifying model for the analysis of phenotypic, genetic, and geographic data","volume":"61","author":"Guillot","year":"2012","journal-title":"Syst. Biol."},{"key":"2025111910421324300_bib33","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7_15","article-title":"Random Forests","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"Hastie","year":"2009"},{"key":"2025111910421324300_bib34","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"2025111910421324300_bib35","doi-asserted-by":"crossref","first-page":"S96","DOI":"10.1098\/rsbl.2003.0025","article-title":"Barcoding animal life: cytochrome c oxidase subunit 1 divergences among closely related species","volume":"270","author":"Hebert","year":"2003","journal-title":"Proc. Roy. Soc. London, Ser. B, Biol. Sci."},{"key":"2025111910421324300_bib36","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1098\/rspb.2002.2218","article-title":"Biological identifications through DNA barcodes","volume":"270","author":"Hebert","year":"2003","journal-title":"Proc. Roy. Soc. London, Ser. B, Biol. Sci."},{"key":"2025111910421324300_bib37","volume-title":"RVAideMemoire: testing and plotting procedures for biostatistics","author":"Herv\u00e9","year":"2023"},{"key":"2025111910421324300_bib38","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.12705\/676.6","article-title":"Mendelian segregation of leaf phenotypes in experimental F2 hybrids elucidates origin of morphological diversity of the apomictic Ranunculus auricomus complex","volume":"67","author":"Hoda\u010d","year":"2018","journal-title":"TAXON"},{"key":"2025111910421324300_bib39","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1111\/tpj.17053","article-title":"Deep learning to capture leaf shape in plant images: validation by geometric morphometrics","volume":"120","author":"Hoda\u010d","year":"2024","journal-title":"Plant J."},{"key":"2025111910421324300_bib40","doi-asserted-by":"crossref","first-page":"418","DOI":"10.3390\/biology12030418","article-title":"Geometric morphometric versus genomic patterns in a large polyploid plant species complex","volume":"12","author":"Hoda\u010d","year":"2023","journal-title":"Biology"},{"key":"2025111910421324300_bib41","doi-asserted-by":"crossref","first-page":"e19254","DOI":"10.1371\/journal.pone.0019254","article-title":"Choosing and using a plant DNA barcode","volume":"6","author":"Hollingsworth","year":"2011","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib42","doi-asserted-by":"crossref","first-page":"20150338","DOI":"10.1098\/rstb.2015.0338","article-title":"Telling plant species apart with DNA: from barcodes to genomes","volume":"371","author":"Hollingsworth","year":"2016","journal-title":"Philos. Trans. R. Soc. B, Biol. Sci."},{"key":"2025111910421324300_bib43","doi-asserted-by":"crossref","first-page":"e2002545117","DOI":"10.1073\/pnas.2002545117","article-title":"Deep learning and computer vision will transform entomology","volume":"118","author":"H\u00f8ye","year":"2021","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2025111910421324300_bib44","doi-asserted-by":"crossref","first-page":"3120","DOI":"10.1093\/bioinformatics\/btab354","article-title":"NeuralPolish: a novel Nanopore polishing method based on alignment matrix construction and orthogonal Bi-GRU Networks","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2025111910421324300_bib45","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2025111910421324300_bib46","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/j.tree.2023.11.002","article-title":"Species delimitation 4.0: integrative taxonomy meets artificial intelligence","volume":"39","author":"Karbstein","year":"2024","journal-title":"Trends Ecol. Evol."},{"key":"2025111910421324300_bib47","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1002\/tax.12365","article-title":"Phylogenomics supported by geometric morphometrics reveals delimitation of sexual species within the polyploid apomictic Ranunculus auricomus complex (Ranunculaceae)","volume":"69","author":"Karbstein","year":"2020","journal-title":"Taxon"},{"key":"2025111910421324300_bib48","doi-asserted-by":"crossref","first-page":"2659","DOI":"10.1111\/mec.15919","article-title":"Moving beyond assumptions: polyploidy and environmental effects explain a geographical parthenogenesis scenario in European plants","volume":"30","author":"Karbstein","year":"2021","journal-title":"Mol. Ecol."},{"key":"2025111910421324300_bib49","doi-asserted-by":"crossref","first-page":"2081","DOI":"10.1111\/nph.18284","article-title":"Untying Gordian knots: unraveling reticulate polyploid plant evolution by genomic data using the large Ranunculus auricomus species complex","volume":"235","author":"Karbstein","year":"2022","journal-title":"New Phytolog."},{"key":"2025111910421324300_bib50","first-page":"13","article-title":"Deep learning in plant phenological research: a systematic literature review","author":"Katal","year":"2022","journal-title":"Front. Plant Sci."},{"key":"2025111910421324300_bib51","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT Multiple Sequence Alignment Software Version 7: improvements in performance and usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol. Biol. Evol."},{"key":"2025111910421324300_bib52","doi-asserted-by":"crossref","first-page":"101633","DOI":"10.1016\/j.ecoinf.2022.101633","article-title":"An effective and fast solution for classification of wood species: a deep transfer learning approach","volume":"69","author":"and","year":"2022","journal-title":"Ecol. Inf."},{"key":"2025111910421324300_bib53","first-page":"320","article-title":"Image-based automated species identification: can virtual data augmentation overcome problems of insufficient sampling? Syst","volume":"71","author":"Klasen","year":"2022","journal-title":"Biol."},{"key":"2025111910421324300_bib54","doi-asserted-by":"crossref","first-page":"evad008","DOI":"10.1093\/gbe\/evad008","article-title":"Deep learning in population genetics","volume":"15","author":"Korfmann","year":"2023","journal-title":"Genome Biol. Evol."},{"key":"2025111910421324300_bib55","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1111\/1755-0998.12175","article-title":"Evaluation of 11 single-locus and seven multilocus DNA barcodes in Lamium L","volume":"14","author":"Krawczyk","year":"2014","journal-title":"(Lamiaceae). Mol. Ecol. Resour."},{"key":"2025111910421324300_bib56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J. Stat. Softw."},{"key":"2025111910421324300_bib57","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1073\/pnas.0709936105","article-title":"DNA barcoding the floras of biodiversity hotspots","volume":"105","author":"Lahaye","year":"2008","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2025111910421324300_bib58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-023-02941-w","article-title":"EvoAug: improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentations","volume":"24","author":"Lee","year":"2023","journal-title":"Genome Biol."},{"key":"2025111910421324300_bib59","doi-asserted-by":"crossref","first-page":"18226","DOI":"10.1038\/s41598-021-97619-3","article-title":"Plant biodiversity assessment through pollen DNA metabarcoding in Natura 2000 habitats (Italian Alps)","volume":"11","author":"Leontidou","year":"2021","journal-title":"Sci. Rep."},{"key":"2025111910421324300_bib60","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1111\/brv.12104","article-title":"Plant DNA barcoding: from gene to genome","volume":"90","author":"Li","year":"2015","journal-title":"Biol. Rev."},{"key":"2025111910421324300_bib61","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1007\/s00449-022-02716-w","article-title":"Prokaryotic and eukaryotic promoters identification based on residual network transfer learning","volume":"45","author":"Liu","year":"2022","journal-title":"Bioprocess Biosyst. Eng."},{"key":"2025111910421324300_bib62","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1111\/2041-210X.13611","article-title":"The Flora Incognita app\u2013interactive plant species identification","volume":"12","author":"M\u00e4der","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"2025111910421324300_bib63","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.3390\/plants11172224","article-title":"A revised phylogenetic classification for Viola (Violaceae)","volume":"11","author":"Marcussen","year":"2022","journal-title":"Plants"},{"key":"2025111910421324300_bib64","doi-asserted-by":"crossref","first-page":"e0192011","DOI":"10.1371\/journal.pone.0192011","article-title":"Ant genera identification using an ensemble of convolutional neural networks","volume":"13","author":"Marques","year":"2018","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib65","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s42979-021-00614-8","article-title":"FishResNet: automatic fish classification approach in underwater scenario","volume":"2","author":"Mathur","year":"2021","journal-title":"SN Comput. Sci."},{"key":"2025111910421324300_bib66","doi-asserted-by":"crossref","first-page":"31625","DOI":"10.1007\/s11042-020-09371-x","article-title":"Crosspooled FishNet: transfer learning based fish species classification model","volume":"79","author":"Mathur","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"2025111910421324300_bib67","doi-asserted-by":"crossref","first-page":"e0217084","DOI":"10.1371\/journal.pone.0217084","article-title":"Assessment of BOLD and GenBank\u2013their accuracy and reliability for the identification of biological materials","volume":"14","author":"Meiklejohn","year":"2019","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib68","doi-asserted-by":"crossref","first-page":"1685","DOI":"10.1111\/nph.18813","article-title":"Photographs as an essential biodiversity resource: drivers of gaps in the vascular plant photographic record","volume":"238","author":"Mesaglio","year":"2023","journal-title":"New Phytolog."},{"key":"2025111910421324300_bib69","doi-asserted-by":"crossref","first-page":"E5716","DOI":"10.1073\/pnas.1719367115","article-title":"Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning","volume":"115","author":"Norouzzadeh","year":"2018","journal-title":"Proc. Nat. Acad. Sci."},{"key":"2025111910421324300_bib70","doi-asserted-by":"crossref","first-page":"e13894","DOI":"10.1111\/1755-0998.13894","article-title":"Species delimitation with limited sampling: an example from rare trapdoor spider genus Cyclocosmia (Mygalomorphae, Halonoproctidae)","volume":"24","author":"Opatova","year":"2024","journal-title":"Mol. Ecol. Resour."},{"key":"2025111910421324300_bib71","first-page":"e000056","article-title":"SNP-sites: rapid efficient extraction of SNPs from multi-FASTA alignments","volume":"2","author":"Page","year":"2016","journal-title":"Microb. Genom."},{"key":"2025111910421324300_bib72","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1111\/2041-210X.12775","article-title":"Lost in parameter space: a road map for stacks","volume":"8","author":"Paris","year":"2017","journal-title":"Method. Ecol. Evol."},{"key":"2025111910421324300_bib73","first-page":"8026","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems 721","author":"Paszke","year":"2019"},{"key":"2025111910421324300_bib74","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1093\/biosci\/biaa044","article-title":"Machine learning using digitized Herbarium specimens to advance phenological research","volume":"70","author":"Pearson","year":"2020","journal-title":"BioScience"},{"key":"2025111910421324300_bib75","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"2025111910421324300_bib76","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/S0893-6080(98)00010-0","article-title":"Automatic early stopping using cross validation: quantifying the criteria","volume":"11","author":"Prechelt","year":"1998","journal-title":"Neural Netw."},{"key":"2025111910421324300_bib77","volume-title":"R: A Language and Environment for Statistical Computing","author":"R Core Team","year":"2023"},{"key":"2025111910421324300_bib78","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1111\/j.1471-8286.2007.01678.x","article-title":"Bold: the barcode of life data system (http:\/\/www.barcodinglife.org)","volume":"7","author":"Ratnasingham","year":"2007","journal-title":"Mol. Ecol. Notes"},{"key":"2025111910421324300_bib79","doi-asserted-by":"crossref","first-page":"e2584","DOI":"10.7717\/peerj.2584","article-title":"VSEARCH: a versatile open source tool for metagenomics","volume":"4","author":"Rognes","year":"2016","journal-title":"PeerJ"},{"key":"2025111910421324300_bib80","doi-asserted-by":"crossref","first-page":"1500074","DOI":"10.3732\/apps.1500074","article-title":"Lineage-specific evolutionary rate in plants: contributions of a screening for Cereus (Cactaceae)","volume":"4","author":"Romeiro-Brito","year":"2016","journal-title":"Appl. Plant Sci."},{"key":"2025111910421324300_bib81","first-page":"12","article-title":"Image-based automated recognition of 31 Poaceae species: the most relevant perspectives","author":"Rzanny","year":"2022","journal-title":"Front. Plant Sci."},{"key":"2025111910421324300_bib82","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining deep neural networks and beyond: a review of methods and applications","volume":"109","author":"Samek","year":"2021","journal-title":"Proc. IEEE"},{"key":"2025111910421324300_bib83","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1146\/annurev-ento-112408-085432","article-title":"Integrative taxonomy: a multisource approach to exploring biodiversity","volume":"55","author":"Schlick-Steiner","year":"2010","journal-title":"Annu. Rev. Entomol."},{"key":"2025111910421324300_bib84","first-page":"e74031","article-title":"Extracting data at scale: machine learning at the Natural History Museum","volume":"5","author":"Scott","year":"2021","journal-title":"Biodivers. Inf. Sci. Stand."},{"key":"2025111910421324300_bib85","doi-asserted-by":"crossref","first-page":"e0245230","DOI":"10.1371\/journal.pone.0245230","article-title":"Multi-view classification with convolutional neural networks","volume":"16","author":"Seeland","year":"2021","journal-title":"PLOS ONE"},{"key":"2025111910421324300_bib86","doi-asserted-by":"crossref","first-page":"8066","DOI":"10.1038\/s41598-022-11450-y","article-title":"Development of a system for the automated identification of herbarium specimens with high accuracy","volume":"12","author":"Shirai","year":"2022","journal-title":"Sci. Rep."},{"key":"2025111910421324300_bib87","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1111\/evo.12582","article-title":"Bayesian species delimitation combining multiple genes and traits in a unified framework","volume":"69","author":"Sol\u00eds-Lemus","year":"2015","journal-title":"Evolution"},{"key":"2025111910421324300_bib88","doi-asserted-by":"crossref","first-page":"bbab569","DOI":"10.1093\/bib\/bbab569","article-title":"Multimodal deep learning for biomedical data fusion: a review","volume":"23","author":"Stahlschmidt","year":"2022","journal-title":"Brief. Bioinform."},{"key":"2025111910421324300_bib89","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.pbi.2007.01.004","article-title":"How many genes are there in plants (... and why are they there)? Curr","volume":"10","author":"Sterck","year":"2007","journal-title":"Opin. Plant Biol."},{"key":"2025111910421324300_bib90","volume-title":"Plant taxonomy: the systematic evaluation of comparative data","author":"Stuessy","year":"2009"},{"key":"2025111910421324300_bib91","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"2025111910421324300_bib92","doi-asserted-by":"crossref","first-page":"1307","DOI":"10.12705\/636.13","article-title":"High-performance digitization of natural history collections: automated imaging lines for herbarium and insect specimens","volume":"63","author":"Tegelberg","year":"2014","journal-title":"TAXON"},{"key":"2025111910421324300_bib93","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1111\/2041-210X.13335","article-title":"Thinking like a naturalist: enhancing computer vision of citizen science images by harnessing contextual data","volume":"11","author":"Terry","year":"2020","journal-title":"Method. Ecol. Evol."},{"key":"2025111910421324300_bib94","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1111\/mec.15458","article-title":"Phylogenomics unravels Quaternary vicariance and allopatric speciation patterns in temperate-montane plant species: a case study on the Ranunculus auricomus species complex","volume":"29","author":"Tomasello","year":"2020","journal-title":"Mol. Ecol."},{"key":"2025111910421324300_bib95","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1016\/j.tree.2022.06.001","article-title":"Emerging technologies revolutionise insect ecology and monitoring","volume":"37","author":"van Klink","year":"2022","journal-title":"Trend. Ecol. Evol."},{"key":"2025111910421324300_bib96","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1111\/2041-210X.13075","article-title":"Machine learning for image based species identification","volume":"9","author":"W\u00e4ldchen","year":"2018","journal-title":"Method. Ecol. Evol."},{"key":"2025111910421324300_bib97","doi-asserted-by":"crossref","first-page":"e1005993","DOI":"10.1371\/journal.pcbi.1005993","article-title":"Automated plant species identification\u2014trends and future directions","volume":"14","author":"W\u00e4ldchen","year":"2018","journal-title":"PLOS Comput. Biol."},{"key":"2025111910421324300_bib98","doi-asserted-by":"crossref","first-page":"e11548","DOI":"10.1002\/aps3.11548","article-title":"From leaves to labels: building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2","volume":"11","author":"Weaver","year":"2023","journal-title":"Appl. Plant Sci."},{"key":"2025111910421324300_bib99","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1111\/2041-210X.14047","article-title":"BarKeeper\u2014a versatile web framework to assemble, analyse and manage DNA barcoding data and metadata","volume":"14","author":"Wiechers","year":"2023","journal-title":"Method. Ecol. Evol."},{"key":"2025111910421324300_bib100","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1093\/sysbio\/syab076","article-title":"Identification of species by combining molecular and morphological data using convolutional neural networks","volume":"71","author":"Yang","year":"2022","journal-title":"Syst. Biol."},{"key":"2025111910421324300_bib101","first-page":"022022","article-title":"An overview of overfitting and its solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J. Phys.: Conf. Ser."},{"key":"2025111910421324300_bib102","first-page":"plv045","article-title":"DNA barcodes from four loci provide poor resolution of taxonomic groups in the genus Crataegus","volume-title":"AoB PLANTS","author":"Zarrei","year":"2015"},{"key":"2025111910421324300_bib103","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1080\/10635150802032982","article-title":"Inferring species membership using DNA sequences with back-propagation neural networks","volume":"57","author":"Zhang","year":"2008","journal-title":"Syst. Biol."},{"key":"2025111910421324300_bib104","volume-title":"DNAGPT: a generalized pre-trained tool for versatile DNA sequence analysis tasks","author":"Zhang","year":"2023"},{"key":"2025111910421324300_bib105","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1117\/12.2672694","article-title":"The effect of input size on the accuracy of a convolutional neural network performing brain tumor detection","volume-title":"International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022)","author":"Zhao","year":"2023"}],"container-title":["Systematic Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/sysbio\/advance-article-pdf\/doi\/10.1093\/sysbio\/syaf026\/63485593\/syaf026.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/sysbio\/advance-article-pdf\/doi\/10.1093\/sysbio\/syaf026\/63485593\/syaf026.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T15:42:33Z","timestamp":1763566953000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/sysbio\/advance-article\/doi\/10.1093\/sysbio\/syaf026\/8161735"}},"subtitle":[],"editor":[{"given":"Manolo","family":"Perez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1093\/sysbio\/syaf026","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.22.634270","asserted-by":"object"}]},"ISSN":["1063-5157","1076-836X"],"issn-type":[{"value":"1063-5157","type":"print"},{"value":"1076-836X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,13]]},"article-number":"syaf026"}}