{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:30:04Z","timestamp":1785407404892,"version":"3.56.0"},"posted":{"date-parts":[[2026,4,1]]},"group-title":"Bioinformatics","reference-count":62,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"crossref","award":["2137533"],"award-info":[{"award-number":["2137533"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"crossref","award":["2009075"],"award-info":[{"award-number":["2009075"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01HG010774"],"award-info":[{"award-number":["R01HG010774"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R35GM148253"],"award-info":[{"award-number":["R35GM148253"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100011929","name":"Foundation for Food and Agriculture Research","doi-asserted-by":"crossref","award":["CA18-SS-0000000009"],"award-info":[{"award-number":["CA18-SS-0000000009"]}],"id":[{"id":"10.13039\/100011929","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100016759","name":"National Council for Air and Stream Improvement","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016759","id-type":"DOI","asserted-by":"crossref"}]},{"award":["2023-67013-39910"],"award-info":[{"award-number":["2023-67013-39910"]}],"id":[{"id":"https:\/\/ror.org\/01na82s61","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Pollen is a robust and widespread substance that captures a historical snapshot of a specific time and place, and it can be used to track movements through space by examining the pollen deposited on various objects. Palynology, the study of pollen, is used across fields such as conservation, natural history, and forensics, where it is particularly useful for tracing the origin and movement of objects. However, pollen has remained underutilized due to the difficulty of distinguishing many pollen taxa beyond the family level and limited pollen reference material to support location predictions. With recent developments in pollen DNA metabarcoding these issues have been rectified, but much of the available pollen data are primarily from wind-pollinated species, which are widespread and less informative of specific sample locations. Bee-collected pollen presents an untapped resource in training predictive models to geolocate sample origin. Here we compiled bee-collected pollen DNA sequence relative abundance data from three projects in the western U.S. and assessed the accuracy of supervised machine learning models to predict the location of sample origin based solely on pollen assemblage, without the need of incorporating additional data. Random Forest and k-Nearest Neighbors models yielded high accuracy across all projects. We also found that models trained on taxonomically clustered pollen assigned sequence variants (ASVs) performed slightly better than those trained on raw sequence data, but the difference was minor, indicating that models trained on raw sequence data can reliably predict location and avoid the time-consuming taxonomic assignment process. Our results demonstrate the utility of repurposing bee-collected pollen for geolocation and provide a framework for employing supervised machine learning in future geolocation efforts.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Highlights<\/jats:title>\n                  <jats:list list-type=\"bullet\">\n                    <jats:list-item>\n                      <jats:p>Bee-collected pollen metabarcoding data was used to accurately predict sample origin<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Random Forest and k-Nearest Neighbors algorithms were most accurate with lowest error<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Taxonomically-classified and raw DNA sequence data training sets performed comparably<\/jats:p>\n                    <\/jats:list-item>\n                  <\/jats:list>\n                <\/jats:sec>","DOI":"10.64898\/2026.03.29.715128","type":"posted-content","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:40:16Z","timestamp":1775040016000},"source":"Crossref","is-referenced-by-count":0,"title":["Assessing the potential of bee-collected pollen sequence data to train machine learning models for geolocation of sample origin"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6167-201X","authenticated-orcid":false,"given":"Rebecca A.","family":"Hayes","sequence":"first","affiliation":[{"name":"Institute of Ecology and Evolution Department of Biology, University of Oregon, 272 Onyx Bridge, Eugene, OR USA, 97403"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4381-4680","authenticated-orcid":false,"given":"Andrew D.","family":"Kern","sequence":"additional","affiliation":[{"name":"Institute of Ecology and Evolution Department of Biology, University of Oregon, 272 Onyx Bridge, Eugene, OR USA, 97403"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren C.","family":"Ponisio","sequence":"additional","affiliation":[{"name":"Institute of Ecology and Evolution Department of Biology, University of Oregon, 272 Onyx Bridge, Eugene, OR USA, 97403"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026040409350460000_2026.03.29.715128v1.1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0905845106"},{"key":"2026040409350460000_2026.03.29.715128v1.2","doi-asserted-by":"crossref","unstructured":"Awad, M. , R. Khanna , M. Awad , and R. Khanna . 2015. Support vector regression. Efficient learning machines: Theories, concepts, and applications for engineers and system designers pages 67\u201380.","DOI":"10.1007\/978-1-4302-5990-9_4"},{"key":"2026040409350460000_2026.03.29.715128v1.3","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.54507"},{"key":"2026040409350460000_2026.03.29.715128v1.4","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1111\/mec.14840","article-title":"Quantitative and qualitative assessment of pollen DNA metabarcoding using constructed species mixtures","volume":"28","year":"2019","journal-title":"Molecular Ecology"},{"key":"2026040409350460000_2026.03.29.715128v1.5","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.fsigen.2015.12.010","article-title":"Review and future prospects for DNA barcoding methods in forensic palynology","volume":"21","year":"2016","journal-title":"Forensic Science International: Genetics"},{"key":"2026040409350460000_2026.03.29.715128v1.6","doi-asserted-by":"publisher","DOI":"10.1139\/gen-2015-0200"},{"key":"2026040409350460000_2026.03.29.715128v1.7","doi-asserted-by":"crossref","first-page":"1600110","DOI":"10.3732\/apps.1600110","article-title":"An rbcL reference library to aid in the identification of plant species mixtures by DNA metabarcoding","volume":"5","year":"2017","journal-title":"Appl. Plant Sci"},{"key":"2026040409350460000_2026.03.29.715128v1.8","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","year":"2012","journal-title":"The journal of machine learning research"},{"key":"2026040409350460000_2026.03.29.715128v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-019-0209-9"},{"key":"2026040409350460000_2026.03.29.715128v1.10","first-page":"1","article-title":"A survey of predictive modeling on imbalanced domains","volume":"49","year":"2016","journal-title":"ACM computing surveys (CSUR)"},{"key":"2026040409350460000_2026.03.29.715128v1.11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026040409350460000_2026.03.29.715128v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2005.11.021"},{"key":"2026040409350460000_2026.03.29.715128v1.13","doi-asserted-by":"crossref","unstructured":"Bryant Jr, V. M. , and R. G. Holloway , 1983. The role of palynology in archaeology. Pages 191\u2013224 in Advances in archaeological method and theory. Elsevier.","DOI":"10.1016\/B978-0-12-003106-1.50010-9"},{"key":"2026040409350460000_2026.03.29.715128v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3869"},{"key":"2026040409350460000_2026.03.29.715128v1.15","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1007\/s00442-022-05151-6","article-title":"Functional traits of plants and pollinators explain resource overlap between honeybees and wild pollinators","volume":"198","year":"2022","journal-title":"Oecologia"},{"key":"2026040409350460000_2026.03.29.715128v1.16","first-page":"1","article-title":"Xgboost: extreme gradient boosting","volume":"1","year":"2015","journal-title":"R package version 0.4-2"},{"key":"2026040409350460000_2026.03.29.715128v1.17","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2021.1369"},{"key":"2026040409350460000_2026.03.29.715128v1.18","first-page":"317","article-title":"Palynology and environmental history during the Quaternary period","volume":"57","year":"1969","journal-title":"American Scientist"},{"key":"2026040409350460000_2026.03.29.715128v1.19","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1139\/x91-163","article-title":"Factors affecting pollen dynamics and its importance to pollen contamination: a review","volume":"21","year":"1991","journal-title":"Canadian Journal of Forest Research"},{"key":"2026040409350460000_2026.03.29.715128v1.20","doi-asserted-by":"crossref","unstructured":"Dietterich, T. G ., 2000. Ensemble methods in machine learning. Pages 1\u201315 in International workshop on multiple classifier systems. Springer.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"2026040409350460000_2026.03.29.715128v1.21","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s41651-020-00048-5","article-title":"Advances of four machine learning methods for spatial data handling: A review","volume":"4","year":"2020","journal-title":"Journal of Geovisualization and Spatial Analysis"},{"key":"2026040409350460000_2026.03.29.715128v1.22","first-page":"119","article-title":"Open research data, data portals and data publication\u2013an introduction to the data curation landscape","volume":"85","year":"2016","journal-title":"Polarforschung"},{"key":"2026040409350460000_2026.03.29.715128v1.23","unstructured":"Erdtman, G . 2023. Pollen morphology and plant taxonomy: Angiosperms (an introduction to palynology). Brill."},{"key":"2026040409350460000_2026.03.29.715128v1.24","unstructured":"Faegri, K. , and J. Iversen . 1992. Textbook of Pollen Analysis. 4 edition. Blackwell Scientific Publications."},{"key":"2026040409350460000_2026.03.29.715128v1.25","doi-asserted-by":"crossref","unstructured":"Fan Brown, J. J. , K. Moriarty , R. McDonald , L. R. Best , J. F. Zorn , and L. C. Ponisio . 2025. Mid-Seral Thinned Stands in Pacific Northwest Coastal Forests Show Enhanced Floral and Bee Diversity without Increased Parasite Prevalence in Wild Bees. J. For. pages 1\u201327.","DOI":"10.1007\/s44392-025-00033-0"},{"key":"2026040409350460000_2026.03.29.715128v1.26","doi-asserted-by":"crossref","unstructured":"Goodman, F. , J. Doughty , C. Gary , C. Christou , B. Hu , E. Hultman , D. Deanto , and D. Masters , 2015. PIGLT: a pollen identification and geolocation system for forensic applications. Pages 1\u20137 in 2015 IEEE International Symposium on Technologies for Homeland Security (HST). IEEE.","DOI":"10.1109\/THS.2015.7225271"},{"key":"2026040409350460000_2026.03.29.715128v1.27","doi-asserted-by":"publisher","DOI":"10.2307\/1942246"},{"key":"2026040409350460000_2026.03.29.715128v1.28","doi-asserted-by":"crossref","first-page":"101443","DOI":"10.1016\/j.ecoinf.2021.101443","article-title":"Network-based geoforensics: Connecting pollen and plants to place","volume":"66","year":"2021","journal-title":"Ecological Informatics"},{"key":"2026040409350460000_2026.03.29.715128v1.29","first-page":"1","article-title":"A machine learning framework to determine geolocations from metagenomic profiling","volume":"15","year":"2020","journal-title":"Biology direct"},{"key":"2026040409350460000_2026.03.29.715128v1.30","doi-asserted-by":"crossref","unstructured":"Hwang, G. M. , K. C. Riley , C. T. Christou , G. M. Jacyna , J. P. Woodard , R. M. Ryan , M. B. Bush , B. G. Valencia , C. N. McMichael , S. W. Punyasena , et al., 2013. Automated pollen identification system for forensic geo-historical location applications. Pages 297\u2013303 in 2013 IEEE International Conference on Technologies for Homeland Security (HST). IEEE.","DOI":"10.1109\/THS.2013.6699018"},{"key":"2026040409350460000_2026.03.29.715128v1.31","doi-asserted-by":"crossref","unstructured":"Karstens, L. , M. Asquith , S. Davin , D. Fair , W. T. Gregory , A. J. Wolfe , J. Braun , and S. McWeeney . 2019. Controlling for contaminants in low-biomass 16S rRNA gene sequencing experiments. MSystems 4.","DOI":"10.1128\/mSystems.00290-19"},{"key":"2026040409350460000_2026.03.29.715128v1.32","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/mst010"},{"key":"2026040409350460000_2026.03.29.715128v1.33","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1111\/plb.12251","article-title":"Evaluating multiplexed next-generation sequencing as a method in palynology for mixed pollen samples","volume":"17","year":"2015","journal-title":"Plant Biology"},{"key":"2026040409350460000_2026.03.29.715128v1.34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1216057111"},{"key":"2026040409350460000_2026.03.29.715128v1.35","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1017\/psrm.2018.23","article-title":"Lost in space: Geolocation in event data","volume":"7","year":"2019","journal-title":"Political science research and methods"},{"key":"2026040409350460000_2026.03.29.715128v1.36","doi-asserted-by":"crossref","first-page":"370","DOI":"10.3390\/insects10110370","article-title":"A multiscale review of behavioral variation in collective foraging behavior in honey bees","volume":"10","year":"2019","journal-title":"Insects"},{"key":"2026040409350460000_2026.03.29.715128v1.37","doi-asserted-by":"publisher","DOI":"10.1111\/mec.13608"},{"key":"2026040409350460000_2026.03.29.715128v1.38","doi-asserted-by":"crossref","unstructured":"McGlone, M. S ., 1988. New Zealand. Pages 557\u2013599 in B. Huntley and T. I. Webb , editors. Vegetation History. Kluwer Academic Publishers, Amsterdam.","DOI":"10.1007\/978-94-009-3081-0_15"},{"key":"2026040409350460000_2026.03.29.715128v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2006.07.012"},{"key":"2026040409350460000_2026.03.29.715128v1.40","doi-asserted-by":"crossref","first-page":"e0244317","DOI":"10.1371\/journal.pone.0244317","article-title":"Applying machine learning and geolocation techniques to social media data (Twitter) to develop a resource for urban planning","volume":"16","year":"2021","journal-title":"PloS one"},{"key":"2026040409350460000_2026.03.29.715128v1.41","doi-asserted-by":"publisher","DOI":"10.2307\/1939310"},{"key":"2026040409350460000_2026.03.29.715128v1.42","doi-asserted-by":"crossref","first-page":"108090","DOI":"10.1016\/j.dib.2022.108090","article-title":"rbcL gene in global molecular data repository","volume":"42","year":"2022","journal-title":"Data in Brief"},{"key":"2026040409350460000_2026.03.29.715128v1.43","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2026040409350460000_2026.03.29.715128v1.44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0009490"},{"key":"2026040409350460000_2026.03.29.715128v1.45","doi-asserted-by":"crossref","unstructured":"Qi, Y . 2012. Random forest for bioinformatics. Ensemble machine learning: Methods and applications pages 307\u2013323.","DOI":"10.1007\/978-1-4419-9326-7_11"},{"key":"2026040409350460000_2026.03.29.715128v1.46","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.10895"},{"key":"2026040409350460000_2026.03.29.715128v1.47","doi-asserted-by":"crossref","first-page":"74349","DOI":"10.1007\/s11042-024-18426-2","article-title":"The accuracy of machine learning models relies on hyperparameter tuning: student result classification using random forest, randomized search, grid search, bayesian, genetic, and optuna algorithms","volume":"83","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"2026040409350460000_2026.03.29.715128v1.48","doi-asserted-by":"crossref","first-page":"e17306","DOI":"10.1111\/mec.17306","article-title":"Plant\u2013 pollinator network architecture does not impact intraspecific microbiome variability","volume":"33","year":"2024","journal-title":"Molecular Ecology"},{"key":"2026040409350460000_2026.03.29.715128v1.49","doi-asserted-by":"crossref","first-page":"e03863","DOI":"10.1002\/ecs2.3863","article-title":"Sex-associated differences in the network roles of pollinators","volume":"12","year":"2021","journal-title":"Ecosphere"},{"key":"2026040409350460000_2026.03.29.715128v1.50","doi-asserted-by":"publisher","DOI":"10.1101\/gr.361602"},{"key":"2026040409350460000_2026.03.29.715128v1.51","doi-asserted-by":"crossref","unstructured":"Steinbach, M. , and P.-N. Tan , 2009. kNN: k-nearest neighbors. Pages 165\u2013176 in The top ten algorithms in data mining. Chapman and Hall\/CRC.","DOI":"10.1201\/9781420089653-15"},{"key":"2026040409350460000_2026.03.29.715128v1.52","doi-asserted-by":"crossref","unstructured":"Testas, A ., 2023. Decision tree regression with pandas, scikit-learn, and PySpark. Pages 75\u2013113 in Distributed Machine Learning with PySpark: Migrating Effortlessly from Pandas and Scikit-Learn. Springer.","DOI":"10.1007\/978-1-4842-9751-3_4"},{"key":"2026040409350460000_2026.03.29.715128v1.53","doi-asserted-by":"crossref","first-page":"e8621","DOI":"10.3897\/oneeco.1.e8621","article-title":"Adoption of machine learning techniques in ecology and earth science","volume":"1","year":"2016","journal-title":"One Ecosystem"},{"key":"2026040409350460000_2026.03.29.715128v1.54","doi-asserted-by":"crossref","first-page":"101615","DOI":"10.1016\/j.compenvurbsys.2021.101615","article-title":"Identifying the spatial footprint of pollen distributions using the Geoforensic Interdiction (GOFIND) model","volume":"87","year":"2021","journal-title":"Computers, Environment and Urban Systems"},{"key":"2026040409350460000_2026.03.29.715128v1.55","doi-asserted-by":"crossref","first-page":"e10609","DOI":"10.1002\/ece3.10609","article-title":"Density of wild honey bee, Apis mellifera, colonies worldwide","volume":"13","year":"2023","journal-title":"Ecology and Evolution"},{"key":"2026040409350460000_2026.03.29.715128v1.56","doi-asserted-by":"crossref","first-page":"110061","DOI":"10.1016\/j.forsciint.2019.110061","article-title":"Using museum pelt collections to generate pollen prints from high-risk regions: a new palynological forensic strategy for geolocation","volume":"306","year":"2020","journal-title":"Forensic science international"},{"key":"2026040409350460000_2026.03.29.715128v1.57","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1080\/00173134.2016.1269188","article-title":"PalDat 3.0\u2013second revision of the database, including a free online publication tool","volume":"56","year":"2017","journal-title":"Grana"},{"key":"2026040409350460000_2026.03.29.715128v1.58","doi-asserted-by":"publisher","DOI":"10.1016\/j.quascirev.2008.01.004"},{"key":"2026040409350460000_2026.03.29.715128v1.59","doi-asserted-by":"publisher","DOI":"10.1080\/01916122.2015.1091138"},{"key":"2026040409350460000_2026.03.29.715128v1.60","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.gpb.2014.09.001","article-title":"Application of next-generation sequencing technology in forensic science","volume":"12","year":"2014","journal-title":"Genomics, proteomics & bioinformatics"},{"key":"2026040409350460000_2026.03.29.715128v1.61","doi-asserted-by":"publisher","DOI":"10.1007\/s13592-020-00839-1"},{"key":"2026040409350460000_2026.03.29.715128v1.62","doi-asserted-by":"crossref","unstructured":"Zhang, C. , and Y. Ma . 2012. Ensemble machine learning. Springer.","DOI":"10.1007\/978-1-4419-9326-7"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.29.715128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T16:35:19Z","timestamp":1775320519000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.03.29.715128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":62,"URL":"https:\/\/doi.org\/10.64898\/2026.03.29.715128","relation":{},"subject":[],"published":{"date-parts":[[2026,4,1]]},"subtype":"preprint"}}