{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:29:19Z","timestamp":1786667359810,"version":"build-2736575974"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2021-NR058630"],"award-info":[{"award-number":["RS-2021-NR058630"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Dinosaur footprints provide crucial paleoecological information about locomotion, behavior, and tracksite distributions. Traditional tracksite surveys rely on time-consuming manual identification by expert researchers, with results influenced by preservation quality and subjective interpretation. Here, we present an automated detection system for dinosaur footprints using You Only Look Once version 8 (YOLOv8), an effective object detection neural network. We trained the model on 49,242 images from the AI-Hub dataset, comprising theropod, ornithopod, and sauropod footprints from Korean tracksites. The final model achieved a mean average precision (mAP50) of 0.949 and mAP50-95 of 0.660. To address resolution-dependent detection challenges, we developed a multi-scale detection approach combining predictions across eight different image resolutions. Testing on previously unseen tracksites demonstrated successful detection of footprints from both Korea and Brazil, including the ichnospecies\n                    <jats:italic>Farlowichnus rapidus<\/jats:italic>\n                    , indicating strong cross-regional generalization. Our results show that detection accuracy depends on illumination conditions, preservation quality, and the presence of outline markings. This deep learning approach offers an efficient alternative to manual tracksite exploration, enabling rapid spatial distribution mapping of extensive dinosaur tracksites while providing objective, reproducible detection results.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-56031-5","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:53:43Z","timestamp":1780541623000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning enables automated detection of dinosaur footprints with high accuracy"],"prefix":"10.1038","volume":"16","author":[{"given":"Yeoncheol","family":"Ha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-Sep","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"56031_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s41513-023-00226-6","volume":"50","author":"I D\u00edaz-Mart\u00ednez","year":"2024","unstructured":"D\u00edaz-Mart\u00ednez, I., Citton, P. & Castanera, D. What do their footprints tell us? Many questions and some answers about the life of non-avian dinosaurs. J. Iber. Geol. 50, 5\u201326 (2024).","journal-title":"J. Iber. Geol."},{"key":"56031_CR2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2413810121","volume":"121","author":"TA Dececchi","year":"2024","unstructured":"Dececchi, T. A. et al. Theropod trackways as indirect evidence of pre-avian aerial behavior. Proc. Natl. Acad. Sci. U.S.A. 121, e2413810121 (2024).","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"56031_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.palaeo.2010.04.020","volume":"293","author":"BS Kim","year":"2010","unstructured":"Kim, B. S. & Huh, M. Analysis of the acceleration phase of a theropod dinosaur based on a Cretaceous trackway from Korea. Palaeogeogr. Palaeoclimatol. Palaeoecol. 293, 1\u20138 (2010).","journal-title":"Palaeogeogr. Palaeoclimatol. Palaeoecol."},{"key":"56031_CR4","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1080\/08912963.2022.2106563","volume":"35","author":"JH Lee","year":"2023","unstructured":"Lee, J. H. et al. Dinosaur tracksites from the Cretaceous Sagok Formation in the Uiseong Regional Geopark, South Korea: historical, palaeobiological perspectives. Hist. Biol. 35, 1656\u20131664 (2023).","journal-title":"Hist. Biol."},{"key":"56031_CR5","doi-asserted-by":"publisher","first-page":"37","DOI":"10.2307\/3514457","volume":"1","author":"MG Lockley","year":"1986","unstructured":"Lockley, M. G. The paleobiological and paleoenvironmental importance of dinosaur footprints. Palaios 1, 37\u201347 (1986).","journal-title":"Palaios"},{"key":"56031_CR6","doi-asserted-by":"publisher","unstructured":"Ahn, J., Wohn, K.-Y. & Kong, D.-Y. 3D digital documentation of dinosaur footprints. In 16th International Conference on Virtual Systems and Multimedia 340\u2013345. https:\/\/doi.org\/10.1109\/VSMM.2010.5665935 (IEEE, 2010).","DOI":"10.1109\/VSMM.2010.5665935"},{"key":"56031_CR7","doi-asserted-by":"publisher","first-page":"662","DOI":"10.5467\/JKESS.2021.42.6.662","volume":"42","author":"H Jo","year":"2021","unstructured":"Jo, H. et al. A survey of Yeosu Sado dinosaur tracksite and utilization of educational materials using 3D photogrammetry. J. Korean Earth Sci. Soc. 42, 662\u2013676 (2021).","journal-title":"J. Korean Earth Sci. Soc."},{"key":"56031_CR8","doi-asserted-by":"publisher","first-page":"129","DOI":"10.5467\/JKESS.2010.31.2.129","volume":"31","author":"D-Y Kong","year":"2010","unstructured":"Kong, D.-Y., Lim, J.-D., Kim, J.-Y. & Kim, K. S. Application of digital photogrammetry to dinosaur tracks from the Namhae Gain-ri tracksite. J. Korean Earth Sci. Soc. 31, 129\u2013138 (2010).","journal-title":"J. Korean Earth Sci. Soc."},{"key":"56031_CR9","first-page":"303","volume":"83","author":"FM Petti","year":"2008","unstructured":"Petti, F. M. et al. Digital 3D modelling of dinosaur footprints by photogrammetry and laser scanning techniques: integrated approach at the Coste dell\u2019Anglone tracksite (Lower Jurassic, Southern Alps, Northern Italy). Studi Trent. Sci. Nat., Acta Geol. 83, 303\u2013315 (2008).","journal-title":"Studi Trent. Sci. Nat., Acta Geol."},{"key":"56031_CR10","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2022.0588","volume":"19","author":"JN Lallensack","year":"2022","unstructured":"Lallensack, J. N., Romilio, A. & Falkingham, P. L. A machine learning approach for the discrimination of theropod and ornithischian dinosaur tracks. J. R. Soc. Interface 19, 20220588 (2022).","journal-title":"J. R. Soc. Interface"},{"key":"56031_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/pab.2015.39","volume":"42","author":"SE Peters","year":"2016","unstructured":"Peters, S. E. & McClennen, M. The Paleobiology Database application programming interface. Paleobiology 42, 1\u20137 (2016).","journal-title":"Paleobiology"},{"key":"56031_CR12","first-page":"7","volume":"24","author":"DC Adams","year":"2013","unstructured":"Adams, D. C., Rohlf, F. J. & Slice, D. E. A field comes of age: Geometric morphometrics in the 21st century. Hystrix Ital. J. Mammal. 24, 7\u201314 (2013).","journal-title":"Hystrix Ital. J. Mammal."},{"key":"56031_CR13","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1038\/261129a0","volume":"261","author":"RM Alexander","year":"1976","unstructured":"Alexander, R. M. Estimates of speeds of dinosaurs. Nature 261, 129\u2013130 (1976).","journal-title":"Nature"},{"key":"56031_CR14","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1666\/13-090","volume":"88","author":"JA Bright","year":"2014","unstructured":"Bright, J. A. A review of paleontological finite element models and their validity. J. Paleontol. 88, 760\u2013769 (2014).","journal-title":"J. Paleontol."},{"key":"56031_CR15","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y. et al. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541\u2013551 (1989).","journal-title":"Neural Comput."},{"key":"56031_CR16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0293020","volume":"18","author":"Y Ha","year":"2023","unstructured":"Ha, Y. & Kim, S.-S. Classification of large ornithopod dinosaur footprints using Xception transfer learning. PLoS One 18, e0293020 (2023).","journal-title":"PLoS One"},{"key":"56031_CR17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2527222122","volume":"123","author":"G Hartmann","year":"2026","unstructured":"Hartmann, G., Blakesley, T., dePolo, P. E. & Brusatte, S. L. Identifying variation in dinosaur footprints and classifying problematic specimens via unbiased unsupervised machine learning. Proc. Natl. Acad. Sci. U.S.A. 123, e2527222122 (2026).","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"56031_CR18","unstructured":"Jocher, G., Chaurasia, A. & Qiu, J. Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics (2023)."},{"key":"56031_CR19","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.cretres.2018.06.003","volume":"91","author":"YN Lee","year":"2018","unstructured":"Lee, Y. N., Lee, H. J., Han, S. Y., Park, E. & Lee, C. H. A new dinosaur tracksite from the Lower Cretaceous Sanbukdong Formation of Gunsan City, South Korea. Cretac. Res. 91, 208\u2013216 (2018).","journal-title":"Cretac. Res."},{"key":"56031_CR20","unstructured":"Huh, M. et al. Dinosaur Fossils of Korea (Kungree, 2009)."},{"key":"56031_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cretres.2023.105720","volume":"153","author":"G Leonardi","year":"2024","unstructured":"Leonardi, G., Fernandes, M. A., Carvalho, I. D. S., Schutzer, J. B. & Silva, R. C. D. Farlowichnus rapidus new ichnogen., new ichnosp.: A speedy and small theropod in the Early Cretaceous Botucatu paleodesert (Paran\u00e1 Basin), Brazil. Cretac. Res. 153, 105720 (2024).","journal-title":"Cretac. Res."},{"key":"56031_CR22","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1080\/10420940.2012.664059","volume":"19","author":"J-D Lim","year":"2012","unstructured":"Lim, J.-D., Lockley, M. G. & Kong, D.-Y. The trackway of a quadrupedal ornithopod from the Jindong Formation (Cretaceous) of Korea. Ichnos 19, 101\u2013104 (2012).","journal-title":"Ichnos"},{"key":"56031_CR23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0115477","volume":"10","author":"I D\u00edaz-Mart\u00ednez","year":"2015","unstructured":"D\u00edaz-Mart\u00ednez, I., Pereda-Suberbiola, X., P\u00e9rez-Lorente, F. & Canudo, J. I. Ichnotaxonomic review of large ornithopod dinosaur tracks: Temporal and geographic implications. PLoS One 10, e0115477 (2015).","journal-title":"PLoS One"},{"key":"56031_CR24","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: unified, real-time object detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 779\u2013788. https:\/\/doi.org\/10.1109\/CVPR.2016.91 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"56031_CR25","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","volume":"5","author":"J Terven","year":"2023","unstructured":"Terven, J., C\u00f3rdova-Esparza, D. M. & Romero-Gonz\u00e1lez, J. A. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Mach. Learn. Knowl. Extr. 5, 1680\u20131716 (2023).","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"56031_CR26","unstructured":"Ultralytics. YOLOv8 anchor-free bounding box prediction. https:\/\/github.com\/ultralytics\/ultralytics\/issues\/189 (2023)."},{"key":"56031_CR27","doi-asserted-by":"publisher","unstructured":"Wang, C. Y. et al. CSPNet: A new backbone that can enhance learning capability of CNN. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 1571\u20131580. https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00203 (IEEE, 2020).","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"56031_CR28","doi-asserted-by":"publisher","unstructured":"Ramachandran, P., Zoph, B. & Le, Q. V. Searching for activation functions. Preprint at\u00a0https:\/\/doi.org\/10.48550\/ARXIV.1710.05941 (2017).","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"56031_CR29","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1904\u20131916 (2015).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"56031_CR30","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1007\/s10341-024-01085-w","volume":"66","author":"T Uygun","year":"2024","unstructured":"Uygun, T. & Ozguven, M. M. Real-time detection of shot-hole disease in cherry fruit using deep learning techniques via smartphone. Appl. Fruit Sci. 66, 875\u2013885 (2024).","journal-title":"Appl. Fruit Sci."},{"key":"56031_CR31","doi-asserted-by":"publisher","unstructured":"Lin, T. Y. et al. Feature pyramid networks for object detection. In\u00a0IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"56031_CR32","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J. & Jia, J. Path aggregation network for instance segmentation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition 8759\u20138768. https:\/\/doi.org\/10.1109\/CVPR.2018.00913 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00913"},{"key":"56031_CR33","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-47460-7","volume":"13","author":"R-Y Ju","year":"2023","unstructured":"Ju, R.-Y. & Cai, W. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Sci. Rep. 13, 20077 (2023).","journal-title":"Sci. Rep."},{"key":"56031_CR34","doi-asserted-by":"publisher","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z. & Sun, J. YOLOX: Exceeding YOLO Series in 2021. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2107.08430 (2021).","DOI":"10.48550\/ARXIV.2107.08430"},{"key":"56031_CR35","doi-asserted-by":"publisher","unstructured":"Tian, Z., Shen, C., Chen, H. & He, T. FCOS: A simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 1\u20131. https:\/\/doi.org\/10.1109\/TPAMI.2020.3032166 (2020).","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"56031_CR36","unstructured":"Li, X. et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In NIPS\u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems (2020)."},{"key":"56031_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Z. et al. Distance-IoU Loss: Faster and better learning for bounding box regression. In\u00a0Proc. AAAI Conf. Artif. Intell.\u00a0Vol. 34, 12993\u201313000 (2020).","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"56031_CR38","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.cretres.2005.10.003","volume":"27","author":"M Huh","year":"2006","unstructured":"Huh, M. et al. Well-preserved theropod tracks from the Upper Cretaceous of Hwasun County, southwestern South Korea, and their paleobiological implications. Cretac. Res. 27, 123\u2013138 (2006).","journal-title":"Cretac. Res."},{"key":"56031_CR39","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.palaeo.2008.02.003","volume":"262","author":"JY Kim","year":"2008","unstructured":"Kim, J. Y. et al. New didactyl dinosaur footprints (Dromaeosauripus hamanensis ichnogen. et ichnosp. nov.) from the Early Cretaceous Haman Formation, south coast of Korea. Palaeogeogr. Palaeoclimatol. Palaeoecol. 262, 72\u201378 (2008).","journal-title":"Palaeogeogr. Palaeoclimatol. Palaeoecol."},{"key":"56031_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-35289-4","volume":"8","author":"KS Kim","year":"2018","unstructured":"Kim, K. S. et al. Smallest known raptor tracks suggest microraptorine activity in lakeshore setting. Sci. Rep. 8, 16908 (2018).","journal-title":"Sci. Rep."},{"key":"56031_CR41","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.cretres.2007.04.003","volume":"29","author":"MG Lockley","year":"2008","unstructured":"Lockley, M. G. et al. Minisauripus\u2015the track of a diminutive dinosaur from the Cretaceous of China and South Korea: Implications for stratigraphic correlation and theropod foot morphodynamics. Cretac. Res. 29, 115\u2013130 (2008).","journal-title":"Cretac. Res."},{"key":"56031_CR42","doi-asserted-by":"publisher","first-page":"2430","DOI":"10.1080\/08912963.2021.2018687","volume":"34","author":"MG Lockley","year":"2022","unstructured":"Lockley, M. G. et al. A high-density Grallator assemblage from the Haman Formation (Cretaceous), Korea: Implications for Cretaceous distribution of grallatorids in East Asia. Hist. Biol. 34, 2430\u20132438 (2022).","journal-title":"Hist. Biol."},{"key":"56031_CR43","doi-asserted-by":"publisher","unstructured":"Cubuk, E. D. et al. AutoAugment: Learning augmentation policies from data. Preprint at\u00a0https:\/\/doi.org\/10.48550\/ARXIV.1805.09501 (2018).","DOI":"10.48550\/ARXIV.1805.09501"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56031-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56031-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56031-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T23:48:49Z","timestamp":1786664929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-56031-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["56031"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-56031-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"assertion":[{"value":"12 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25415"}}