Machine Learning Training Data: Over 500,000 Images of Butterflies and Moth with Species Labels

Machine Learning


  • McClure, EC et al. Artificial intelligence fills citizen science and charges ecological surveillance. Patterns (New York, New York) 1100109, https://doi.org/10.1016/j.patter.2020.100109 (2020).

    ArticlePubMed Google Scholar

  • Lotfian, M., Ingensand, J. & Brovelli, MA Citizen Science and Machine Learning Partnership: Benefits, Risks and Future Challenges on Engagement, Data Collection, Data Quality. Sustainability 138087, https://doi.org/10.3390/SU13148087 (2021).

    ArticleGoogle Scholar

  • Chandler, M. et al. Citizen science contributions to international biodiversity surveillance. Biological Conservation 213280–294, https://doi.org/10.1016/j.biocon.2016.09.004 (2017).

    ArticleGoogle Scholar

  • Besson, M. et al. Towards fully automated surveillance of ecological communities. Ecology Letter twenty five2753–2775, https://doi.org/10.1111/ele.14123 (2022).

    ArticlePubMed PubMed Central Google Scholar

  • Tuia, D. et al. Machine learning perspective for wildlife conservation. Natural Communication 13792, https://doi.org/10.1038/S41467-022-27980-y (2022).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Willi, M. et al. Deep learning and citizen science are used to identify animal species in camera trap images. Method evol 1080–91, https://doi.org/10.1111/2041-210x.13099 (2019).

    ArticleGoogle Scholar

  • Wang, Z., Cui, J. & Zhu, Y. Review of plant leaf recognition. Artif Intel Rev 564217–4253, https://doi.org/10.1007/S10462-022-10278-2 (2023).

    ArticleGoogle Scholar

  • Maider, P. et al. Flora Incognita App – Interactive plant species identification. Method evol 121335–1342, https://doi.org/10.1111/2041-210x.13611 (2021).

    ArticleGoogle Scholar

  • Hansen, OLP et al. Species-level image classification using convolutional neural networks allows for the identification of insects from habitual images. Ecology and evolution 10737–747, https://doi.org/10.1002/ece3.5921 (2020).

    ArticlePubMed Google Scholar

  • Theivaprakasham, H. Identification of Indian butterflies using deep convolutional neural networks. Journal of Asia-Pacific Entomology twenty four329–340, https://doi.org/10.1016/j.aspen.2020.11.015 (2021).

    ArticleGoogle Scholar

  • Gomez Villa, A., Salazar, A. & Vargas, F. Ecological Informatics 4124–32, https://doi.org/10.1016/j.ecoinf.2017.07.004 (2017).

    ArticleGoogle Scholar

  • Norzade, MS et al. Deep learning automatically identifies, counts and explains wildlife in camera trap images. Proceedings of the United States Academy of Sciences 115E5716 – E5725, https://doi.org/10.1073/pnas.1719367115 (2018).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Unger, S., Rollins, M., Tietz, A. & Dumais, H. Abuse as an attractive tool for identifying living things in outdoor activities. Journal of Biological Education 55537–547, https://doi.org/10.1080/00219266.2020.1739114 (2021).

    ArticleGoogle Scholar

  • Balta, Z. Deep learning in Earth Conservation Biology. Biologia futura 74359–367, https://doi.org/10.1007/S42977-023-00200-4 (2023).

    ArticlePubMed Google Scholar

  • Brereton, T., Roy, DB, Middlebrook, I., Botham, M. & Warren, M. Development of the UK butterfly indicator and evaluation in 2010. Journal of Insect Conservation 15139–151, https://doi.org/10.1007/S10841-010-9333-Z (2011).

    ArticleGoogle Scholar

  • Van Swaay, C., Warren, M. & Loïs, G. Biotope use and European butterfly trends. J Insect Conserv 10189–209, https://doi.org/10.1007/S10841-006-6293-4 (2006).

    ArticleGoogle Scholar

  • Thomas, JA monitors changes in insect abundance and distribution using butterflies and other groups of indicators. Philosophical deals of the Royal Society of London. Series B, Biology 360339–357, https://doi.org/10.1098/rstb.2004.1585 (2005).

    ArticleCAS PubMed PubMed Central Google Scholar

  • Andal, M. et al. Bird efficiency as a bioindicator for other taxa in mountain farmland. Ecological indicators 158111569, https://doi.org/10.1016/j.ecolind.2024.111569 (2024).

    ArticleGoogle Scholar

  • Gerlach, J., Samways, M. & Pryke, J. Terrestrial invertebrates as Bioindicators: An overview of available taxa. J Insect Conserv 17831–850, https://doi.org/10.1007/S10841-013-9565-9 (2013).

    ArticleGoogle Scholar

  • Van Swai, C. et al. EU Butterfly Indicator for Grassland Species: 1990-2017: Technical Report. Butterfly Conservation Europe & Eable/EBMS (www.butterfly-monitoring.net) (2019).

  • Roy, DB, Rothery, P., Brereton, T., Kühn, E. &Settele. j. Design of a systematic research scheme for monitoring British butterflies (2005).

  • Talon, D. & Lease, L. Surveillance for butterfly maintenance. With the conservation of North American butterflies. Edited by J.C. Daniels, pp. 35–57 (Springer, Dordrecht, 2015) Efforts to support the relief of charismatic microfaunas edited.

  • Schlegel, J. & Rupf, R. Attitudes towards potential animal flagship species in conservation: A survey of students from various educational institutions. Journal for Nature Conservation 18278–290, https://doi.org/10.1016/j.jnc.2009.12.002 (2010).

    ArticleGoogle Scholar

  • Chang, Q., Qu, H., Wu, P. &Yi, J. Fine-grained butterflies and Moth classification using deep convolutional neural networks (2017).

  • Nie, L., Wang, K., Fan, X. & Gao, Y. Recognition of fine, dense butterflies using deep residual networks: new baselines and benchmarks. International Conference on Digital Image Computing 2017: Technology and Applications (DICTA), pp. 1–7 (IEEE 2017).

  • Mattins, RF, Sarobin, MVR, Aziz, AA & Srivarshan, S. Object detection and classification of butterflies using efficient CNN and pre-trained deep convolutional neural networks. Multi-compatible tool Appl; https://doi.org/10.1007/S11042-023-17563-4 (2023).

  • Isaac, NJB et al. The challenges are distance sampling and monitoring butterfly populations. Method evol 2585–594, https://doi.org/10.1111/j.2041-210x.2011.00109.x (2011).

    ArticleGoogle Scholar

  • Koch, W., Hogeweg, L., Nilsen, Eb, O'hara, RB & Finstad, Ag Civic Science photography. Royal Society Open Science 10221063, https://doi.org/10.1098/rsos.221063 (2023).

    ArticleAdsPubMed PubMed Central Google Scholar

  • Arazy, O. & Malkinson, D. Observer-based bias framework in biodiversity monitoring in citizen science: a semi-unstructured biodiversity monitoring protocol. front. Ecole. Evol. 9https://doi.org/10.3389/fevo.2021.693602 (2021).

  • Tu, Z. et al. Maxvit: Multi-axis Vision Transformer (2022).

  • Den, J. et al. Imagenet: Large-scale hierarchical image database. in 2009 IEEE Computer Vision and Pattern Recognition Conference,pp. 248–255 (IEEE 2009).

  • Barkmann, F. Image-based butterfly species identification using convolutional neural networks. Available at https://ulb-dok.uibk.ac.at/urn/urn:nbn:at:at-ubi:1-172379 (2025).

  • Friederike Barkmann, Andreas Lindner, Ronald Würflinger, Helmut Höttinger & Johannes Rüdisser. Machine learning training data: Over 500,000 images of butterflies and moths with species labels. https://doi.org/10.25452/figshare.plus.29135618 (2025).

  • Höttinger, H. & Pennerstorfer, J. Rote Liste Der TagschmetterlingeÖsterreichs (Lepid: Papilionoidea & Hesperioidea). Listen to gefährdetertiere Österreichs on route. Checklisten, gefährdungsanalysen, Handlungsbedarf. Teil 1: Säugetiere, Vögel, Heuschrecken, Wasserkäfer, Netzflügler, Schnabelfliegen, Tagfalter. , K. Zulka, pp. 313–354 (bundesministerium fürand-forstwirtschaft, umwelt und 2005).

  • Huemer, P. Die SchmetterlingeÖsterreichs (Lepidaceae). Systematische und Faunistice CheckListe (Tiroler Landesmuseum Ferdinandeum, Innsbruck, 2013).

  • Wiemers, M. et al. Updated checklist of European butterflies (Lepididae, Papillionoidea). Zookeys9–45, https://doi.org/10.3897/zookeys.811.28712 (2018).

  • Karsholt, O. & Razowski, J. European calpidites: Distribution checklist (Brill, 1996).

  • Paszke, A. et al. Pytorch: A deep, imperative style, high-performance learning library. in Advances in neural information processing systemsH. Edited by Wallach, et al. , vol. 32 (Curran Associates, Inc 2019).

  • Li, S. et al. Pytorch's Distribution: Experience with Accelerated Parallel Training of Data (2020).

  • Gugar, S. et al. Acceleration: Large-scale training and reasoning made it simple, efficient and adaptable (2022).

  • Buda, M., Maki, A. & Mazurowski, Systematic study of class imbalance problems in Massachusetts, Massachusetts, Systematic study of class imbalance problems in convolutional neural networks. Neural Networks: Official Journal of the International Neural Network Society 106249–259, https://doi.org/10.1016/j.neunet.2018.07.011 (2018).

    ArticlePubMed Google Scholar

  • Barkmann, F. & Lindner, A. maxvit_butterfly_identification; https://doi.org/10.57967/hf/5986.



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *