Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Automated Detection of Sosnowsky’s Hogweed Using Sentinel-2 Imagery and Machine Learning

, ,

DOI: http://dx.doi.org/10.15439/2026F9420

Citation: Reinis Odītis, ,

Full text

Abstract. Sosnowsky's hogweed (Heracleum sosnowskyi) is an invasive plant species widespread in Latvia, posing threats to biodiversity, human health, and economic activity. Manual reinspection of the approximately 19,000 registered occurrence records is impractical at scale. This study proposes an automated machine learning framework for hogweed detection using freely available Sentinel-2 multispectral satellite imagery, with reference data sourced from the State Plant Protection Service geospatial database. Three supervised classification algorithms --- Support Vector Machine, Random Forest, and Extreme Gradient Boosting --- were evaluated across multiple dataset configurations combining spectral bands, derived indices, and multi-temporal features. Binary classification achieved a peak accuracy of 92.6\%, while multi-class classification reached 87.7\% (Cohen's kappa 0.836). The results demonstrate that Sentinel-2 imagery combined with multi-temporal features enables reliable automated monitoring of hogweed distribution at national scale.

References

  1. Heracleum sosnowskyi, Skatı̄ts: 2026. gada 13. aprı̄lis, 03/2026.
  2. V. augu aizsardzı̄bas dienests, Sosnovska latvānis, Skatı̄ts: 2026. gada 17. marts, 02/2022.
  3. V. augu aizsardzı̄bas dienests, Sosnovska latvān , a izplatı̄ba latvijā, Skatı̄ts: 2026. gada 17. marts, 07/2025.
  4. J. Müllerová, J. Brůna, T. Bartaloš, P. Dvořák, M. Vítková, and P. Pyšek, “Timing is important: unmanned aircraft vs. satellite imagery in plant invasion monitoring”, Frontiers in Plant Science Volume 8 - 2017, 10.3389/fpls.2017.00887 (2017).
  5. M. M. Zaka and A. Samat, “Advances in remote sensing and machine learning methods for invasive plants study: a comprehensive review”, Remote Sensing 16, https://dx.doi.org/10.3390/rs16203781 (2024).
  6. W. Maes and K. Steppe, “Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture”, Trends in Plant Science 24, https://dx.doi.org/10.1016/j.tplants.2018.11.007 (2018).
  7. J. Morgan, S. Gergel, and N. Coops, “Aerial photography: a rapidly evolving tool for ecological management”, Bioscience 60, 47–59 (2010).
  8. R. Massey, L. Bernier, A. Foster, S. Goetz, and U. Vepakomma, “Remote sensing tools for monitoring forests and tracking their dynamics”, in (02/2023).
  9. Z. Sun, X. Wang, Z. Wang, L. Yang, Y. Xie, and Y. Huang, “Uavs as remote sensing platforms in plant ecology: review of applications and challenges”, Journal of Plant Ecology 14, 1003–1023 (2021).
  10. D. Olson and J. Anderson, “Review on unmanned aerial vehicles, remote sensors, imagery processing, and their applications in agriculture”, Agronomy Journal 113, 971–992 (2021).
  11. D. Phiri, M. Simwanda, S. Salekin, V. R. Nyirenda, Y. Murayama, and M. Ranagalage, “Sentinel-2 data for land cover/use mapping: a review”, Remote Sensing 12, 10.3390/rs12142291 (2020).
  12. D. Roy, M. Wulder, T. Loveland, C. Woodcock, R. Allen, M. Anderson, D. Helder, J. Irons, D. Johnson, R. Kennedy, T. Scambos, C. Schaaf, J. Schott, Y. Sheng, E. Vermote, A. Belward, R. Bindschadler, W. Wohen, F. Gao, and Z. Zhu, “Landsat-8: science and product vision for terrestrial global change research”, Remote Sensing of Environment 2014, 154–172 (2014).
  13. J. Masek, M. Wulder, B. Markham, J. McCorkel, C. Crawford, J. Storey, and D. Jenstrom, “Landsat 9: empowering open science and applications through continuity”, Remote Sensing of Environment 248, 111968 (2020).
  14. European Space Agency (ESA), Sentinel-2 user handbook, Issue 1, Rev. 2. Available online: https://sentinels.copernicus.eu/documents/247904/685211/Sentinel-2 _ User _ Handbook , European Space Agency (Paris, France, 2015).
  15. O. Justice, E. Vermote, J. Townshend, R. Defries, D. Roy, D. Hall, V. Salomonson, J. Privette, G. Riggs, A. Strahler, W. Lucht, R. Myneni, Y. Knyazikhin, S. Running, R. Nemani, Z. Wan, A. Huete, W. Van Leeuwen, R. Wolfe, and M. Barnsley, “The moderate imaging spectroradiometer (modis): land remote sensing for global change research. ieee trans. geosci. remote sens”, Geoscience and Remote Sensing, IEEE Transactions on 36, 1228–1249 (1998).
  16. R. Houborg and M. McCabe, “Daily retrieval of ndvi and lai at 3 m resolution via the fusion of cubesat, landsat, and modis data”, Remote Sensing 10, https://dx.doi.org/10.3390/rs10060890 (2018).
  17. N. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, “Google earth engine: planetary-scale geospatial analysis for everyone”, Remote Sensing of Environment 202, Big Remotely Sensed Data: tools, applications and experiences, 18–27 (2017).
  18. Valsts Augu Aizsardzı̄bas Dienests, AKD Latvān , i public shapes: hogweed distribution database, ArcGIS REST Services, State Plant Protection Service of Latvia., 2025.
  19. SentiWiki, Sentinel-2 products, Copernicus Sentinel Online, 2023.
  20. World Bank, Latvia: land use statistics, World Bank Open Data, 2023.