EVALUATION OF THE PERFORMANCE OF CLASSIFICATION ALGORITHMS IN THE QGIS SYSTEM
DOI:
https://doi.org/10.68302/std2026.vol3.196Keywords:
reeds, classification algorithms, modeling, satellite data, QGISAbstract
The use of lake reeds as a source of green energy is becoming increasingly significant. Accurate estimation of reed-covered areas is essential, as it enables forecasting of potential biomass yields and supports carbon footprint calculations. However, in Latvia, there is currently a lack of comprehensive research on the availability and spatial distribution of reeds. The main objective of this research is to develop a method for modeling the distribution of lake reeds in order to predict their future availability. The research focuses on satellite imagery of lakes, with spatial analysis and modeling performed using QGIS. A critical stage in the methodology is classification, which allows reeds to be distinguished from surrounding land cover types and enables estimation of their extent within lake environments. For this purpose, several semi-automatic classification algorithms were applied, including Minimum Distance and Random Forest. The performance of these algorithms was evaluated experimentally, and the most suitable approach was selected based on its agreement with available historical data.
Supporting Agencies
This research was funded by grant number RTU-PA-2024/1-0077, “Towards a sustainable bioeconomy: assessing reed biomass potential and applications (ReedREvolution)”.Downloads
References
[1] “Plant family,” [Online] Available: https://www.britannica.com/plant/Poaceae [Accessed: Feb. 20, 2026].
[2] E.Čubars and G. Noviks, Influence of Different Factors on Productivity of Reed Growths, Environment. Technology. Resources, Proceedings of the 9th International Scientific and Practical Conference. Volume 1, Rezekne, Latvia, 2013. https://doi.org/10.17770/etr2013vol1.801
[3] E.Tiškus, D.Vaičiūtė, M.Bučas, and J. Gintauskas," Evaluation of common reed (Phragmites australis) bed changes in the context of management using earth observation and automatic threshold," European Journal of Remote Sensing, 2022. https://doi.org/10.1080/22797254.2022.2161070
[4] L. Sciuto, F. Licciardello, A.C. Barbera, and G. Cirelli, "A GIS‐based multicriteria decision analysis to reduce riparian vegetation hydrogeological risk and to quantify harvested biomass (Giant reed) for energetic retrieval," Ecological Indicators, Volume 144, November 2022, https://doi.org/10.1016/j.ecolind.2022.109548
[5] S. Baier, N.C. Meneses, J. Geist, and T.Schneider, "Assessment of Aquatic Reed Stands from Airborne Photogrammetric 3K Data," Remote Sens. 14(2), 337, 2022, https://doi.org/10.3390/rs14020337
[6] H. Runkui and L.Yuqin, "Application of remote sensing technique to the investigation on reed resources of Bosten Lake," Chinese Geographical Science, Volume 2, pages 266–276, 1992, https://doi.org/10.1007/BF02664604
[7] S. Baier, N.C. Meneses, J. Geist and T. Schneider, "Assessment of Aquatic Reed Stands from Airborne Photogrammetric 3K Data. Remote Sens," 14(2), 337, 2022. https://doi.org/10.3390/rs14020337
[8] A. Baibagyssov, A. Magiera, N. Thevs and R. Waldhardt, "Resource Characteristics of Common Reed (Phragmites australis) in the Syr Darya Delta, Kazakhstan, by Means of Remote Sensing and Random Forest," Plants, 2025. https://www.mdpi.com/2223-7747/14/6/933
[9] P. Grabusts, J. Musatovs and Ē. Teirumnieka, Modeling the Distribution of Lake Reeds Using GIS, In Proceedings of the 16th International Scientific and Practical Conference Environment. Technology. Resources, Rezekne Latvia, June 2025. https://doi.org/10.17770/etr2025vol2.8619
[10] “Latvian lakes database.” [Online] Available: https://www.ezeri.lv/database/2196/ [Accessed: Feb. 20, 2026].
[11] “Copernicus project,” [Online] Available: https://www.copernicus.eu/en [Accessed: Feb. 20, 2026].
[12] “SentiWiki Home Page,” [Online] Available: https://sentiwiki.copernicus.eu/web/sentiwiki [Accessed: Feb. 20, 2026].
[13] “QGIS project,” [Online] Available: https://qgis.org/project/overview/ [Accessed: Feb. 20, 2026].
[14] R.O. Duda, P.E. Hart and D.G. Stork, Pattern Classification, 2nd edition, 2001.
[15] S.Haykin, Neural Networks and Learning Machines, 3rd edition, Pearson, 2009.
[16] L. Breiman, Random Forests. Machine Learning, 45(1), 5–32, 2001. https://doi.org/10.1023/A:1010933404324
[17] C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Peter Grabusts, Jurijs Musatovs
This work is licensed under a Creative Commons Attribution 4.0 International License.
