Monitoring tree mortality in Ukrainian Pinus sylvestris L. forests using remote sensing data from earth observing satellites

• Published in: Annals of forest research Vol. 65; no. 2; pp. 91 - 101
• Main Authors: Skydan, Oleh V., Fedoniuk, Tetiana P., Mozharovskii, Оleksandr S., Zhukov, Оleksandr V., Zymaroieva, Anastasiia A., Pazych, Viktor М., Hurelia, Vitaliy V., Melnychuk, Taras V.
• Format: Journal Article
• Language: English
• Published: Voluntari Forest Research and Management Institute (ICAS) - editor of Annals of Forest Research, owner of Silvica Publishing House 28.02.2023
• Subjects: Algorithms; Classification; Deforestation; Fire damage; Fires; Forest resources; Forestry; Machine learning; Maximum likelihood method; Monitoring; Optimization; Pests; Pine trees; Principal components analysis; Remote observing; Remote sensing; Satellite observation; Satellites; Spatial discrimination; Spatial resolution; Workflow
• ISSN: 1844-8135; 2065-2445
• DOI: 10.15287/afr.2022.2328

This article considers the application of remote sensing data to solve the problems of forestry in the Polissia zone (Ukraine). The satellite remote sensing was shown to be applicable to monitoring the damage caused by diseases and pests to forest resources and to assessing the effects of fires. During the research, a detailed analysis and optimization of the information content of Sentinel-2 long-term data sets was performed to detect changes in the forest cover of Polissia, affected by pests and damaged by fires. The following classification algorithms were used for automated decryption: the maximum likelihood method; cluster classification without training; Principal Component Analysis (PCA); Random Forest classification. The results of this study indicate the high potential of Sentinel-2 data for application in applied problems of forestry and vegetation analysis, despite the decametric spatial resolution. Our proposed workflow has achieved an overall classification accuracy of 90 % for the Polissia region, indicating its reliability and potential for scaling to a higher level, and the proposed forecast model is stationary and does not depend on time parameters. To improve the classification results, testing of different combinations of bands emphasized the importance of Band 8 in combination with red edge bands, as well as other bands with a resolution of 10 m for summer scenes. The red margin shows clearly visible differences in the spectral profiles, but bands with a higher resolution of 10 m were crucial for good results.