No abstract

Wildfire has been one of the most dangerous environmental stressors nowadays. It is an important disturbance where ecosystem biomass is burned and where organisms are damaged or killed by fire. Therefore, the detecting and monitoring of this stressor are of great importance. During last decades, extensive forest fires have spread in Southern Europe, and they are registered in Serbia as well. During year 2007, several significant fires were registered in Stara Planina and Svrljiške Planine Mountains. The aims of this study were to detect land cover changes for the studied site from 2007-2017, to focus on monitoring the area affected by the wildfire, and to analyse the environment response to stressor. The study area is situated in East Serbia, partially covering the Mountains Stara Planina (western part) and Svrljiške planine (eastern part). The remote sensing techniques were used in the analysis and main satellite data were obtained via USGS Earth Explorer application. Six different classes were selected: Water, Forest, Pastures, Artificial area, Agriculture, and Bare soil. Results showed significant changes in two classes, Forest, and Pastures-the forest spread for more than 20% at the expense of pasture, which decreased more than 23%.

No abstract

Vegetation plays an active role in ecosystem dynamics, and monitoring its patterns and changes is vital for effective environmental resource management. This study explores the possibility of machine learning techniques and remote sensing data to improve the accuracy of forest detection. The research focuses on the southeastern part of the Republic of Serbia as a case study area, using Sentinel-2 multispectral bands. The study employs publicly accessible satellite data and incorporates different vegetation indices to improve classification accuracy. The main objective is to examine the practicability of expanding the input parameters for forest detection using a machine learning approach. The classification process is performed by employing support vector machines (SVM) algorithm and utilising the SVM module in the scikit-learn package. The results demonstrate that including vegetation indices alongside the multispectral bands significantly improves the accuracy of vegetation detection. A comprehensive assessment reveals an overall classification accuracy of up to 99.01% when the selected vegetation indices (MCARI, RENDVI, NDI45, GNDVI, NDII) are combined with the Sentinel-2 bands. This research highlights the potential of machine learning and remote sensing in forest detection and monitoring. The findings underscore the importance of incorporating vegetation indices to enhance classification accuracy using the Python programming language. The study’s outcomes provide valuable insights for environmental resource management and decision-making processes, particularly in regions with diverse forest ecosystems.

No abstract