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.

The application of remote sensing methods provides useful information that can be used for numerous research. Thus, spatial changes in soil, vegetation, hydrography and such can be analyzed. By analyzing the data obtained by remote sensing methods, high-quality and important data can be obtained for monitoring changes in soil movement caused by landslides. This method provides the possibility of determining the state of the observed space over a longer period of time. Historical aerial imagery has a high level of spatial detail analysis. Comparative analysis of the aerial imagery from the past, recent ones and other surveys can certainly provide information on the trend of ground movement, as well as lead to conclusions for taking specific measures. The present paper gives an example of the analysis of the particular area of the “Umka” landslide based on historical surveys. The “Umka” landslide is located along the right bank of the Sava River near the city of Belgrade, which, with its long-term activity, jeopardizes residential buildings, infrastructure facilities and the population that still lives on it.

Useful and important information for the spatial, ecological, and many other changes in the living environment may be obtained using the analysis of historical aerial photography, with comparison to contemporary imagery. This method provides the ability to determine the state of elements of the space over a long period, encompassing the time when it was not possible to acquire the data from satellite imagery or some other contemporary sources. Aerial images are suitable for mapping spatial phenomena with relatively limited spatial distribution because they possess a high level of details and low spatial coverage. With a comparative analysis of aerial imagery from the past, contemporary aerial imagery, and other sources of aerial imagery, we can obtain information about the nature and trends of the observed phenomena as well as directions of future actions, considering changes detected in the environment, whether they are preventive or corrective in nature. This paper gives the methodological framework for the appliance of the existing knowledge from various fields, intending to use historical aerial photography for monitoring of environmental changes of the Bovan Lake in Eastern Serbia.