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 primary goal of this paper was to investigate the strength of the influence of different types of risk on the travelers’ intention to visit destinations in future, that are, prejudiced due to COVID-19, marked as “stigmatized”, “isolated”, or “risky destinations”. Field interview research was conducted at the “Belgrade Nikola Tesla Airport” (Serbia). The results obtained by multiple regression analysis showed that all types of risks influenced the intention of travelers, with financial risk showing a more significant impact. Canonical discriminant analysis indicated that men were most afraid of human induced risk, service quality risk, natural disaster and COVID-19 risk, and they chose safer destinations. Among the women, the biggest fear was financial risk, socio-psychological risk, and food safety risk. Older respondents and those under the influence of external factors decided on safer destinations, while financial status did not play a significant role in predicting the choice of destination. The selection of the destination according to the degree of security was determined by the ordinal regression methodology. The entire research presents a certain novelty, because so far in the numerous studies on the topic of the negative consequences of COVID-19 on tourism, there has been no discussion of stigmatized or risky destinations that received that epithet, and were therefore negatively and unfairly marked in the minds of tourists for future visits.

Cultural assets in the area of the Danube Limes in Serbia are an integral part of the world heritage “Roman Empire Borders”. The research presented in this paper includes the tourist and cartographic visualization of 19 Roman sites in the Danube Limes region of Golubac–Radujevac, to determine the real possibilities of tourism development in this area. The historical and cultural heritage of this area is among the most attractive tourist destinations in Serbia, Djerdap National Park and Djerdap Geopark. Despite its diverse cultural and historical values and the specific and unique natural environment, this area is not sufficiently used for tourism. The research included the evaluation of localities, which may serve as the basis to establish which activities should be undertaken in order to plan, use, preserve, and protect such important cultural assets, under the principles of sustainable tourism development. Information based on spatially referenced data in the research process requires cartographic support, in order to understand the geospatial relations of the site significance. Cartographic visualization enabled efficiently systematized data organization, spatial identification, presentation, and the use of complex information from the mapped area in the data analysis in this paper.

This paper describes the frequency analysis of absolute maximum air temperatures, using annual maximum series (AMS) in the period 1961-2010 from 40 climatological stations in Serbia with maximum likelihood estimation of distribution parameters. For the goodness of fit testing of General Extreme Value (GEV), Normal, Log-Normal, Pearson 3 (three parameters), and Log-Pearson 3 distribution, three different tests were used (Kolmogorov-Smirnov, Anderson-Darling, chi-square). Based on the results of these tests (best average rank of certain distribution), the appropriate distribution is selected. GEV distribution proved to be the most appropriate one in most cases. The probability of exceedance of absolute maximum air temperatures on 1%, 0.5%, 0.2%, and 0.1% levels are calculated. A spatial analysis of the observed and modeled values of absolute maximum air temperatures in Serbia is given. The absolute maximum air temperature of 44.9?C was recorded at Smederevska Palanka station, and the lowest value of maximum air temperature 35.8?C was recorded at Zlatibor station, one of the stations with the highest altitude. The modeled absolute maximum air temperatures are the highest at Zajecar station with 44.5?C, 45.6?C, 47.0?C, and 48.0?C and the lowest values are calculated for Sjenica station with 35.5?C, 35.8?C, 36.1?C, and 36.2?C for the return periods of 100, 200, 500, and 1000 years, respectively. Our findings indicate the possible occurrence of much higher absolute maximum air temperatures in the future than the ones recorded on almost all of the analyzed stations.

In a previous study, the Normalized Difference Gamma-Ray Index (NDGRI) was introduced as a spectral approach to highlight surface conditions associated with elevated gamma radiation. When validated against car-borne and airborne spectrometry surveys, NDGRI demonstrated potential for delineating radiation anomalies in semi-arid terrains. Detecting such anomalies from satellite data is of practical importance, as it offers a cost-effective way to narrow down prospective zones before deploying expensive car-borne or airborne surveys. Building on this foundation, this study assesses whether deep learning can extend this approach beyond index-based methods by classifying elevated radiation from Sentinel-2 spectral data. Multilayer perceptron (MLP) networks were implemented for per-pixel spectral classification, using fully connected dense layers with dropout regularization. Hyperparameters, including number of layers, neurons per layer, dropout rates, optimizers, and learning rates, were tuned via Keras Tuner and AutoKeras in Python to balance model complexity and generalization. Training and validation samples were extracted from car-borne and air-borne gamma-ray spectrometry heatmaps, providing pixel-level labels for supervised learning. Three input configurations were tested: NDGRI provided as a single-band raster, the full set of 11 Sentinel-2 bands, and selected band subsets that showed diagnostic potential in our previous NDGRI analysis. The results showed that the NDGRI raster performed strongly as a compact predictor of elevated radiation, whereas multi-band inputs provided better overall performance, with certain subsets consistently outperforming NDGRI alone. These findings indicate that although NDGRI efficiently captures key spectral contrasts, the inclusion of targeted spectral combinations enables the network to exploit complementary features and improve classification robustness. The findings suggest that deep learning can serve as a powerful extension of NDGRI-based workflows, combining the interpretability of targeted indices with the flexibility of data-driven classification. This approach could offer a scalable and computationally efficient means of mapping elevated gamma-radiation anomalies from multispectral satellite imagery, with implications for cost-effective uranium exploration in semi-arid terrains.

Long-term wildfire susceptibility mapping represents a significant component of disaster prevention and the protection of human communities, public health, and local ecosystems. In this study, a wildfire inventory was developed through multi-sensor fusion of satellite data (MODIS and VIIRS), comprising 153,305 fire events across China for the period 2001–2024. In addition to historical incidents, 14 predictive variables were processed, representing geomorphological, climatological, hydrological, vegetative, and anthropogenic conditions. This study evaluates long-term spatial wildfire susceptibility based on long-term mean environmental and climatic conditions. Methodologically, the research applies six models from machine learning (ML), deep learning (DL), and transformer-based approaches: Random Forest (RF), Extreme Gradient Boosting (XGBoost), Deep Neural Network (DNN), Fourier Multi-Layer Perceptron (F-MLP), Kolmogorov–Arnold Network (KAN), and Feature Tokenizer (FT) Transformer. The results were integrated into an ensemble susceptibility map with a spatial resolution of 500 m using Geographic Information Systems (GIS), indicating that 7.4% of China’s territory is classified as having a very high wildfire susceptibility. In addition to the national-scale assessment, a local differentiation was conducted across 34 province-level divisions, revealing that Fujian Province (86.8%) and the Guangxi Zhuang Autonomous Region (82.9%) had the largest shares of areas classified as high and very high wildfire susceptibility. Performance evaluation under spatial block-based validation demonstrated that the Random Forest model achieved the highest predictive power, with an area under the curve (AUC) of 87.8%, followed by XGBoost (87.3%) and Fourier MLP (86.6%). Based on the combined SHAP (Shapley additive explanations) analysis of all applied models, soil moisture, elevation, and terrain slope were identified as the most influential factors affecting wildfire occurrence in China. Overall, the findings contribute to more effective wildfire prevention and risk management strategies at both the local and national levels.