Ivana Petkovski

Ecosystem services (ES) represent the benefits that natural and semi-natural ecosystems provide to human societies, yet their spatial distribution remains insufficiently integrated into urban and spatial planning practice in Serbia. This study presents a GIS-based assessment of ES capacity for the administrative territory of the City of Niš, combining CORINE Land Cover (CLC 2018) vector data with the Burkhard matrix scoring framework to quantify and spatially map provisioning, regulating and maintenance, and cultural ecosystem services across 22 land cover classes covering 59,622 ha. The analysis reveals a pronounced center-periphery gradient, with the urbanized core forming a persistent cold spot of Very Low to Low ES capacity, while forested uplands and heterogeneous agricultural landscapes in the periphery constitute extensive hot spot zones. Total ES capacity is High to Very High across 68.46% of the territory, with only 2.29% classified as Very Low. A key contribution of this study is the full automation of the analytical workflow through a QGIS Python script, making the approach directly transferable to any Serbian municipality without reliance on commercial software and aligned with the EU Nature Restoration Law (2024). Principal limitations include the 25-ha minimum mapping unit, which underestimates ES provision by urban green infrastructure, and the absence of a regionally validated Burkhard matrix for Balkan ecosystem types. Future research should address higher-resolution data integration, field-based score validation, and demand-side ES analysis.

The growing application of technology in industrial activities poses global ecological challenges in the form of resource depletion and raises awareness about the material reuse practice. Therefore the research focuses on prioritizing 25 EU nations according to their integration of digital technology (DT) in industry and the development of the circular economy (CE) as two important strategies towards sustainable development (SD). The author compared the ranking results from the CRITIC-ARAS multi-criteria model to assess the consistency between DT application in the industrial sector and CE practice in promoting SD. The sensitivity analysis of the proposed methodological scope was validated by MEREC and EDAS. Several hierarchical clusters of countries were generated according to SD scores. The research findings indicate a positive correlation between the application of DT and the current practice of CE. The top performers in achieving sustainable industrial development are the Netherlands, Germany, Belgium, Sweden and Italy. Romania, Bulgaria, Hungary and Greece achieve the weakest results. The paper proposes guidelines for enhancing SD which are important for future decisionmaking.

In the digital world, inequalities in digital participation often arise as a consequence of the uneven distribution of digital resources. Therefore, the objective of this study is to develop a digital divide index (DDI) that facilitates the temporal and spatial examination of disparities in the availability and quality of internet access, internet use and outcomes. Empirical data for 27 European countries were collected from online available datasets for 2014 and 2022. Exploratory factor analysis (EFA) was used to identify factors in DDI, while the weight values were calculated using the Shannon entropy method. The average difference in DDI scores indicates a spread of the digital divide facilitated by Finland, Latvia, Estonia, Germany, Poland and Slovakia. States in Northern and Central Europe like Norway, Austria and the Czech Republic are at the forefront of achieving digital equality. Spatial analysis reveals that Benelux countries along with Scandinavian countries show the highest levels of DDI, while Southern Europe lags behind. Sensitivity testing results show a stable index structure with variations in the importance of factors not significantly affecting the ranking results.

This paper proposes a data-driven approach to predict session-level EV energy demand using contextual station data and user behavior from historical logs. A large realistic dataset and a time-aware, user-level anti-leakage split ensured robust evaluation. The XGBoost model outperformed other regressors, offering accurate forecasts without vehicle telemetry. This scalable method enables operators to predict energy demand reliably, supporting smarter EV charging network management and allowing future integration of detailed user or technical data.

Provision of equitable access to available urban green spaces is one of the key elements for promoting environmental justice as well as well-being among the population in urban areas. This research introduces a spatial model for park-network extension in Niš, based on an analysis of accessibility focused on network-based methodologies and GIS-based spatial decision support. The paper considers three scenarios of service area estimation for: 1) existing parks, 2) parks defined by General Urban Plan 2010-2025 (GUP), and 3) identified free parcels that could become grounds for developing new parks. Accessibility analysis is conducted for two cases: 1) considering built-up areas, and 2) population distribution. An 800-meter walking distance is accepted as a threshold boundary, the standard threshold measure for park accessibility considering maximization of environmental and socio-cultural ecosystem services. The findings indicate that existing and GUP-planned parks offer considerable potential for the improvement of urban life since almost 60% of the built-up area in the study area contains a park in proximity of 800 m, however, even though physical coverage reveals considerable beneficial change, the accessibility analysis about population points to social inequality in the planned spatial distribution of parks, where a significant share of the population remains without a park >1.5ha within 10 minutes' proximity. The outcome is a replicable model of analysis for park accessibility and expansion, which offers a systematic framework to urbanists for strategic augmentation of their green infrastructure systems. 

This study examines the relationship between digitalization and energy performance in European countries by analyzing the Digital Economy and Society Index (DESI) with Sustainable Development Goal 7 (SDG7) indicators. Applying bivariate mapping and correlation analysis, spatial patterns from 2017 to 2022 are assessed. The findings reveal a positive correlation between digital advancement and the integration of renewable energy while simultaneously highlighting issues with energy poverty and digital inclusion. Most countries showed improvements in digitalization and energy efficiency between 2017 and 2022; yet progress remained uneven across regions. Regional disparities persist. Thus, Nordic nations illustrate the success of holistic policies while Southern and Eastern European countries face enduring challenges. The findings highlight the need for cohesive digital and energy policies, expansion of digital infrastructure and targeted support to marginalized areas.

The regular use of digital devices and Internet applications in modern society is significantly influenced by the user's educational attainment. In educational institutions, particularly at the primary and secondary levels, digital technologies (DT) are recognized as essential to the teaching process. Current educational programs involve active use of DT in class and thus improve digital skills necessary for active engagement in the digital world. A hybrid machine learning model was built to analyze the impact of varying educational degrees on Internet usage and innovation investments across the European Union (EU) population. Principal component analysis (PCA) was employed for detecting the primary indicators of education and innovation, resulting in the reduction of the initial variables to two factors, one including four indicators and the other containing two indicators. Linear regression (LR) was applied to the PCA factor loadings derived from the primary factor, which exhibited a statistically significant relationship with the percentage of Internet usage (r = 0.767). The results demonstrate that formal education, supported by investments in innovations within the education system, is an essential precondition for the continued development of the digital society.

Predictions across multiple disciplines rely on the efficacy of fundamental artificial neural networks, such as multilayer perceptron (MLP). Optimization is a key step in improving predictive performance of these models. In this study, a global nonlinear neural model was developed to predict the impact of using the digital technology in society, the economy and public administration on economic development. By conducting 17 experiments on the basic MLP neural network, authors investigated the effects of modifying the network architecture, learning rate and type of activation function. Standard measures of model errors and coefficient of determination were employed as criteria to prioritize configurations using the PROMETHEE II multi-criteria approach. The results reveal that models featuring two hidden layers, reduced learning speed and adequate activation functions achieve optimal performance with MSE16=0.012, RMSE16=0.110, MAPE16=12.186 and R²16=0.719. Conversely, too complex models complicate the learning process and lead to imprecise predictions as in the case of MSE5=0.019, RMSE5=0.138, MAPE5=17.225 and R²5=0.559. The results indicate the importance of adjusting the neural network hyperparameters to the nature of the research problem. Additionally, the study reveals the important role of MCDM in choosing the most adequate configuration when considering diverse criteria with different targets.

Serbia, like many other countries, works to manage and protect water resources, promote sustainable practices, and improve infrastructure. However, there is no systematic advocacy for the implementation of sustainable stormwater management practices (SWM) in urban areas in Serbia. As highlighted by the Development Plan of the City of Niš For the Period 2021-2027, in the last decade the number of flash floods has increased, causing infrastructure and property damages. As a result, reducing the risk of flooding by external and internal waters is prioritized under the territorial development and environmental protection axis. As a contribution to the development of SWM practice, in this research, the prediction of the potential of runoff from roofs in the city of Niš, was performed using L-Moment and GIS. The research included 262 buildings in the city center and results indicate an increasing trend in average runoff from roofs across all sectors.