In 2015, the 2030 Agenda for Sustainable Development was adopted by all United Nations Member States and includes a set of 17 Sustainable Development Goals. The indicator, “Ratio of land consumption rate to population growth rate” (indicator 11.3.1) was proposed for the monitoring of urban development. The present study proposes the analysis of the built-up space evolution in relation to the demographic growth in the main metropolitan areas of Romania using the 11.3.1 indicator. Land consumption rate and population growth rate (LCRPGR) is used to assess the sustainability of urban growth, which takes into account both the change in the built-up area and in the population. LCRPGR is calculated as the ratio of land consumption rate (LCR) and the population growth rate (PGR). The analysis was conducted at the metropolitan area level for the 2006–2009, 2009–2015 and 2015–2020 periods. LCR and PGR proved to be very useful indicators for the monitoring of the intensity of built-up changes in the eight metropolitan areas both in time and in space and are useful for the local and central administrations, in both the context of achieving the sustainable development targets and goals and in conducting urban design and planning.

Assessing land use/land cover changes currently represents an important avenue for achieving a better understanding of the urbanization phenomenon. Various free datasets based on satellite imagery are available, but the user should decide which one is the most suitable for their study area. The aim of the present paper is to perform an accuracy assessment of built-up areas using four datasets: Corine Land Cover Backbone (CLC Backbone), High Resolution Layers (HRL)–Imperviousness, Esri Land Cover and Dynamic World. The study case is represented by 12 major metropolitan areas (MAs) in Romania which have the most dynamic economic development and urban expansion. Confusion matrices were created, and the following metrics have been computed: overall accuracy (OA), kappa coefficient (k) and user accuracy (UA). The analysis was performed on three levels: for the entire surface of the MAs and separately for the urban and rural sides. The results at the metropolitan level show that even though CLC Backbone 2018 is the most suitable for extracting the built areas (0.85 overall accuracy), HRL and Esri Land Cover could also be used, as they share the same overall accuracy values (0.67). Significant differences exist between the urban and rural areas. CLC Backbone performed better in the rural areas (0.87) than in the urban areas (0.84). The other three datasets recorded major variations in the overall accuracy for the urban and rural areas. Esri Land Cover has the second greatest overall accuracy for the urban areas (0.81), while HRL is the second most accurate, after CLC Backbone, for assessing the rural areas (0.67). In conclusion, CLC Backbone has the best accuracy performance for all three levels of analysis. The significance of the study lies in the accuracy assessment results on the four datasets, performed at urban and rural levels. This paper aims to help researchers and decision makers choose the best dataset for assessing land use changes. Additionally, having a reliable dataset may help compute the indicators used to monitor the Sustainable Development Goals (SDGs).

Spatial planning decisions form the basis of territorial progress by enhancing the resilience and opportunities for local and regional development. Therefore, decisions made as a result of multidisciplinary studies based on GIS assessment of all involved factors can provide a real and up-to-date image of the analyzed territory. In this context, geomorphic processes are among the factors restricting development, affecting built-up areas, transport infrastructure, and economic activities. This paper assesses geomorphic processes at the level of Cluj County, Romania, which mainly consist of active landslides that directly impact the accessibility of communities and their degree of safety, while accelerated soil erosion severely affects the output of land used for agriculture. GIS technology and a semi-quantitative model for determining the landslide hazard were used to classify landslides across occurrence probability classes. This methodology was implemented in Romania through Government Decision no. 447/2003. The USLE model was used to determine the soil erosion. As a result, the territory of Cluj County, which is the study area of this paper, was entirely included in one of the classes of risk concerning active geomorphic processes. Another important aspect consisted of categorizing transport infrastructure according to risk classes. A population risk assessment was also performed, taking into account the degree of accessibility of the territorial emergency department in the event that such hazards and processes occur. These results form the basis of proposals to efficiently plan the county territory, adapting decisions to the present trends in the evolution.

The recent increase of regional inequalities in Europe, and in particular in Central and Eastern Europe (CEE) has led to the reconsideration and revival of the “growth pole” concept in academic fields like regional economics, economic geography and spatial planning. In contrast to the classical view developed by French economists, the new policy-led approach on growth poles is emphasizing a much broader perspective. Designed for the reduction of regional inequalities, the rebirth of growth poles concept in the development planning practice triggered an important debate about the relation between spatial inequalities, economic growth and development. This article provides a critical overview and assessment of growth pole policy and spatial inequalities in Romania. The main objective is the analysis of the spatial change in the metropolitan areas of the seven growth poles by taking into consideration four groups of indicators: demographic, economic, housing and land use. The empirical results show a differentiated socio-spatial dynamic of the metropolitan areas, although being designated and treated as national growth poles. Moreover, there is no evidence for the adequateness of the growth pole spatial planning tool to its main objective: the reduction of spatial inequalities. In this case a crisis (increasing spatial inequalities and peripheralization) has not generated any transformative power in spatial planning, which rises serious doubts about the innovative capacities of the spatial development policies.

Following the collapse of the communist regime, Romania underwent significant economic, territorial, and social transformations that exacerbated inequality. To help policymakers create effective economic strategies, it is necessary to pinpoint the areas with the largest disparities. Thus, using spatial statistics available in ArcGIS, the primary goal of this study is to identify spatial clusters/outliers of income per capita. The findings indicate a strong concentration of high incomes at the regional level in Bucharest-Ilfov, West, Centre, and North-West regions. Conversely, low-income groups are concentrated in every other region, and their circumstances do not appear to improve over the course of the analysis period (2007–2021). At the metropolitan level, large cities are particularly home to high-value clusters and their influence within metropolitan areas is outlined.

Urban heat islands (UHIs) represent a major environmental challenge, particularly in cities with complex topography and local air dynamics where spatial variability of the surface temperature is difficult to model. This study presents an enhanced UHI modeling framework that integrates Random Forest regression with Regression Kriging (RF–RK) in Cluj-Napoca, Romania. Using a network of 36 air temperature sensors and spatial predictors such as urban environment and location parameters, we evaluated the performance of RF–RK against traditional Multiple Linear Regression (MLR). Results show that RF–RK achieved substantially higher accuracy (R² = 0.844, RMSE = 0.241 °C) compared to MLR (R² = 0.653, RMSE = 0.359 °C). Spatial patterns revealed that a notable thermal gradient can be seen between the western and eastern parts of the city and the extension of the heat island core eastward. The combined approach effectively captured both the non-linear relationships of predictors and the spatial autocorrelation of residuals, outperforming single-method models. These findings highlight the potential of hybrid machine learning–geostatistical frameworks for urban climate research and provide insights for urban planning and heat mitigation strategies in topographically diverse cities.