The Danube River plays significant role not only for preserving natural ecosystems. The aim of this paper is to examine the Middle Danube water quality in the part flowing through Serbia in section Bezdan -Banatska Palanka. Water quality data were examined for seven control points for period 2004-2018, for seven parameters: suspended solids (SS), dissolved oxygen (DO), electrical conductivity (EC), nitrates (NO3 –-N), total phosphorus (Ptot), biochemical oxygen demand (BOD5) and chemical oxygen demand (COD). Data analyses included the application of ANOVA, linear regression analysis and Mann-Kendall trend test. The Mann-Kendall tests in most (32/49) cases, i.e. in 65 %, confirmed the non-existence of a significant trend. Significant downward trends were confirmed in 17 cases. Water quality improvement was confirmed at following control points: Bezdan for NO3 –-N, Ptot and BOD5; Bogojevo for NO3 –-N, Ptot, COD and BOD5; Novi Sad for Ptot, BOD5 and COD; Slankamen for BOD5 and COD; Smederevo for NO3 –-N and COD; Banatska Palanka for NO3 –-N. Slight deterioration of water quality was confirmed only in two cases, at the Zemun and Smederevo where DO was decreasing. Water quality for the examined period was stable and can be characterised as excellent and/or very good (class I or class II). Results emphasise fact that water quality trends monitoring reveals river sectors where the process of water quality degradation is ongoing. Timely detected critical river sectors can draw the attention of decision-makers, who can improve the existing legislation that would lead to water quality improvement.

Large-scale infrastructure, such as China–Europe Railway Express (CER-Express), which connects countries and regions across Asia and Europe, has a potentially profound effect on land use, as evidenced by changes in land cover along the railway. To ensure sustainable development of such infrastructure and appropriate land administration, effective ways to monitor and assess its impact need to be developed. Remote sensing based on publicly available satellite imagery represents an obvious choice. In the study presented here, we employ a state-of-the-art deep-learning-based approach to automatically detect different types of land cover based on multispectral Sentinel-2 imagery. We then use these data to conduct and present a study of the changes in land use in two geopolitically diverse regions of interest (in Serbia and China and with and without CER-Express infrastructure) for the period of the last three years. Our results show that the standard image-patch-based land cover classification approaches suffer a significant drop in performance in our target scenario in which each pixel needs to be assigned a cove class, but still, validate the applicability of the proposed approach as a remote sensing tool to support the sustainable development of large infrastructure. We discuss the technical limitations of the proposed approach in detail and potential ways in which it can be improved.