The study includes an assessment of groundwater quality from one shallow and two deeper aquifers in the Danube left bank, under the conditions of coexistence of the open coal mine, arable lands with increasing irrigation needs and potential regional water supply system for the Banat region. The spatial distribution maps of the targeted parameters were used as a starting point in the identification of nine zones in the study area. The Piper plot and the specific ionic plots pointed out that dissolution of carbonate and silicate minerals, as well as cation exchange, plays a significant role in the groundwater chemistry. Although the geological and hydrogeological complexity of the study area highlighted the considerable vertical and horizontal zonations when it comes to groundwater quality, waters have a desirable quality for drinking while for irrigation the eastern zone of the study area is better. Vertical mixing of shallow and deeper groundwaters confirmed the post-sedimentary faulting and erosion of coal seams in the central part of the study area. Generally, the results of determining the origin and quality of groundwaters throughout the study area could greatly help in making decisions regarding the regional water supply and expansion of irrigated lands in the future.

Dam monitoring data are nonlinear and nonstationary time series. Most existing data-driven dam displacement models are developed independently for each measuring point, disregarding the fact that a dam is a complex structure composed of various interconnected elements that form a unified whole. Regardless of the dam type, all points on the dam are exposed to the same external environmental influences. To account for the correlation between displacement time series at different points, this paper proposes a novel fine-tuned deep-learning nonlinear autoregressive (NAR) model based on a Long Short-Term Memory (LSTM) network for predicting dam tangential displacement, and a new method for generating source data to train the base model. The models for three measuring points were developed and tested on experimental data collected over a period of slightly more than twelve years. Compared with the model without fine-tuning, the proposed approach achieves an average mean square error (MSE) reduction of 80.68% on the training set and 65.79% on the test set, as well as an average mean absolute error (MAE) reduction of 51.05% and 52.62%, respectively. Furthermore, the proposed model outperforms Random Forest (RF), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP) models for dam displacement prediction.

The Iron Gate Hydropower and Navigation System (composed of HPP “Iron Gate 1” and HPP “Iron Gate 2”) not only greatly influences water levels along a more than 300 km stretch of the Danube River but also affects groundwater regimes in wide coastal areas and the functioning and changes of ecosystems in the impounded zone. At the same time, it acts as a retention area for sediment and various types of pollutants originating from upstream parts of the basin, transported by the Danube and its tributaries. The construction of the Iron Gate 1 and Iron Gate 2 hydropower and navigation systems permanently altered the natural conditions within the reservoirs and in the surrounding coastal areas, leading to certain negative consequences. These include increased groundwater levels in the coastal zone, threatening settlements, industrial, municipal, and transport infrastructure, and causing waterlogging of agricultural land; raised flood levels due to sediment deposition within the reservoir; threats to the stability of flood defence dikes and high banks; and changes in the river biocenosis, among others. From the outset, the highly complex task of managing these ransboundary systems and their impact on the environment has required significant efforts to regulate interstate and international obligations, as well as to reconcile often conflicting iterests. This paper presents the principles of a holistic management approach, which, in addition to the primary purpose of energy production, emphasizes handling all other relevant aspects: groundwater regimes in the riparian land, sediment management—both in terms of quantity and quality—and more. The management approach is defined by considering all existing technical systems relevant to these issues. In accordance with the defined principles, the paper also presents the structure of a software/hardware management support system based on existing technical systems that encompass a large number of interconnected hardware and software components, measuring instruments, and users.

Unesko (UNESCO) je specijalizovana agencija UN za obrazovanje, nauku i kulturu, osnovana 1945. godine, sa ciljem da se ostvari intelektualna i moralna solidarnost čovečanstva, kao sredstvo za izgradnju trajnog mira. U okviru Uneska, 1975. godine, nakon Međunarodne hidrološke dekade (IHD) (1964-1974), osnovan je Međuvladin hidrološki program (Intergovernmental Hydrological program – IHP). IHP je jedini međuvladin program u sistemu Ujedinjenih nacija i posvećen je unapređenju istraživanja i upravljanja vodnim resursima, kao i povezanim obrazovnim inicijativama i razvoju kapaciteta, koji su ključni za podsticanje održivog i integralnog upravljanja vodama. Rad IHP se odvija u vremenski ograničenim fazama, a trenutno je aktuelna deveta faza (IHP-IX) koja se odvija u periodu 2022-2029. godine koja je fokusirana na pomoć državama članicama u ostvarivanju ciljeva održivog razvoja, kroz identifikaciju ključnih prioritetnih oblasti u transdisciplinarnom istraživanju voda. U radu je prikazan istorijat IHP i aktivnosti pod njegovim okriljem u Republici Srbiji.