Radovan Savić

Reference evapotranspiration (ET₀) is most commonly estimated using the FAO-56 Penman–Monteith (PM) equation. However, its application is often limited by the lack of required meteorological parameters. Due to their flexibility, ability to operate with limited input, and high accuracy in estimating ET₀, machine learning models have become increasingly relevant in scientific research, offering a practical alternative under limited data conditions. In this study, artificial neural networks (ANNs) were applied to estimate daily ET₀ using meteorological data from the Novi Sad station in Vojvodina (Serbia). The dataset consisted of eight meteorological variables relevant to evapotranspiration processes. Analysis showed that some variables had a stronger influence on ET₀ prediction than others. To evaluate their combined effect, a series of ANN models with different input combinations were developed and tested. The random forests, gradient boosting and k-nearest neighbors models were used as a benchmark, and model performance was evaluated using R², NSE, RMSE, and MAE. The highest accuracy was achieved when all variables were included, providing the model with maximum information. The best performance was obtained using a two-hidden-layer architecture with 32 and 16 neurons, resulting in R² = 0.97, NSE = 97.07%, RMSE = 0.23 mm/day, and MAE = 0.21 mm/day. The results showed that a limited number of input variables can be used to estimate ET₀ with high accuracy, achieving an R² value of 0.95 using only three input variables. Therefore, the findings of this study may contribute to more accurate and cost-effective irrigation scheduling and water balance estimation, providing practical benefits for agricultural water management and farmers in Serbia.

Reference evapotranspiration (ET0) is most commonly estimated using the FAO-56 Penman-Monteith (PM) equation. However, its application is often limited by the lack of required meteorological parameters. Due to their flexibility, ability to operate with limited input, and high accuracy in estimating ET0, machine learning models have become increasingly relevant in scientific research, offering a practical alternative under limited data conditions. In this study, artificial neural networks (ANNs) were applied to estimate daily ET0 using meteorological data from the Novi Sad station in Vojvodina (Serbia). The dataset consisted of eight meteorological variables relevant to evapotranspiration processes. Analysis showed that some variables had a stronger influence on ET0 prediction than others. To evaluate their combined effect, a series of ANN models with different input combinations was developed and tested. The FAO-56 PM method was used as a benchmark, and model performance was evaluated using R2, NSE, RMSE, and MAE. The highest accuracy was achieved when all variables were included, providing the model with maximum information. The best performance was obtained using a two-hidden-layer architecture with 32 and 16 neurons, resulting in R2 = 0.98, NSE = 97.86%, RMSE = 0.25 mm day-1, and MAE = 0.17 mm day-1.

The global promotion of decarbonisation through the circular solutions and (re)use of bio-based resources (BBR), i.e. waste streams, notably from the agricultural, forest and municipal sectors has steadily increased in recent decades. Among the transformative solutions offered by BBR, biosolids (BS), biochars (BC), and bioashes (BA) specifically attract scientific attention due to their highly complex organo-mineral matrices, which present significant potential for recovery in the agro-/forest-ecosystems. These materials enhance various soil (i) chemical (pH, macro/micro nutrient concentrations, organic matter content), (ii) physical (porosity, water–air relations, compaction) or (iii) microbial (diversity, activity) properties. Furthermore, some of transformed BBR contribute to a multitude of environmental services such as the remediation of contaminated sites and wastewater treatment, employing cost-effective and eco-friendly approaches that align with circular economy/waste management principles, ultimately contributing to climate change mitigation. However, several challenges impede the widespread utilization/transformation of BBR, including technological limitations in processing and application, concerns about contamination (e.g., PAHs, PCBs, micro/nano plastics present in BS), toxicity issues (e.g., heavy metals in BA or nanoparticles in BC), and regulatory constraints (e.g., non-uniform regulations governing the reuse of BA and BS). Addressing these challenges demands an interdisciplinary and intersectoral approach to fully unlock the potential of BBR in sustainable decarbonisation efforts.

In the spacious inundation area on the left bank of the lower course of the Sava River in Serbia, there is an abandoned meander Special Nature Reserve, “Obedska bara”, which represents a very important floodplain in this part of Europe. This area is characterized by an exceptional wealth of biodiversity with a significant presence of rare and endangered species of national and international importance. Hydrological conditions in the mentioned area were analyzed from the aspect of surface water movement in nature and conditions altered by human factors (after the construction of the road network, canals, etc.). The movement of surface water, i.e., the filling and emptying of the investigated area, parallel to the water level of the Sava River, is shown using a digital terrain model. Our simulation of the change in surface water level within the studied area included the display of underwater areas, both with the formation of a flood wave (i.e., increasing water level of the Sava) and with the outflow of water from the pond when the water level in the Sava was reduced in both scenarios (natural and conditions altered by human factors). GIS and terrain digitalization were used for geospatial and hydrological analyses and, based on this, maps that display endangered areas could be made. The obtained results show that the largest human impact was recorded at the water level of the Sava River 74 m above sea level. The aforementioned water regime changes were shown to negatively affect dominant vegetation, such as pedunculate oak and ash.

Conserving clean and safe freshwater is a global challenge, with nitrogen (N) and phosphorus (P) as frequent limiting factors affecting water quality due to eutrophication. This paper provides a critical overview of the spatiotemporal variability in both nutrient concentrations and their total mass ratio (TN:TP) in the canal network of the Hydro system Danube–Tisza–Danube at 21 measuring locations monitored by the Environmental Protection Agency of the Republic of Serbia over a length of almost 1000 km, collected once a month during the last decade. A spatiotemporal variation in nutrient concentrations in the tested surface water samples was confirmed by correlations and cluster analyses. The highest TN concentrations were found in winter and early spring (non-vegetation season), and the highest TP concentrations in the middle of the year (vegetation season). The TN:TP mass ratio as an indicator of the eutrophication pointed out N and P co-limitation (TN:TP 8–24) in 64% of samples, N limitation (TN:TP < 8) was detected in 27% and P limitation (TN:TP > 24) in the remaining 9% of water samples. Such observations indicate slow-flowing, lowland water courses exposed to the effects of non-point and point contamination sources as nutrient runoff from the surrounding farmlands and/or urban and industrial zones, but further investigation is needed for clarification. These results are an important starting point for reducing N and P runoff loads and controlling source pollution to improve water quality and underpin recovery from eutrophication in the studied watershed.

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 (NO ₃ ^– -N), total phosphorus (P _tot ), biochemical oxygen demand (BOD ₅ ) 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 NO ₃ ^– -N, P _tot and BOD ₅ ; Bogojevo for NO ₃ ^– -N, P _tot , COD and BOD ₅ ; Novi Sad for P _tot , BOD ₅ and COD; Slankamen for BOD ₅ and COD; Smederevo for NO ₃ ^– -N and COD; Banatska Palanka for NO ₃ ^– -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.

The study evaluates irrigation water quality in the Danube-Tisa-Danube hydrosystem area (Vojvodina, northern Serbia). The area is dominantly a plain with about 75% arable land, suitable for agricultural production and irrigation. Use of water of inadequate quality can have long-term effects on irrigated land and affect the yield of cultivated crops. The analyses included data from 40 surface water and 23 groundwater quality monitoring locations, observed during the period 2013–2018. The average annual values of the concentrations of major cations and anions and of electrical conductivity in surface and groundwater were comparatively analyzed. These values were statistically significantly higher (by p < 0.05) in groundwater bodies with most of the analyzed parameters. Hydrochemical classification of water types shows that 95% of surface and 87% of groundwater locations belong to the Ca·Mg–HCO₃ water type. Water suitability for irrigation was assessed using specific parameters and indices (sodium adsorption ratio, Na%, residual sodium carbonate, magnesium hazard, permeability index, and Kelly’s index). The results showed that surface and groundwater resources are generally of good quality and suitable for irrigation, with sporadic deviations at several locations. The principal component analysis (PCA) was used to identify the most important variables affecting the chemical composition of the analyzed waters and group the monitoring locations by their chemical characteristics. The spatial variation of the analyzed water quality indices was shown on thematic maps.

To test an assumption that organic soil can ameliorate nutritional disorders associated with metal and salinity stresses, we exposed salt-sensitive strawberry and lettuce to four salinity (0–60 mM NaCl) and three contamination (0.3–5 mg Cd/kg) rates in peat (pH_H2O = 5.5). The results showed that, even at 20 mM NaCl, salinity stress exerted a dominant effect on rhizosphere biogeochemistry and physiological processes, inducing leaf-edge burns, chlorosis/necrosis, reducing vegetative growth in crops; at ≥40 mM, NaCl mortality was induced in strawberry. Signifiacntly decreased K/Na, Ca/Na and Mg/Na concentration ratios with raising salinity were confirmed in all tissues. The combined CdxNaCl stresses (vs. control) increased leaf Cd accumulation (up to 42-fold in lettuce and 23-fold in strawberry), whereas NaCl salinity increased the accumulation of Zn (>1.5-fold) and Cu (up to 1.2-fold) in leaves. Lettuce accumulated the toxic Cd concentration (up to 12.6 mg/kg) in leaves, suggesting the strong root-to-shoot transport of Cd. In strawberry Cd, concentration was similar (and sub-toxic) in fruits and leaves, 2.28 and 1.86 mg/kg, respectively, suggesting lower Cd root-to-shoot translocation, and similar Cd mobility in the xylem and phloem. Additionally, the accumulation of Cd in strawberry fruits was exacerbated at high NaCl exposure (60 mM) compared with lower NaCl concentrations. Thus, in salinized, slightly acidic and organically rich rhizosphere, pronounced organo- and/or chloro-complexation likely shifted metal biogeochemistry toward increased mobility and phytoavailability (with metal adsorption restricted due to Na⁺ oversaturation of the caton exchange complex in the substrate), confirming the importance of quality water and soils in avoiding abiotic stresses and producing non-contaminated food.