Nevenka Djurovic

Comparison of Groundwater Level Models Based on Artificial Neural Networks and ANFIS

Water table forecasting plays an important role in the management of groundwater resources in agricultural regions where there are drainage systems in river valleys. The results presented in this paper pertain to an area along the left bank of the Danube River, in the Province of Vojvodina, which is the northern part of Serbia. Two soft computing techniques were used in this research: an adaptive neurofuzzy inference system (ANFIS) and an artificial neural network (ANN) model for one-month water table forecasts at several wells located at different distances from the river. The results suggest that both these techniques represent useful tools for modeling hydrological processes in agriculture, with similar computing and memory capabilities, such that they constitute an exceptionally good numerical framework for generating high-quality models.

Application of the AquaCrop model to simulate the biomass of Miscanthus x giganteus under different nutrient supply conditions

There are conflicting opinions about the need to fertilize Miscanthus and, also, the question has been raised whether Miscanthus should be irrigated, especially if water resources are limited. Crop growth modeling can help answer such questions. In this article the FAO AquaCrop water‐driven model was selected to simulate Miscanthus biomass under different nutrient and water supply conditions. The article reports the outcomes of 6‐year experiments with Miscanthus on two locations in Serbia: Zemun, where three fertilizer treatments were applied (Nl – 100 kg ha−1, Nopt 50 kg ha−1 and Nf nonfertilized), and Ralja, where only Nl 100 kg ha−1 was applied. Model calibration focused on the measured data (root depth, crop phenology, and the above‐ground biomass by year of growth. Calibration results showed a very good match between measured and simulated values. The largest and only significant difference was noted in 2008, when the crop was establishing and exhibited uneven radication. The simulation results for the next 5 years showed a variance from −4 to 5.7%, believed to be a very good match. A high coefficient of determination (R2 = 0.995) and high Willmott index of agreement (0.998) were also indicative of a good match between simulated and recorded biomass yields. The measured and simulated results for validated datasets at both locations were good. The average RMSE was 2.89 Mg ha−1; when compared to the deviations noted at the test site itself, it was apparent that they were smaller in all the years of research except the first year. The index of agreement was 0.97 and the coefficient of determination R2 0.947. The AquaCrop model can be used with a high degree of reliability in strategic planning of Miscanthus cultivation in new areas, under different nutrient and water supply and local weather and soil conditions.

Contamination of local water supply systems in suburban Belgrade

In suburban Belgrade, there are some 200 local water supply systems which are not connected to either the Belgrade Water Supply System or to supply systems operated by municipal utilities. The small systems in Belgrade suburbs are either operated by local municipality (local government) or even by the group of local citizens who have neither technical capability nor financial resources to do it properly. Roughly 200,000 of Belgrades inhabitants obtain their drinking water from these water supply systems. The water quality delivered by these local water supply systems is often compromised in terms of microbiological, physical and/or chemical compliance with drinking water standards in addition to the general lack of strategy on water safety plans and risk assessment. WHO Guidelines on water quality standards as well as the recommendations on safety plans and whole risk assessment are strictly respected in the main (central) Water Supply System in Belgrade. Most frequently, elevated concentrations of ammonia, nitrites, nitrates and iron lead to lack of chemical compliance, while elevated counts of aerobic mesophilic bacteria and the presence of bacteria indicative of faecal pollution tend to be behind microbiological lack of compliance with drinking water standards. In most cases, failure to meet drinking water standards can be attributed to groundwater pollution. No sewer system exists in these areas, and wastewater from septic tanks, in practice infiltration wells, is in direct contact with groundwater. Of a total of 72 laboratory-tested drinking water samples, 51.3% failed to meet physical and/or chemical standards, and 73.6% failed to meet microbiological standards. Groundwater pollution can only be prevented if wastewater disposal system is provided for all households and all suburban residential areas which obtain their water supply from local water supply systems. Some possible mitigation measures have been indicated. In the interim period, water must be disinfected continually, and the feasibility of ozonation or UV irradiation, in addition to chlorination, should be assessed.

Some characteristics of groundwater in Southeast Srem

The area of Southeast Srem is rich in groundwater. Water regime of the first aquifer has a great significance from the standpoint of agricultural production. 32 piezometers were singled out and groundwater depth was measured aiming at the analysis of some groundwater characteristics. In the area of Southeast Srem, groundwater level fluctuates very widely, depending on the distance from water courses. Mean value of groundwater fluctuation in Southeast Srem amounts to 3.49m. In this area, groundwater moves in Southeast direction, i.e. in the direction of the main receiving streams of the region, the Sava and the Danube. The greatest risk of groundwater overflowing in Southeast Srem occurs in the central parts of the loess terrace and in low parts of the alluvial plain along the Sava, where groundwater level is at the depth of less than 1m.

Application of Kraijenhoff Van de Leur - Maasland’s method in drainage

The aim of this work is to show some properties of the application of Kraijenhoff Van de Leur-Maasland’s method for drain spacing determination in unsteady state of flow. The analysis of the method is based on data obtained from drainage field with 10 m of drain spacing which dries out eugley soil. The results of analysis show the range of method applicability as well as certain limitations in the case of non-modelled dynamics of ground water recharges.