With the goal of enhancing the quality of the environment, urban green infrastructure (UGI) is an essential element in sustainable cities, and nature-based solutions (NBS) are being carried out as new infrastructure solutions that increase the resilience of cities. In this research, the method of theoretical analysis and the content analysis as the basic fact-gathering technique was applied to answer to following questions: What are the hindrances and bottlenecks in implementing NBS? Are the current decision-making mechanisms helping NBS get in route to shape cities? Is there any binding policy in practice that promotes NBS? In Belgrade is planned Type 3 of the degree of intervention/level and engineering type—Creation and new ecosystem management in the classifications of intensive urban green space management; urban planning strategies; urban water management; ecological restoration of degraded terrestrial ecosystems; and restoration and creation of semi-natural water bodies and hydrographic networks. In the future, it is essential to implement policies and incentives on national, regional, and local scales that help encourage the usage of NBS in the development of urban infrastructure.

Purpose: To anticipate the impact of illegal landfills, development of new models should become a part of environmental risk management strategies. One of such approaches includes applications of the artificial neural network (ANN). The main objective of this study was to elucidate the impact of illegal landfilling on the surrounding soil environment and human health, as well as to establish an artificial neural network (ANN) models for predicting the hazards of illegal landfilling as an effective tool in decision-making and environmental risk management. Methods: The identification of heavy metals source in soil was performed by principal component analysis (PCA). To assess the sensitivity of the soil ecosystem to heavy metal concentrations, Soil Quality standards and quantitative indices were used. The possible health effects were valued using the average daily doses (ADDs), hazard quotient (HQ), hazard index (HI), and carcinogenic risk (CR). ANN modeling was used for the prediction of heavy metal concentrations in the soil based on landfill size, municipality size, the number of residents, plant species, soil, and landform types. Results: The average values of the pollution indexes for Cd were in the moderately contaminated and very high contamination categories. The $$HQ$$HQ values were lower than the safe level. Cr and Pb posed a significant $$CR$$CR for adults and children, and Ni for children. The ANN models have exhibited good generalization power and accurately predicted the output parameters with a high value of the coefficient of determination. Conclusion: Concerning heavy metal concentrations, illegal landfills near agricultural soil have a significant impact on the soil ecosystem and people’s health. The developed ANN models can be applied generally to anticipate the heavy metal concentrations in soil, according to the before mentioned input parameters, with high accuracy.

The negative external effects caused by traffic growth have been recognized as the main factors that degrade city quality of life. Therefore, research around the world is being conducted to understand the impact of traffic better and find adequate measures to reduce the negative impact of traffic growth. The central part of this research consists of mathematical models for simulating the negative consequences of congestion and noise pollution. Four non-linear models for determining noise levels as a function of traffic flow parameters (intensity and structure) in the urban environment were developed. The non-linear models, including two artificial neural networks and two random forest models, were developed according to the experimental measurements in Novi Sad, Serbia, in 2019. These non-linear models showed high anticipation accuracy of the equivalent continuous sound level (Laeq), with R² values of 0.697, 0.703, 0.959 and 0.882, respectively. According to the developed ANN models, global sensitivity analysis was performed, according to which the number of buses at crossings was the most positively signed influential parameter in Laeq evaluation, while the lowest Laeq value was reached during nighttime. The locations occupied by frequent traffic such as Futoska and Temerinska positively influenced the Laeq value.

The main objective of this study is to determine the possibility of predicting the impact of land use and soil type on concentrations of heavy metals (HMs) and phthalates (PAEs) in soil based on an artificial neural network model (ANN). Qualitative analysis of HMs was performed with inductively coupled plasma–optical emission spectrometry (ICP/OES) and Direct Mercury Analyzer. Determination of PAEs was performed with gas chromatography (GC) coupled with a single quadrupole mass spectrometry (MS). An ANN, based on the Broyden–Fletcher–Goldfarb–Shanno (BFGS) iterative algorithm, for the prediction of HM and PAE concentrations, based on land use and soil type parameters, showed good prediction capabilities (the coefficient of determination (r²) values during the training cycle for HM concentration variables were 0.895, 0.927, 0.885, 0.813, 0.883, 0.917, 0.931, and 0.883, respectively, and for PAEs, the concentration variables were 0.950, 0.974, 0.958, 0.974, and 0.943, respectively). The results of this study indicate that HM and PAE concentrations, based on land use and soil type, can be predicted using ANN.

Dimethachlor is an herbicide used for oilseed rape protection. Previous studies have demonstrated its high mobility in the soil, which could lead to water contamination. This research aimed to determine the occurrence of dimethachlor and its metabolites (dimethachlor ethanesulfonic acid ESA and dimethachlor oxalamic acid OA) in surface water using a recently developed analytical method. This article is one of the first to document dimethachlor and its metabolites’ presence in surface water samples. The samples were collected from the Danube river and Tisza river. The quantitative determination of dimethachlor and its metabolites in the obtained extracts was done by high-performance liquid chromatography. Descriptive statistical methods, including correlation analysis, cluster analysis, and principal component analyses, were utilized to analyze method validation experimental results. In addition, the artificial neural network (ANN) model was applied as an optimization tool. The developed ANN model adequately predicted observed variables, suggesting the optimum results were obtained at a pH value 7, spike value 1, and injection volume equal to 0.5 μL. The average concentrations in Danube River samples were 1.51 µg/L for OA 0.01 µg/L for ESA, and 0.63 µg/L for DMC, while the average concentrations of chloroacetanilide herbicides detected in Tisza River samples were 1.43 µg/L for OA, 0.08 µg/L for ESA and 1.82 µg/L for DMC.

Pesticides in soils raise concerns about the biodiversity, food safety, and contamination of watercourses, contributing to unsustainable land management practices. Monitoring the residue levels in agricultural soils is essential, as this offers valuable insights into the current extent of soil contamination and potential environmental risks attributed to their application. This study aimed to address the occurrence of the currently used herbicides in soil under intensive crop production, comparing the results of monitoring at two depths (0–30 and 30–60 cm) in 2013 and 2023. The research concerned the main agricultural area in Vojvodina Province (Serbia) and evaluated the presence of 41 herbicides in 128 localities. Pesticides were found in all samples, finding even more than six different herbicides per sample. The significant concentrations of s-metolachlor, etofumesate, clomazone, diflufenican, pendimethalin, and terbuthylazine found can be attributed to application practices, as they are typically applied pre-emergence, either through direct soil treatment with or without incorporation. Moreover, the correlation between different depths, herbicide residues, and soil properties was not significant. The decrease in the herbicide residues found in 2023 compared to the residues found in 2013 can be attributed to the implementation of good agricultural practices, which promote sustainable agricultural strategies through controlled pesticide application.