1. Predrag Dašić, SaTCIP Publisher Ltd., 36610 Vrnjačka Banja i Visoka tehnička mašinska škola strukovnih studija (VTM, Serbia
2. Sladjana Beljić Miletić, O.Š. Dobrica Ćosić, 37245 Velika Drenova (37240 Trstenik), , Serbia
3. Suzana Jakovljević, O.Š. Dobrica Ćosić, 37245 Velika Drenova, O.Š. Ljubivoje Bajić, 37244 Medveđa 37240 Trstenik, Serbia
Water quality assessment (WQA) is a comprehensive and complex multidisciplinary process of evaluating the physical, chemical and biological properties of water in order to determine its state with respect to human impacts and intended uses. Determining and assessing WQA requires the integration, analysis and interpretation of large amounts of spatial, temporal, ecological, hydrochemical and other data. Conventional approaches to water quality monitoring are often based on measurements obtained from a limited number of sampling locations and predefined monitoring intervals. Although these approaches provide valuable information about the current state of water quality and water resources, they may not adequately represent spatial and temporal variations in water quality. To overcome these limitations and integrate heterogeneous datasets, identify complex relationships between environmental parameters, spatial prediction, and visualize water quality conditions, artificial intelligence-based geographic information systems (GIS) (AI-GIS or GeoAI) have been increasingly used in recent years. AI-GIS systems combine artificial intelligence (AI), artificial neural networks (ANN), machine learning (ML), deep learning (DL), and computer vision (CV) with spatial mapping data. This integration automates complex spatial analysis, extracts features from satellite and drone imagery, processes natural language mapping commands, and drives modeling and prediction for the real environment.
In this paper presents the analysis and application of the AI-GIS system for water quality assessment (WQA) and support for spatial decision-making and planning. AI-GIS systems integrate GIS capabilities with artificial intelligence (AI) and artificial neural networks (ANN), machine learning (ML) and deep learning (DL) methods to analyze water quality parameters and their spatial and temporal variability. The methodology includes collection and preprocessing of water quality data, georeferencing of sampling locations, integration of hydrochemical and environmental variables into a GIS environment, and application of selected AI-based models for classification, prediction, and spatial assessment of water quality. Depending on the characteristics of the available data set, parameters such as: pH, temperature, electrical conductivity, dissolved oxygen, turbidity, biochemical oxygen demand, chemical oxygen demand, nitrates, phosphates, concentrations of selected heavy metals, etc. can be taken into account. Some authors include additional spatial factors in these analyses, including land use, soil characteristics, hydrological conditions, population density, industrial activities, proximity to potential sources of pollution, etc.
Ključne reči :
Tematska oblast:
Datum:
25.08.2026.
Contemporary Materials 2026 - Savremeni Materijali
Datoteka uz rad
(56.00 KB)
