Effective application of artificial intelligence in water research and in addressing water-related environmental challenges requires access to high-quality and properly structured data. This thesis presents a systematic review of publicly available data sources in the fields of water quality, hydrology, floods and droughts, aquatic ecosystems, pollution, and wastewater treatment. A methodology was developed for identifying, evaluating, and classifying data sources according to thematic scope, geographic coverage, data acquisition method, format, and suitability for machine learning. Recent scientific studies that utilize these data sources were also analyzed, with their effectiveness and approaches to data integration assessed. The final outcome of the thesis is a structured catalog of data sources, along with an analysis of their limitations and potential for further data-driven research.
|
