Abstract
The aim of this study is to develop an intelligent water resource monitoring system for hydraulic structures in the Zhambyl region using IoT technologies, GIS, and machine learning methods. The novelty of the approach lies in the integration of real-time data from IoT sensors with deep learning algorithms to predict changes in water quality and hydrological events. The study presents a model that enables automated assessment of water quality and early detection of environmental risks. The results show that among the tested algorithms, the Random Forest model achieved the highest accuracy (~80%) in water quality classification. Compared to previous studies, the proposed solution offers a higher level of automation and prediction accuracy due to the combination of sensor data and artificial intelligence. The practical significance of the work lies in improving the efficiency of water resource management, enabling rapid detection of pollution, and enhancing preparedness for floods and droughts.