This research focuses on the integration of IoT and a Soft Sensor Model to measure the dissolved oxygen content and water purity in water bodies. Various sensors, including pH, temperature, and turbidity sensors, are employed to collect sensor readings that reflect the water quality. The collected data is utilized to develop mathematical models and algorithms for predicting the dissolved oxygen concentration and water purity. Regression equations and a neural network algorithm are implemented to accurately estimate the desired parameters based on the sensor readings. The integration of IoT technology enables real-time inpecting and analysis of water quality, facilitating timely detection of deviations and implementation of corrective measures. The developed models demonstrate high accuracy in predicting the dissolved oxygen concentration and water purity, showcasing the reliability and effectiveness of the proposed approach. The findings of this research contribute to the field of water quality management by providing a robust framework for continuous monitoring and assessment. The integration of IoT and the Sensor Model presents a valuable tool for various sectors, including environmental management and water treatment facilities. Future research could explore the expansion of the dataset and incorporation of additional sensors, as well as the integration of advanced machine learning techniques, to further enhance the prediction capabilities and gain comprehensive insights into water quality dynamics. Overall, this research contributes to the advancement of efficient and reliable methods for measuring and assessing water quality parameters, paving the way for effective water resource management and environmental conservation.