Downloads: 2 | Views: 45 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2
Research Paper | Computer Science and Information Technology | United States of America | Volume 13 Issue 2, February 2024 | Popularity: 5 / 10
Machine Learning - Based TDS Prediction and Water Quality Monitoring
Omkar Reddy Polu
Abstract: Public health and environmental sustainability demand that water quality integrity is ensured. A primary metric used to measure water contamination is Total Dissolved Solids (TDS), however conventional methods have no predictive capabilities, real time. A machine learning based water quality monitoring framework is presented, which implements the predictive analytics together with the IoT enabled sensor networks for the purpose of an early anomaly detection and dynamic contamination assessment, this research. Temperatures such as high and low approximate the max and min, with the another representing the count and what you?re walking into. Continuous real time water quality parameters can be obtained from IoT modules based ESP8266, the data is transmitted to the cloud based inference engine. The predictive robustness is improved by a hybrid DNN based LSTM networks & Random Forest Regression and Bayesian optimization machine learning model. Another is the addition of a water flow sensor driven analytics module to give intelligent water management; the analytics module enables correlation of consumption-based contamination. For computational efficiency as well as feasibility to deploy on every edge, such lightweight deep learning models are optimized for inference on resource constrained environments. Empirical dataset based rigorous model validation shows high precision anomaly detection i. e., very low false positives in alerts of contamination. The proposed framework is extensible and thus can be extended towards adaptation, adaptive filtration automation, federated learning for decentralized quality monitoring, and multi modal sensor fusion.
Keywords: Predictive Water Quality Assessment, TDS Forecasting, IoT - Enabled Anomaly Detection, ML - Driven Contamination Analysis, Smart Water Governance
Edition: Volume 13 Issue 2, February 2024
Pages: 1911 - 1916
DOI: https://www.doi.org/10.21275/SR24027114805
Please Disable the Pop-Up Blocker of Web Browser
Verification Code will appear in 2 Seconds ... Wait