SMART LAKE REJUVENATION WITH AI-POWERED ENVIRONMENTAL MONITORING

This project, Smart Lake Rejuvenation with AI-Powered Environmental Monitoring (SLIM-AI Lite), successfully developed an AI-based system for continuous lake water quality monitoring. The system uses Random Forest for water quality classification and Isolation Forest for anomaly detection. It also provides explainable results, identifies possible pollution sources, calculates a lake health score, and predicts future pollution risks. The Digital Twin approach enables realistic testing without physical IoT sensors, making the system cost-effective and easy to validate. The interactive dashboard displays real-time readings, alerts, and historical data for better decision-making. Overall, the proposed system provides an efficient, scalable, and intelligent solution for sustainable lake monitoring and can be enhanced in the future by integrating real IoT sensors and cloud technology.  

[1] Bhardwaj, A., Gupta, R., & Kumar, S. (2020). IoT-Based Real-Time Water Quality Monitoring System for Smart Aquaculture. International Journal of Engineering Research and Technology, 9(8), 78–83. [2] Raju, K. L., & Reddy, P. S. (2021). Design and Implementation of a Multi-Parameter Water Quality Monitoring Device Using Raspberry Pi. Journal of Sensors, 2021, Article ID 5567921. https://doi.org/10.1155/2021/5567921 [3] Singh, A., Patel, H., & Desai, M. (2021). Machine Learning Approaches for River Water Quality Classification in India. Water Resources Management, 35(4), 1345–1360. https://doi.org/10.1007/s11269-021-02754-z [4] Chen, Y., & Shi, P. (2022). Water Quality Index Prediction Using Gradient Boosting Machines: A Case Study of Taihu Lake. Environmental Modelling and Software, 148, 105282. https://doi.org/10.1016/j.envsoft.2021.105282 [5] Kiliç, K. E., & Ozbay, E. (2021). Anomaly Detection in Urban Water Systems Using One-Class SVM. Procedia Computer Science, 185, 190–197. https://doi.org/10.1016/j.procs. 2021.05.020 [6] Zhang, L., Liu, J., & Wang, H. (2023). Isolation Forest-Based Unsupervised Anomaly Detection for Municipal Water Quality Data. Water Science and Technology: Water Supply, 23(1), 112–124. https://doi.org/10.2166/ws.2022.432 [7] Gupta, S., & Mehta, K. (2023). Explainable Artificial Intelligence for Lake Water Quality Assessment: A LIME-Based Approach. Environmental Informatics, 42(3), 567–580. [8] Pedersen, M., & Larsen, J. (2022). Digital Twin of a Wastewater Treatment Plant for Scenario Simulation and Predictive Control. Water Research, 211, 118012. https://doi.org/10.1016/j.watres. 2021.118012 [9] Ramesh, A., Nair, S., & Das, S. (2023). Simulation-Based Validation of IoT-Enabled Lake Monitoring Systems Using Digital Twins. IEEE Sensors Journal, 23(15), 17210–17220. https://doi.org/10.1109/JSEN.2023.3275621 [10] Sharma, D., & Patel, R. (2024). A Review of Smart Water Quality Monitoring: From Sensors to Machine Learning and Digital Twins. Sustainable Computing: Informatics and Systems, 41, 100912. https://doi.org/10.1016/j.suscom.2023.100912