LoRa- Based Dynamic Water Level and Quality Monitoring System Using Machine Learning

Abstract

This paper proposes LoRa based Dynamic water level and quality monitoring system using machine learning. Traditional systems rely on GSM or Wi-Fi, which limits range and drains power, especially in remote areas. Recent studies show a shift toward smarter sensor networks enhanced by machine learning, but many setups still struggle with scalability, prediction, and combined monitoring of both water level and quality. The system discussed here tackles these gaps by using affordable sensors, an ESP32, and LoRa for long-range, low-power data transfer. Algorithms like Random Forest and Isolation Forest improve water quality classification and anomaly detection. Overall, combining LoRa with machine learning provides a reliable, efficient, and cost-effective way to monitor groundwater in real time and prevent contamination.

Introduction

Groundwater is a vital resource for domestic, agricultural, and industrial use, but urbanization, industrial discharge, and climate change are causing depletion and contamination. Traditional monitoring systems are limited—they often measure only water level, rely on costly or energy-intensive mobile networks, and require lab testing for water quality, which is slow and not real-time.

This paper proposes a low-cost, smart groundwater monitoring system using IoT sensors, LoRa long-range communication, and machine learning. The system continuously monitors water level and quality parameters like pH, turbidity, and Total Dissolved Solids (TDS). A Random Forest classifier assesses water quality, while an Isolation Forest detects anomalies. Data is visualized in real-time through a Flask-based dashboard, enabling early detection of pollution or equipment faults.

The system is energy-efficient, suitable for remote and resource-limited areas, and improves on traditional methods by offering real-time, multi-parameter, and intelligent monitoring. Experimental tests show accurate water level measurement, reliable data transmission, and effective classification of safe versus unsafe water conditions, demonstrating its practical applicability for groundwater management.

Conclusion

The Machine Learning–based Intelligent Water Quality Monitoring System represents a significant advancement in integrating IoT and artificial intelligence for environmental monitoring. Now we have successfully developed and deployed a Flask-based web dashboard capable of real-time monitoring and classification of water quality based on five key parameters: pH, turbidity, temperature, dissolved oxygen (DO), and conductivity. The system accurately classifies water as “Safe” or “Unsafe”, detects sudden spikes and anomalies in sensor readings using Isolation Forest, and predicts future trends using Linear Regression. This phase has validated the feasibility of combining machine learning models with IoT sensors to provide actionable insights into water quality. Next phases will expand the project toward a comprehensive smart water management solution. The ongoing development promises a scalable, intelligent, and sustainable approach to ensuring safe water resources for communities

References

[1] O. H. Kombo, S. Kumaran, and A. Bovim, “Design and Application of a Low-Cost, Low- Power, LoRa-GSM, IoT Enabled System for Monitoring of Groundwater Resources with Energy Harvesting Integration,” IEEE Access, vol. 9, pp. 150312–150324, 2021. [2] M. M. Rahman, C. Bapery, M. J. Hossain, Z. Hassan, G. M. J. Hossain, and M. M. Islam, “Internet of Things (IoT) Based Water Quality Monitoring System,” International Journal of Multidisciplinary and Current Educational Research (IJMCER), vol. 2, no. 4, pp. 245–252, 2020. [3] F. T. Liu, K. M. Ting, and Z. H. Zhou, “Isolation Forest,” Proceedings of the IEEE International Conference on Data Mining (ICDM), Pisa, Italy, pp. 413–422, 2008. [4] “Water Quality Monitoring System Using ML Model,” International Journal of Creative Research Thoughts (IJCRT), vol.12, no. 5, pp. 1124–1130, 2024. [5] A. J. Calderwood, R. A. Pauloo, A. M. Yoder, and G. E. Fogg, “Low-Cost, Open-Source Wireless Sensor Network for Real-Time, Scalable Groundwater Monitoring,” Water, vol. 12, no. 4, pp. 1–16, 2020. [6] Z. Sun, H. Yang, K. Liu, Z. Yin, Z. Li, and W. Xu, “Recent Advances MS56in LoRa: A Comprehensive Survey,” ACM Transactions on Sensor Networks (TOSN), vol. 18, no. 4, pp. 1–39, 2022. [7] E. I. Putra, M. U. E. Syakbandani, S. Pramono, and A. Saad, “Estimating Groundwater Level in Peatlands by Using Submersible Sensor,” Journal of Tropical Silviculture Science and Technology, vol. 15, no. 1, pp. 25–32, 2024. [8] V. Shilwant, P. Thakare, and S. Sangle, “Comparative Study of Water Quality Assessment with IoT & Lab Test,” International Journal of Engineering Research & Technology (IJERT), vol. 13, no. 4, pp. 450–453, 2024. [9] G. R. Kumar, D. Kishore, and G. V. M. G. Kumar, “Waste Contamination in Water – A Real-Time Water Quality Monitoring System using IoT,” Proceedings of the International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, IEEE, pp. 1–5, 2021. [10] A. N. Prasad, K. A. Mamun, F. R. Islam, and H. Haqva, “Smart Water Quality Monitoring System,” Proceedings of the Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), Nadi, Fiji, IEEE, pp. 1–6, 2015.

Copyright

Copyright © 2026 Devanandhini B, Abhirami A S , Anishma A R, Carolin Suresh, Prof. Jayaresmi J, Prof. Smitha K S. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.