WatAI: AI-Based System for Real-Time Flow Monitoring and Demand Prediction in Water Networks
Downloads
Efficient monitoring and control of water demand are crucial for sustainable water resource management. Bogotá, Colombia, currently faces supply rationing due to climate change and ineffective public policies. This study presents WatAI (Water + AI), an AI-powered system designed for real-time flow monitoring and demand prediction in water distribution networks. The system integrates flow sensors, microcontrollers, and machine learning algorithms to capture high-resolution temporal data. A dynamic sequential artificial neural network (ANN) with ReLU activation and Adam optimization is implemented, allowing real-time adjustments (1 sec) to flow variations and anomaly detection. To enhance accuracy, the system applies real-time signal filtering and transmits early alerts via email to service providers. The ANN model achieved an MSE of 0.006510, demonstrating improved accuracy with increasing historical data. Compared to traditional forecasting models, WatAI provides higher temporal resolution and adaptability to demand fluctuations, making it a more effective tool for intelligent water management. The study contributes to the development of IoT-based smart infrastructures for sustainable urban water planning.
Downloads
[1] Mounce, S. R., Mounce, R. B., & Boxall, J. B. (2011). Novelty detection for time series data analysis in water distribution systems using support vector machines. Journal of Hydroinformatics, 13(4), 672–686. doi:10.2166/hydro.2010.144.
[2] Samikwa, E., Voigt, T., & Eriksson, J. (2020). Flood Prediction Using IoT and Artificial Neural Networks with Edge Computing. Proceedings - IEEE Congress on Cybermatics: 2020 IEEE International Conferences on Internet of Things, IThings 2020, IEEE Green Computing and Communications, GreenCom 2020, IEEE Cyber, Physical and Social Computing, CPSCom 2020 and IEEE Smart Data, SmartData 2020, 234–240. doi:10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00053.
[3] Adeleke, I. A., Nwulu, N. I., & Ogbolumani, O. A. (2023). A hybrid machine learning and embedded IoT-based water quality monitoring system. Internet of Things (Netherlands), 22, 22. doi:10.1016/j.iot.2023.100774.
[4] Bhati, A., Hiran, K. K., Vyas, A. K., Mijwil, M. M., Aljanabi, M., Metwally, A. S. M., Al-Asad, M. F., Awang, M. K., & Ahmad, H. (2024). Low cost artificial intelligence Internet of Things based water quality monitoring for rural areas. Internet of Things (Netherlands), 27, 101255. doi:10.1016/j.iot.2024.101255.
[5] Poyen, F. Bin, Ghosh, A., Kundu, P., Hazra, S., & Sengupta, N. (2021). Prototype Model Design of Automatic Irrigation Controller. IEEE Transactions on Instrumentation and Measurement, 70, 1–17. doi:10.1109/TIM.2020.3031760.
[6] Islam, M. R., Azam, S., Shanmugam, B., & Mathur, D. (2023). An Intelligent IoT and ML-Based Water Leakage Detection System. IEEE Access, 11, 123625–123649. doi:10.1109/ACCESS.2023.3329467.
[7] Ladino-Moreno, E. O., & García-Ubaque, C. A. (2024). Leak Detection in Urban Hydraulic Systems Using the K-BiLSTM-Monte Carlo Dropout Model. Civil Engineering Journal (Iran), 10(7), 2066–2087. doi:10.28991/CEJ-2024-010-07-01.
[8] Narayanan, L. K., Sankaranarayanan, S., Rodrigues, J. J. P. C., & Kozlov, S. (2020). Water Demand Forecasting using Deep Learning in IoT Enabled Water Distribution Network. International Journal of Computers, Communications and Control, 15(6)و 3977. doi:10.15837/ijccc.2020.6.3977.
[9] Liu, C. H., Yang, T. H., & Wijaya, O. T. (2022). Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting. Sensors, 22(21), 8532. doi:10.3390/s22218532.
[10] Escobar-Jiménez, R., Salvide-Hernández, F., López-Muñoz, R., Tolentino-Eslava, R., & Maya-Rodriguez, M. C. (2022). Monitoring and Prediction of Drinking Water Consumption. Telematics and Computing. WITCOM 2022. Communications in Computer and Information Science, Springer, Cham, Switzerland. doi:10.1007/978-3-031-18082-8_5.
[11] Dhanalakshmi, R., Anand, J., Sivaraman, A. K., & Rani, S. (2022). IoT-Based Water Quality Monitoring System Using Cloud for Agriculture Use. Cloud and Fog Computing Platforms for Internet of Things, 183–196, Chapman and Hall/CRC, Boca Raton, United States. doi:10.1201/9781003213888-14.
[12] Blanco-Gómez, P., Mateu-Belloch, A., Jiménez-García, J. L., Salas-Cantarellas, A. J., Pieras-Company, J. J., & Santamaría-Casals, E. (2024). Real-time ultrasonic water level IoT sensor for in-situ soil permeability testing. HardwareX, 19, 19,541. doi:10.1016/j.ohx.2024.e00541.
[13] Benazzouza, S., Ridouani, M., Salahdine, F., & Hayar, A. (2024). A novel spectrogram based lightweight deep learning for IoT spectrum monitoring. Physical Communication, 64, 64,102364. doi:10.1016/j.phycom.2024.102364.
[14] Liu, Z. (2024). Implementation of Fast Fourier Transform in Iot Data Analysis, Ai and Audio Signal Processing. IET Conference Proceedings, 24, 436–440. doi:10.1049/icp.2024.4546.
[15] Ibrom, A., Dellwik, E., Flyvbjerg, H., Jensen, N. O., & Pilegaard, K. (2007). Strong low-pass filtering effects on water vapour flux measurements with closed-path eddy correlation systems. Agricultural and Forest Meteorology, 147(3–4), 140–156. doi:10.1016/j.agrformet.2007.07.007.
[16] Shahid, M. B., Abbasi, M. A., & Muazzam, M. (2015). Detection of noise in high pass IIR digital filters. In 2015 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), 1-5. doi:10.1109/HNICEM.2015.7393222.
[17] Suwansukho, N., & Wutthithanyawat, C. (2024). Experimental Study of Real-Time Water Quality Analysis with Deep Neural Network (DNN) on Edge Computing. 2024 10th International Conference on Engineering, Applied Sciences, and Technology (ICEAST), 138–143. doi:10.1109/iceast61342.2024.10553703.
[18] Wu, Y., Liu, S., Smith, K., & Wang, X. (2018). Using Correlation between Data from Multiple Monitoring Sensors to Detect Bursts in Water Distribution Systems. Journal of Water Resources Planning and Management, 144(2), 04017084. doi:10.1061/(asce)wr.1943-5452.0000870.
[19] Zese, R., Bellodi, E., Luciani, C., & Alvisi, S. (2021). Neural Network Techniques for Detecting Intra-Domestic Water Leaks of Different Magnitude. IEEE Access, 9, 126135–126147. doi:10.1109/access.2021.3111113.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
