Urban Flood Early Warning System Based on Sensor Networks and Big Data
DOI:
https://doi.org/10.63891/j-mart.v2i1.119Keywords:
urban flooding, early warning, sensor networks, real-time analytics, nowcastingAbstract
Urban flooding is increasingly disruptive in dense cities because intense rainfall and limited drainage capacity can trigger rapid water accumulation with little time for response. Effective early warning requires continuous, local monitoring and fast analytics that can transform high-frequency observations into actionable alerts. This paper presents an urban flood early warning system that integrates distributed sensor networks with real-time data streaming and analytics to deliver timely, reliable warnings at neighborhood scale. The objective of the study was to design and evaluate an end-to-end operational workflow that covers data acquisition, automated data quality control, risk-state detection, short-horizon water-level prediction, and alert generation. The method employed rainfall and water-level sensors that transmitted time-stamped measurements to a gateway and then to a streaming platform for ingestion, storage, and real-time processing. Data quality control was applied to remove physically implausible values, detect spikes, and flag sensor stalls before inference. Risk assessment combined threshold-based logic with predictive nowcasting based on recent rainfall and water-level dynamics, and system performance was evaluated using classification metrics for risk states, prediction error metrics for water level, and operational metrics including end-to-end latency and warning lead time. Results showed that the system maintained 96.7% data availability with a median data gap of 4 minutes, while automated quality control removed 3.2% anomalous readings and flagged seven flatline segments. Risk-state detection achieved precision of 0.84, recall of 0.79, and an F1-score of 0.81, and water-level nowcasting achieved a mean absolute error of 5.2 centimeters, and a root mean square error of 8.9 centimeters. Operationally, alerts were generated with a median end-to-end latency of 3.4 minutes (95th percentile 5.2 minutes) and provided a median warning lead time of 22 minutes (maximum 38 minutes) before critical threshold exceedance. In conclusion, integrating sensor networks with real-time big-data analytics enables practical, low-latency urban flood early warning with measurable lead time and improved alert stability, supporting rapid municipal response actions.
References
Abdel-Basset, M., Mohamed, R., Elhoseny, M., & Chang, V. (2020). Evaluation framework for smart disaster response systems in uncertainty environment. Mechanical Systems and Signal Processing, 145, 106941. https://doi.org/10.1016/j.ymssp.2020.106941
Acosta-Coll, M., Ballester-Merelo, F., Martinez-Peiró, M., & De la Hoz-Franco, E. (2018). Real-time early warning system design for pluvial flash floods A review. Sensors, 18(7), 2255. https://doi.org/10.3390/s18072255
Akanbi, A., & Masinde, M. (2020). A distributed stream processing middleware framework for real-time analysis of heterogeneous data on big data platform: Case of environmental monitoring. Sensors, 20(11), 3166. https://doi.org/10.3390/s20113166
Cumbane, S. P., & Gidófalvi, G. (2019). Review of big data and processing frameworks for disaster response applications. ISPRS International Journal of Geo-Information, 8(9), 387. https://doi.org/10.3390/ijgi8090387
Hajjaji, Y., Boulila, W., Farah, I. R., Romdhani, I., & Hussain, A. (2021). Big data and IoT-based applications in smart environments: A systematic review. Computer Science Review, 39, 100318. https://doi.org/10.1016/j.cosrev.2020.100318
Handayani, W., Chigbu, U. E., Rudiarto, I., & Putri, I. H. S. (2020). Urbanization and increasing flood risk in the northern coast of Central Java Indonesia: An assessment towards better land use policy and flood management. Land, 9(10), 343. https://doi.org/10.3390/land9100343
Ibarreche, J., Aquino, R., Edwards, R., Rangel, V., Pérez, I., Martínez, M., Castellanos, E., Álvarez, E., Jimenez, S., Rentería, R., Edwards, A., & Álvarez, O. (2020). Flash flood early warning system in Colima, Mexico. Sensors, 20(18), 5231. https://doi.org/10.3390/s20185231
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., & Herrnegger, M. (2018). Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrology and Earth System Sciences, 22, 6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Lei, X., Chen, W., Panahi, M., Falah, F., Rahmati, O., Uuemaa, E., Kalantari, Z., Ferreira, C. S. S., Rezaie, F., Tiefenbacher, J. P., Lee, S., & Bian, H. (2021). Urban flood modeling using deep-learning approaches in Seoul, South Korea. Journal of Hydrology, 601, 126684. https://doi.org/10.1016/j.jhydrol.2021.126684
Mendoza-Cano, O., Aquino-Santos, R., López-De la Cruz, J., Edwards, R. M., Khouakhi, A., Pattison, I., Rangel-Licea, V., Castellanos-Berjan, E., Martinez-Preciado, M. A., Rincón-Avalos, P., Lepper, P., Gutiérrez-Gómez, A., Uribe-Ramos, J. M., Ibarreche, J., & Perez, I. (2021). Experiments of an IoT-based wireless sensor network for flood monitoring in Colima, Mexico. Journal of Hydroinformatics, 23(3), 385–401. https://doi.org/10.2166/HYDRO.2021.126
Moreno, C., Aquino, R., Ibarreche, J., Pérez, I., Castellanos, E., Álvarez, E., Rentería, R., Anguiano, L., Edwards, A., Lepper, P., Edwards, R., & Clark, B. (2019). RiverCore: IoT device for river water level monitoring over cellular communications. Sensors, 19(1), 127. https://doi.org/10.3390/s19010127
Ray, P. P., Mukherjee, M., & Shu, L. (2017). Internet of things for disaster management: State-of-the-art and prospects. IEEE Access, 5, 18818–18835. https://doi.org/10.1109/ACCESS.2017.2752174
Silva, B. N., Khan, M., Jung, C., Seo, J., Muhammad, D., Han, J., & Yoon, Y. (2018). Urban planning and smart city decision management empowered by real-time data processing using big data analytics. Sensors, 18(9), 2994. https://doi.org/10.3390/s18092994
Wang, S., Zhang, X., Wang, J., Tao, T., Xin, K., Yan, H., & Li, S. (2023). Optimal sensor placement for the routine monitoring of urban drainage systems: A re-clustering method. Journal of Environmental Management, 335, 117579. https://doi.org/10.1016/j.jenvman.2023.117579
Zhou, Q., Leng, G., Su, J., & Ren, Y. (2019). Comparison of urbanization and climate change impacts on urban flood volumes: Importance of urban planning and drainage adaptation. Science of the Total Environment, 658, 24–33. https://doi.org/10.1016/j.scitotenv.2018.12.184
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahmad Budi Trisnawan, Sutresna Wati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
