STUDI LITERATUR PENERAPAN INTERNET OF THINGS (IoT) UNTUK SISTEM PERINGATAN DINI BANJIR PADA SMART CITY

  • Adrian Syaputra Univeristas Muhammadiyah Riau
  • Januar Al Amien Univeristas Muhammadiyah Riau
  • Harun Mukhtar Univeristas Muhammadiyah Riau
  • Sunanto Univeristas Muhammadiyah Riau
Keywords: Internet of Things (IoT), Early Warning System, Urban Flooding, Smart City, Systematic Literature Review (SLR).

Abstract

The increasing frequency and intensity of urban flooding due to climate change drives an urgent need for intelligent, real-time, and affordable early warning systems (EWS). Internet of Things (IoT) technology presents itself as a potential solution through wireless sensor networks integrated with cloud platforms and artificial intelligence, but challenges of protocol fragmentation, device power limitations, and cross-vendor interoperability still hamper implementation at a city scale. This study aims to map the development of IoT technology for flood EWS in the Smart City context and identify open research gaps, using the Systematic Literature Review (SLR) method based on the PRISMA framework of 59 selected studies from Scopus and IEEE databases for the period 2020–2025, with five research questions (RQ1–RQ5) covering publication trends, theme structure, future technology directions, the influence of infrastructure architecture, and research gaps in the context of developing countries. The results of the synthesis of the solution taxonomy identify four main domains: (1) LPWAN protocol-based Data Acquisition & Transmission (LoRa and NB-IoT) for low-cost widearea connectivity; (2) Predictive Analytics using Machine Learning models such as LSTM and Random Forest with prediction accuracy up to 94.3%; (3) Multi-channel Warning Dissemination that reduces notification time to under 45 seconds; and (4) Edge Computing infrastructure and energy harvesting for system operational resilience during disasters. The main contribution of this research is an integrated taxonomic framework that conceptually connects these four domains, uncovering patterns of synergy between domains that have not been widely explored in previous literature reviews, while identifying the lack of IoT implementation studies in developing country contexts as a strategic research gap. In conclusion, the IoT ecosystem for flood SPD is evolving from a passive monitoring system to an intelligent predictive platform integrated with Smart City infrastructure, with future development directions towards interoperability standardization, Federated Learning, and Digital Twin integration.

References

[1] Ahmad, F., et al. (2025). IoT-Based Urban Flood Early Warning System with Multi-Channel Alert Dissemination. Sensors, 25(3), 112.
[2] Bao, Y., et al. (2024). A Comprehensive Review of IoT Applications in Flood Monitoring and Early Warning. IEEE Internet of Things Journal, 11(2), 2450–2468. [3] Chen, W., et al. (2024). LoRa-Based Flood Monitoring Network for Low-Infrastructure Urban Areas in Southeast Asia. Sensors, 24(8), 2541.
[4] Devi, R., & Patel, S. (2025). Ultrasonic Water Level Sensor Arrays for Real-Time Flood Detection in Urban Drainage Systems. Applied Sciences, 15(4), 1893.
[5] Fernandez, G., et al. (2024). LPWAN Technologies for IoTBased Flood Early Warning: A Comparative Analysis of LoRa, NB-IoT, and Sigfox. IEEE Access, 12, 34512–34529.
[6] Garcia, M., et al. (2025). Radar Level Sensors in Smart Flood Monitoring Infrastructure: Performance Under Extreme Weather Conditions. Sensors, 25(7), 2198.
[7] Hassan, K., et al. (2024). Solar-Powered IoT Sensor Nodes for Resilient Flood Monitoring in Power-Constrained
Environments. Sustainability, 16(9), 3754.
[8] Ibrahim, A., et al. (2024). Multi-Tier IoT Architecture for Simultaneous Multi-Zone Urban Flood Monitoring Using AWS IoT. IEEE Internet of Things Journal, 11(5), 8901–8916.
[9] Jha, P., & Mishra, A. (2025). NB-IoT Deployment for Flood Early Warning in Rural-Urban Fringe Areas: A Case Study. Smart Cities, 8(1), 45.
[10] Kumar, R., et al. (2024). Edge-Cloud Hybrid Architecture for Low-Latency Flood Sensor Data Processing. Future Generation Computer Systems, 155, 287–301.
[11] Lee, J., et al. (2025). Zigbee-Based Wireless Sensor Network for Urban Flood Detection with Sub-2-Second Transmission Latency. Sensors, 25(11), 3412.
[12] Li, X., et al. (2025). Cloud-Mobile Integration for Sub-45Second Flood Warning Dissemination in Dense Urban Areas. IEEE Internet of Things Journal, 12(3), 5621–5635.
[13] Martinez, C., et al. (2024). MQTT and CoAP Protocol Efficiency Comparison for Bandwidth-Constrained IoT Flood Monitoring Systems. Computers, Environment and Urban Systems, 108, 102083.
[14] Nguyen, T., et al. (2024). CNN-Satellite-IoT Data Fusion for High-Resolution Urban Flood Inundation Mapping. Remote Sensing, 16(14), 2673.
[15] Okafor, E., et al. (2025). Crowdsourcing Mobile App Integration with IoT Sensor Networks for Participatory Flood Monitoring. International Journal of Disaster Risk Reduction, 98, 104122.
[16] Park, H., et al. (2024). Random Forest Multi-Level Flood Risk Classification from Real-Time IoT Sensor Data. Water, 16(12), 1687.
[17] Rahman, M., et al. (2025). NB-IoT vs. LoRa for Wide-Area Flood Early Warning: Coverage, Power, and Cost Analysis. IEEE Access, 13, 45823–45841.
[18] Silva, A., et al. (2025). LSTM-Based Water Level Prediction for Urban Flood Early Warning: 94.3% Accuracy at 6-Hour Horizon. Journal of Hydrology, 634, 131987. [19] Tan, B., et al. (2025). Edge Computing for 73% Latency Reduction in Distributed IoT Flood Sensor Networks. IEEE Internet of Things Journal, 12(6), 11234–11249.
[20] Wang, Z., et al. (2024). Ensemble Machine Learning for Real-Time Flood Risk Assessment from Multi-Parameter IoT Sensor Streams. Natural Hazards and Earth System Sciences, 24(3), 945–962.
[21] Zhao, L., et al. (2024). Fog Computing Architecture for Reliable Flood Warning Data Processing Under Infrastructure Failure. Environmental Modelling & Software, 181, 106189.
[22] Afrianto, I., et al. (2025). IoT-Driven Smart City Flood Resilience: A Framework for Integrated Sensor-to-Dashboard Architecture. IEEE Access, 13, 62341–62358.

[23] Brown, K., et al. (2025). Open-Source Cloud IoT Platforms for Municipal Flood Early Warning: A Scalability Benchmark. Smart Cities, 8(2), 78.
[24] Chen, H., & Liu, Y. (2024). Semantic Middleware for IoT Interoperability in Heterogeneous Flood Monitoring Ecosystems. Journal of Cleaner Production, 412, 137387.
[25] Djenouri, Y., et al. (2025). Adaptive Consensus Protocol for Fault-Tolerant IoT Flood Sensor Networks Under Extreme Weather. Sensors, 25(15), 4789.
[26] Gupta, A., et al. (2024). Distributed Edge Intelligence for Real-Time Urban Flood Detection Without Cloud Dependency. Computers, Environment and Urban Systems, 110, 102098.
[27] Hassan, M., et al. (2024). Physics-Informed Neural Networks for Hydrologically Consistent Flood Prediction from IoT Data. Environmental Modelling & Software, 183, 106212.
[28] Kim, J., et al. (2025). Transformer-Based Sequential Model for Long-Horizon River Stage Forecasting Using IoT Monitoring Data. Journal of Hydrology, 638, 132145.
[29] Lopez, R., et al. (2025). 5G-Enabled Massive IoT Deployment for City-Scale Real-Time Flood Monitoring. IEEE Internet of Things Journal, 12(9), 18723–18739.
[30] Mueller, B., et al. (2025). Digital Twin Integration with IoT Networks for Predictive Urban Flood Management. Smart Cities, 8(3), 125.
[31] Nguyen, L., et al. (2024). CoAP-Based Lightweight IoT Protocol for Energy-Efficient Flood Sensor Communication. Applied Sciences, 14(19), 8934.
[32] Obi, C., et al. (2025). Federated Learning for PrivacyPreserving Distributed Flood Prediction Across IoT Edge Nodes. IEEE Access, 13, 87654–87671.
[33] Park, S., et al. (2024). Gradient Boosting Ensemble for Multi-Class Urban Flood Severity Classification from IoT Sensor Fusion. Water, 16(18), 2634.
[34] Qin, Y., et al. (2025). Piezoelectric Energy Harvesting for Self-Powered IoT Flood Sensors in Remote Urban Drainage Networks. Sustainability, 17(4), 1567.
[35] Rodriguez, M., et al. (2024). Solar-Piezoelectric Hybrid Energy System for Perpetual IoT Flood Monitoring Node Operation. Sensors, 24(22), 7312.
Published
2026-08-29
How to Cite
Adrian Syaputra, Januar Al Amien, Harun Mukhtar, & Sunanto. (2026). STUDI LITERATUR PENERAPAN INTERNET OF THINGS (IoT) UNTUK SISTEM PERINGATAN DINI BANJIR PADA SMART CITY. EDU RESEARCH, 7(2), 8970-8984. https://doi.org/10.47827/jer.v7i2.3577
Section
Articles