Internet of Things and Fuzzy Logic-based Flood Early Warning System Integrated with a Telegram Bot for Urban Disaster Mitigation

Muhamad Wisnu Alfiansyah, Istin Fitriana Aziza, Zulkipli Zulkipli, Nabila Wahyu Khairunnisa

Abstract


Flood events require environmental monitoring systems capable of rapidly providing information when risk levels change. This study develops an Internet of Things (IoT)-based prototype for early flood risk detection using four input parameters: water surface distance, water flow rate, rainfall, and wind speed. Data from the four sensors are collected by a Raspberry Pi 5 and processed using the Mamdani Fuzzy Logic method to generate a risk score ranging from 0% to 100%, which is classified into four risk levels: Safe, Caution, Alert, and Danger. Calibration results yielded Mean Absolute Percentage Error (MAPE) values of 0.713% for the ultrasonic sensor, 1.043% for the anemometer, 4.185% for the rain gauge, and 4.553% for the flow sensor. The Mamdani Fuzzy Logic method was evaluated using 25 test datasets, comprising prototype sensor readings and simulation scenarios designed to expand the range of input combinations. Validation of the system implementation using ten datasets produced a MAPE of 0.0233% between manual calculations and system outputs, with no discrepancies in risk classification. This MAPE value indicates the consistency of the Mamdani Fuzzy Logic implementation rather than its accuracy in detecting actual flood events. The processed results can be stored in Firebase Realtime Database, transmitted via MQTT, and delivered to users through a Telegram Bot in the form of sensor readings, risk scores, and risk classifications. The test results demonstrate that multi-sensor data acquisition, Mamdani Fuzzy Logic processing, data storage, and risk information delivery have been successfully integrated into a single early flood risk detection prototype. Further field testing under real-world conditions is required to evaluate the system's performance during actual flood events.

Keywords


flood early warning; Internet Of Things; mamdani fuzzy logic; multi-sensor; telegram bot

Full Text:

PDF

References


Badan Nasional Penanggulangan Bencana (BNPB), “Data Bencana Nasional Indonesia 2024,” 2024.

U. O. for D. R. Reduction; and W. M. Organization, “Global Status of Multi-Hazard Early Warning Systems,” 2025.

N. Byaruhanga, D. Kibirige, and S. Gokool, “Evolution of Flood Prediction and Forecasting Models for Flood Early Warning Systems : A Scoping Review,” Water, Vol. 16, No. 3, pp. 1–29, 2024.

A. Akbar, M. Clinton, and I. F. Ashari, “Analysis and Implementation Monitoring Flood System based on IoT using Sugeno Fuzzy Logic,” Komputika J. Sist. Komput., Vol. 12, No. 1, pp. 25–34, 2023, DOI: 10.34010/komputika.v12i1.7089.

M. I. Dwiyanto, A. E. Wardoyo, and D. L. Pater, “Rancang Bangun Sistem Peringatan Dini Bencana Banjir berbasis IoT menggunakan Metode Fuzzy Sugeno,” J. Sist. dan Teknol. Inf. Indones., Vol. 10, No. 1, pp. 62–72, 2025.

E. Alimudin, A. Sumardiono, and Z. Zaenurohman, “Implementation of Fuzzy Logic for Early Warning System for Flood Disaster in Cilacap District,” J. Ecotipe (Electronic, Control. Telecommun. Information, Power Eng., Vol. 12, No. 1, pp. 1–10, 2025, DOI: 10.33019/jurnalecotipe.v12i1.4529.

M. I. Zakaria, W. A. Jabbar, and N. Sulaiman, “Internet of Things and Cyber-Physical Systems Development of a Smart Sensing Unit for LoRaWAN-based IoT flood Monitoring and Warning System in Catchment Areas,” Internet Things Cyber-Physical Syst., Vol. 3, No. May, pp. 249–261, 2023, DOI: 10.1016/j.iotcps.2023.04.005.

W. T. Sung, I. V. Devi, and S. J. Hsiao, “Early Warning of Impending Flash Flood based on a IoT,” EURASIP J. Wirel. Commun. Netw., pp. 1–18, 2022, DOI: 10.1186/s13638-022-02096-5.

H. Hambali, A. Akbar, and A. Yani, “Early Warning System for Flood in Gunungsari District based on IoT With Telegram Bot as a Warning Message Sender,” J. Pilar Nusa Mandiri, Vol. 18, No. 2, pp. 173–178, 2022, DOI: 10.33480/pilar.v18i2.3711.

P. A. Wijaya Ariyanto and R. Soelistijadi, “Implementasi NodeMCU sebagai Sistem Deteksi Dini Bahaya Banjir di Purwodadi berbasis Web dengan Notifikasi Bot Telegram,” J. Teknol. dan Manaj. Inform., Vol. 8, No. 2, pp. 64–73, 2022, DOI: 10.26905/jtmi.v8i2.7902.

A. D. Rakhman, I. K. Somawirata, and M. Ardita, “Flood Early Warning System with Notification using Telegram Bot based on IoT System,” J. Electr. Eng. Comput., Vol. 7, No. 1, pp. 206–216, 2025, DOI: 10.33650/jeecom.v7i1.10850.

P. Ponukumati and S. K. Regonda, “Press Web-Messaging-based Dissemination of Urban Rainfall and Flood Information : A Telegram Bot Framework TI TI ES,” npj Nat. Hazards, No. February, pp. 1–22, 2026.

K. Widya Kayohana, I. N. Switrayana, and M. Wisnu Alfiansyah, “Analisis Kebutuhan Pengembangan Prototype Mitigasi Bencana Banjir berbasis Internet of Things (IoT) di Desa Sedau,” JATI (Jurnal Mhs. Tek. Inform., Vol. 7, No. 5, pp. 3541–3548, 2024, DOI: 10.36040/jati.v7i5.7957.

I. Irawan, Z. Azmi, and M. Hutasuhut, “IoT pada Sistem Monitoring Kecepatan Air Sungai Babura sebagai Peringatan Dini Banjir berbasis Node Mcu,” J. Sist. Komput. Triguna Dharma (JURSIK TGD), Vol. 3, No. 3, pp. 80–87, 2024, DOI: 10.53513/jursik.v3i3.9289.

A. Adriansyah, M. H. Budiutomo, H. Hermawan, and R. I. Andriani, “Design of Water Level Detection Monitoring System using Fusion Sensor based on Internet of Things ( IoT ),” SINERGI, Vol. 28, No. 1, pp. 191–198, 2024.

R. Kridalukmana, D. Eridani, R. Septiana, and I. P. Windasari, “Enhancing River Flood Prediction in Early Warning Systems using Fuzzy Logic-based Learning,” Int. J. Eng. Technol. Innov., Vol. 14, No. 4, pp. 434–450, 2024, DOI: 10.46604/ijeti.2024.13426.

A. Wahid, J. M. Parenreng, W. Chandra, K. Kusnandar, and P. Dani, “Telegram Bot-based Flood Early Warning System with WSN Integration,” Ilk. J. Ilm., Vol. 16, No. 2, pp. 151–160, 2024.




DOI: https://doi.org/10.32520/stmsi.v15i11.6904

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.