Pendeteksian Dini pada Potensi Banjir dengan Berbasis Internet of Things Menggunakan Algoritma Random Forest
DOI:
https://doi.org/10.30865/jurikom.v13i2.9644Keywords:
Flood Prediction, Internet Of Things, Random Forest, Hydrological Data, Early Warning SystemAbstract
Flood is a natural disaster that frequently occurs and causes significant material and social losses. Conventional flood monitoring systems are generally reactive and rely on threshold-based approaches, which limits their effectiveness in supporting early detection. This study proposes an Internet of Things (IoT)-based early flood detection system using the Random Forest algorithm. The developed system collects hydrological data, including water level and flow velocity, through IoT sensors that periodically transmit data to a server for further processing. The collected data are then aggregated and classified into flood and non-flood conditions using a Random Forest model. Model performance is evaluated using accuracy, precision, recall, f1-score, confusion matrix, and 5-fold cross-validation. Experimental results indicate that the proposed model achieves an accuracy of 97.26% with a mean cross-validation score of 0.9863. However, the recall for flood events remains limited due to data imbalance and the relatively small number of flood occurrences. Despite these limitations, the proposed system demonstrates potential to support the development of early flood warning systems and can be further improved by incorporating longer and more diverse historical datasets.
References
[1] M. S. Sumalatha, P. M. Mathews, H. Mohan, T. Chippy, and P. S. Nair, “Real-Time Flood Risk Mapping Using ML And Iot Sensor Data,” vol. 11, no. 24, pp. 911–920, 2025.
[2] H. S. Yani Dwi Yulianti, Miftahul Huda, “Adaptive Governance dalam Mitigasi Bencana Banjir di Kabupaten Bojonegoro,” Relig. Educ. Soc. Laa Roiba J., vol. 6, pp. 1974–1984, 2024, doi: 10.47476/reslaj.v6i3.5870.
[3] A. Alamsyah and E. Wahyudi, “Transformasi Digital untuk Mitigasi Banjir : Optimalisasi Sistem Informasi di Jawa Barat,” vol. 01, no. 2, pp. 50–62, 2024.
[4] A. Rachmawardani and S. K. Wijaya, “Prediksi Banjir menggunakan ANFIS-PCA sebagai Peringatan Dini Bencana Banjir,” vol. 12, no. 2, pp. 335–351, 2024.
[5] M. I. Drilanang, Z. Indra, A. P. Walidin, and T. S. Warman, “Development of an Adaptive Hybrid Weather Prediction Model Based on Pattern Classification and Deep Learning for Disaster Mitigation in Indonesia,” vol. 4, no. 3, pp. 921–931, 2025.
[6] S. K. W. A. Rachmawardani, Giarno, H. A. Nugroho, Suharni, D. Sucahyono, Hariyanto, “State of the Art of Remote Sensing in Flood Early Warning System: Review Article,” vol. 5, no. Smbpsb, pp. 108–117, 2022.
[7] T. S. Famuji, E. E. Citra, and S. Mutmainah, “Analisis Perancangan Sistem Informasi Pendukung Keputusan untuk Mitigasi Bencana Alam Berbasis Data Real-Time,” J. Comput. Sci. Informatics, vol. Vol.2, No., 2025, doi: 10.34304/scientific.v2i1.339.
[8] K. C. A. & N. Sawiji, “Penerapan Teknologi Ramah Lingkungan Dalam Pemetaan Genangan Air Pada Wilayah Rawan Banjir Menggunakan Google Earth Engine ( Studi Kasus : Kabupaten Denak),” vol. 1, no. 1, pp. 45–56, 2025.
[9] I. P. Bagus, R. Sugita, N. N. Pujianiki, I. P. Gustave, and S. Pariartha, “Rainfall Data as an Indicator of Climate Change ( Case Study : Kuta District , Badung Regency ),” vol. 7, no. 02, 2025.
[10] H. M. Farhan S, B. Sitorus and Sitorus, “Rancang Bangun Monitoring Banjir Pada Pintu Air Berbasis IoT,” J. Ilm. Fak. Tek. LIMIT’S, vol. 2, no. 1, pp. 19–27, 2024.
[11] M. Amin and L. I. Burhan, “Integrasi Sensor Low-Cost , Aplikasi Mobile , dan Mekanisme Respons Komunitas : Model Early Warning System untuk Desa Berliterasi Teknologi Rendah,” vol. 1, no. 4, pp. 30–43, 2025, doi: 10.63982/dharmabakti.yp5vf934.
[12] M. Alfidyah, “Pemanfaatan Internet Of Things ( IOT ) Untuk Monitoring Kualitas Air Sebagai Upaya Mendukung Smart City,” vol. 1, no. 1, pp. 8–14, 2025.
[13] M. J. Sitepu and F. Azmi, “Rancang Bangun Monitoring Ketinggian Air Berbasis IoT Untuk Deteksi Dini Banjir Pada Bendungan Sungai Deli,” vol. 10, pp. 1–8, 2025.
[14] M. Feizbahr, N. Brake, H. Arbabkhah, H. H. Asli, and K. Woods, “Flood Susceptibility Mapping Using Machine Learning and Geospatial-Sentinel-1 SAR Integration for Enhanced Early Warning Systems,” pp. 1–30, 2025.
[15] S. Sanjaya, B. Koes, P. Cantik, and A. S. Wardaningrum, “Analisis Derajat Bencana Kekeringan Di Pulau Jawa Akibat Fenomena El-Nino 202,” vol. 4, no. 2, pp. 115–126, 2024, doi: 10.56860/jtsda.v4i1.14.
[16] A. I. Samudra, R. M. Syawal, T. Satrio, and W. Haryono, “Aplikasi Pemantauan dan Prediksi Kadar Kualitas Air Sungai Dengan Algoritma Random Forest Pada Pusat Riset Fotonika,” vol. 4, no. 2, pp. 5376–5387, 2025.
[17] A. Setiawan, R. Handoko, S. Kahfi, and G. Andriyanto, “Pemanfaatan Sistem Pemantauan Tinggi Muka Air Sungai Berbasis Sensor Radar dan Internet Of Things,” vol. 4, no. 2, pp. 28–34, 2025.
[18] and W. W. R. T Ardani, “Analisis Pola Kejadian Bencana Hidrometeorologi Secara Spasial-Temporal Di Kabupaten Klaten Tahun 2018-2023,” 2023.
[19] J. T. Santoso, Cara memanipulasi pembelajaran mesin. Semarang: Yayasan Prima Agus Teknik Bekerja & Universitas Sains dan Teknologi Komputer (Universitas STEKOM).
[20] and H. M. Fauzi, Mushi, “Analisis Penggunaan Model Random Forest dalam Memprediksi Resiko Banjir di Daerah Rawan Bencana Kabupaten Pamekasan,” vol. 11, no. 1, pp. 17–25, 2025.
[21] S. M. Natzir, “Perbandingan Kinerja Model Pembelajaran Mesin dalam Prediksi Banjir menggunakan KNN , Naive Bayes , dan Random Forest,” vol. 14, no. c, pp. 59–64, 2023.
[22] R. A. Aufa, E. Altiarika, A. Pramudyantoro, Y. B. Pratama, and Z. Wahyuzi, “Pengenalan Pola Kasus Potensi Banjir Di Pangkalpinang Dengan Algoritma Random Forest Dan Xgboost Menggunakan Google Earth Engine,” vol. 3, no. 1, pp. 1–6, 2025.
[23] D. Fernanda and A. A. Syukron, “Implementasi Sensor Ultrasonic Untuk Pemantauan Debit Sungai Serayu Sebagai Antisipasi Banjir Berbasis Arduino,” vol. 6, no. 3, pp. 1920–1929, 2025.
[24] R. Agustian, G. P. Dirgantoro, and I. Aristia, “Sistem Kamera Cerdas Pendeteksi kendaraan Salip Kiri Untuk Mengurangi Laka Lantas Berbasis Pembelajaran Mesin,” pp. 1–6, 2025.
[25] M. J. Vikri et al., “Identifikasi Kualitas Beras Berdasarkan Standar Pangan Indonesia Berbasis Electronic Nose,” no. 1, 2025.
