Sistem Akuisisi Data Debit Air Sungai Berbasis IoT Menggunakan Sensor Aliran Air dengan Random Forest Regression dan XGBoost Regression
Abstract
Pemantauan debit air sungai merupakan komponen kritis dalam sistem peringatan dini banjir dan pengelolaan sumber daya air. Penelitian ini merancang dan mengimplementasikan sistem akuisisi data debit air sungai berbasis Internet of Things (IoT) menggunakan sensor aliran air YF-S201 yang terintegrasi dengan mikrokontroler ESP32, serta menerapkan dua algoritma regresi machine learning, yaitu Random Forest Regression (RF) dan XGBoost Regression (XGB), untuk memprediksi debit satu langkah ke depan. Dataset yang digunakan terdiri dari 1.488 rekaman dengan interval 30 menit sepanjang bulan Juli 2025, mencakup variabel FlowRate, Velocity, WaterLevel, DebitRiver, Rainfall, Temperature, serta fitur temporal dan fitur lag. Data dibagi secara kronologis menjadi tiga subset: pelatihan (70%, n = 1.042), validasi (15%, n = 223), dan uji (15%, n = 222). Hasil evaluasi menunjukkan bahwa XGBoost Regression mencapai kinerja yang lebih unggul dengan nilai MAE = 0,1692 m³/s, RMSE = 0,3429 m³/s, MAPE = 5,15%, dan R² = 0,9924 dibandingkan dengan Random Forest dengan MAE = 0,1791 m³/s, RMSE = 0,3498 m³/s, MAPE = 5,58%, dan R² = 0,9921. Kedua model menunjukkan akurasi tinggi (R² > 0,99), dengan 82,9–85,6% prediksi menghasilkan absolute error di bawah 0,25 m³/s. XGBoost memberikan prediksi yang lebih presisi pada kondisi normal hingga sedang, sementara keduanya mengalami peningkatan error pada debit puncak ekstrem (> 10 m³/s). Sistem ini berpotensi menjadi infrastruktur dasar pemantauan sungai secara cerdas dan terotomasi untuk mendukung sistem peringatan dini banjir.
Keywords
Full Text:
PDFReferences
BNPB, “Data Bencana Indonesia 2024.” Pusat Data, Informasi, dan Komunikasi Kebencanaan (Pusdatinkom) BNPB, Indonesia, Jun. 13, 2025. https://bnpb.go.id/
A. Fahmi, A. Amali, and A. Badruzzaman, "Prediksi Curah Hujan Jawa Barat Menggunakan Algoritma Machine Learning: Analisis Komparatif Berbasis Data Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) 2024," Journal of Information System Research (JOSH), vol. 7, no. 2, pp. 438–446, Jan. 2026, doi: 10.47065/josh.v7i2.9018.
E. M. Hasiri and H. N. Allia, “Peringatan Dini Banjir Menggunakan Multi Sensor Pada Prototype Aliran Sungai Berbasis Internet of Things,” JIU, vol. 12, no. 1, pp. 60–69, Jun. 2023, doi: 10.55340/jiu.v12i1.1299.
D. Feng, K. Fang, and C. Shen, “Enhancing Streamflow Forecast and Extracting Insights Using Long‐Short Term Memory Networks With Data Integration at Continental Scales,” Water Resources Research, vol. 56, no. 9, p. e2019WR026793, Sep. 2020, doi: 10.1029/2019WR026793.
M. N. Ciner et al., “The Forecast of Streamflow through Göksu Stream Using Machine Learning and Statistical Methods,” Water, vol. 16, no. 8, p. 1125, Apr. 2024, doi: 10.3390/w16081125.
L. T. Pham, L. Luo, and A. Finley, “Evaluation of random forests for short-term daily streamflow forecasting in rainfall- and snowmelt-driven watersheds,” Hydrol. Earth Syst. Sci., vol. 25, no. 6, pp. 2997–3015, Jun. 2021, doi: 10.5194/hess-25-2997-2021.
H. Solanki, U. Vegad, A. Kushwaha, and V. Mishra, “Improving Streamflow Prediction Using Multiple Hydrological Models and Machine Learning Methods,” Water Resources Research, vol. 61, no. 1, p. e2024WR038192, Jan. 2025, doi: 10.1029/2024WR038192.
A. Basuki, F. D. Saputra, D. Priantono, and B. Purwahyudi, “Monitoring Ketinggian Air Sungai Berbasis Internet of Things (IoT),” I, vol. 3, no. 1, pp. 1–9, May 2025, doi: 10.54732/i.v3i1.1220.
E. T. De Camargo et al., “Low-Cost Water Quality Sensors for IoT: A Systematic Review,” Sensors, vol. 23, no. 9, p. 4424, Apr. 2023, doi: 10.3390/s23094424.
M. Miller, A. Kisiel, D. Cembrowska-Lech, I. Durlik, and T. Miller, “IoT in Water Quality Monitoring—Are We Really Here?,” Sensors, vol. 23, no. 2, p. 960, Jan. 2023, doi: 10.3390/s23020960.
C. Z. Zulkifli et al., “IoT-Based Water Monitoring Systems: A Systematic Review,” Water, vol. 14, no. 22, p. 3621, Nov. 2022, doi: 10.3390/w14223621.
S. F. Nasution, H. Harmadi, S. Suryadi, and B. Widiyatmoko, “Development of River Flow and Water Quality Using IoT-based Smart Buoys Environment Monitoring System,” J. Ilmu Fis., vol. 16, no. 1, pp. 1–12, Sep. 2023, doi: 10.25077/jif.16.1.1-12.2024.
L. M. Pires and J. Gomes, “River Water Quality Monitoring Using LoRa-Based IoT,” Designs, vol. 8, no. 6, p. 127, Nov. 2024, doi: 10.3390/designs8060127.
L. M. F. Vieira, S. B. Soares, G. F. Loureiro, T. A. Luiz, and T. F. A. Ferreira, “Development and calibration of a low-cost flow meter using a YF-S201 sensor connected to an Arduino Uno,” Cad. Pedagógico, vol. 22, no. 12, p. e20743, Oct. 2025, doi: 10.54033/cadpedv22n12-152.
M. A. Rahu, A. F. Chandio, K. Aurangzeb, S. Karim, M. Alhussein, and M. S. Anwar, “Toward Design of Internet of Things and Machine Learning-Enabled Frameworks for Analysis and Prediction of Water Quality,” IEEE Access, vol. 11, pp. 101055–101086, 2023, doi: 10.1109/ACCESS.2023.3315649.
N. Evitarina and T. D. Y. Utami, “Prediksi Potensi Banjir Menggunakan Machine Learning Dengan Pendekatan XGBoost Dan Logistic Regression,” JSAI (Journal Scientific and Applied Informatics), vol. 9, no. 1, pp. 59–65, Jan. 2026, doi: 10.36085/jsai.v9i1.9867.
R. Szczepanek, “Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost,” Hydrology, vol. 9, no. 12, p. 226, Dec. 2022, doi: 10.3390/hydrology9120226.
R. Hao and Z. Bai, “Comparative Study for Daily Streamflow Simulation with Different Machine Learning Methods,” Water, vol. 15, no. 6, p. 1179, Mar. 2023, doi: 10.3390/w15061179.
N. Kedam, D. K. Tiwari, V. Kumar, K. M. Khedher, and M. A. Salem, “River stream flow prediction through advanced machine learning models for enhanced accuracy,” Results in Engineering, vol. 22, p. 102215, Jun. 2024, doi: 10.1016/j.rineng.2024.102215.
Ö. Terzi, E. U. Küçüksille, T. Baykal, and E. D. Taylan, “Deep and machine learning for daily streamflow estimation: a focus on LSTM, RFR and XGBoost,” Water Practice & Technology, vol. 18, no. 10, pp. 2401–2414, Oct. 2023, doi: 10.2166/wpt.2023.144.
W. Fang et al., “An evaluation of random forest-based input variable selection methods for one-month-ahead streamflow forecasting,” Sci Rep, vol. 14, no. 1, p. 29766, Nov. 2024, doi: 10.1038/s41598-024-81502-y.
D. M. Moges et al., “Streamflow Prediction with Time-Lag-Informed Random Forest and Its Performance Compared to SWAT in Diverse Catchments,” Water, vol. 16, no. 19, p. 2805, Oct. 2024, doi: 10.3390/w16192805.
R. Akbar, M. Faturrahman, F. Januarsyah, and S. Lestari, “Implementasi Alat Pendeteksi Ketinggian Air Menggunakan Arduino Via Telegram Berbasis IoT Pada RT 01 Malaka Jaya,” INTECOMS, vol. 8, no. 1, pp. 273–279, Feb. 2025, doi: 10.31539/intecoms.v8i1.14495.
M. A. L. Badaly, J. A. Milanesta, and M. A. Hidayatulloh, “Sistem IoT Pemantauan Ketinggian Air Sungai Berbasis Arduino dan Bot Telegram,” Seminar Nasional Teknologi & Sains (STAINS), DOI : 10.29407/7nphw358 , vol. 5, 2026.
DOI: https://doi.org/10.55340/jiu.v15i1.2686
Refbacks
- There are currently no refbacks.
__________________________________________________________________________________________________________________________________________________
SK Accreditation No. 286/DST/C3/HM.01.00/2026 Tanggal 7 April 2026
Editorial Address :
Program Studi Teknik Informatika, Fakultas Teknik, Universitas Dayanu Ikhsanuddin Jl. Dayanu Ikhsanuddin no.124 Baubau, Sulawesi Tenggara
Jurnal Informatika by Program Studi Teknik Informatika, Fakultas Teknik, Universitas Dayanu Ikhsanuddin Baubau, Indonesia is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Based on work at https://ejournal.unidayan.ac.id/index.php/JIU