Pemodelan Prediksi Curah Hujan Bulanan Menggunakan LSTM Berbasis Deret Waktu di Provinsi Sumatera Utara
Abstract
Rainfall prediction is important for supporting hydrometeorological disaster mitigation and data-based decision making. This study aims to model monthly rainfall prediction using Long Short-Term Memory (LSTM) based on time series data in North Sumatra Province, with monthly weather data from Medan City as the study case. The data used cover the period from 2010 to 2025 and include rainfall, rainy days, temperature, humidity, wind speed, and air pressure. The research stages consist of data validation, exploratory data analysis, threshold determination for high rainfall, feature engineering, chronological data splitting, scaling, LSTM model training, baseline comparison, backtesting, cross validation, and rainfall prediction for 2026-2027. The best LSTM configuration used 64 units, dropout 0.1, learning rate 0.0005, batch size 8, and weighted MSE loss function. Evaluation on the 2025 test set produced MAE of 75.30 mm, RMSE of 89.34 mm, MAPE of 64.23%, and R2 of 0.3703. The LSTM model outperformed the baseline models based on MAE, RMSE, and R2. Forecast results indicate higher rainfall tendencies at the end of 2026 and 2027, especially in October, November, and December.
References
Akbar, A. A., Darmawan, Y., Wibowo, A., & Rahmat, H. K. (2024). Accuracy assessment of monthly rainfall predictions using seasonal ARIMA and long short-term memory (LSTM). Journal of Computer Science and Engineering (JCSE), 5(2), 99–114. https://doi.org/10.36596/jcse.v5i2.843
Aslam, F. M., & Afghani, F. A. (2024). Comparing monthly rainfall prediction in West Sumatra using SARIMA, ETS, LSTM, and XGBoosting methods. Indonesian Journal of Applied Statistics, 7(1), 14–26. https://doi.org/10.13057/ijas.v7i1.83187
Badan Meteorologi, Klimatologi, dan Geofisika. (2024). Hujan lebat menyebabkan banjir dan gangguan transportasi di Kota Medan. BMKG.
Badan Pusat Statistik Provinsi Sumatera Utara. (2025). Jumlah curah hujan dan hari hujan menurut stasiun BMKG di Provinsi Sumatera Utara. BPS Provinsi Sumatera Utara.
Dhuha, M. A. S., Saputra, A. H., Kristianto, A., & Mulya, A. (2024). Impact-Based Forecasting (IBF) untuk mendukung manajemen risiko banjir di kawasan Jabodetabek. Jurnal Ilmu Lingkungan, 22(5), 1159–1173. https://doi.org/10.14710/jil.22.5.1159-1173
Gaol, G. M. L., Syafrullah, M., & Supardi, S. (2024). Comparison of monthly rainfall prediction using long short term memory and multi layer perceptron methods in South Tangerang City. Jurnal Sisfokom (Sistem Informasi dan Komputer), 13(2), 293–297. https://doi.org/10.32736/sisfokom.v13i2.2149
Jannah, A. N., Fauji, A., & Wiguna, M. S. (2022). Perbandingan model statistika dan machine learning dalam memprakirakan curah hujan dasarian. Jurnal Meteorologi dan Geofisika, 23(2), 75–86.
Jansen, D., Handhayani, T., & Hendryli, J. (2023). Penerapan metode long short-term memory dalam memprediksi data meteorologi di Kalimantan Timur. Simtek: Jurnal Sistem Informasi dan Teknik Komputer, 8(2), 348–352. https://doi.org/10.51876/simtek.v8i2.202
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(11), 6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Misshuari, I. W., Kurniyaningrum, E., & Saily, R. (2023). Studi peramalan curah hujan menggunakan metode ARIMA di Daerah Asahan. Construction Engineering and Sustainable Development, 6(2), 22–28. https://doi.org/10.25105/cesd.v6i2.18815
Nazeri Tahroudi, M. (2025). Comprehensive global assessment of precipitation trend and pattern variability considering their distribution dynamics. Scientific Reports, 15(1), Article 22458. https://doi.org/10.1038/s41598-025-06050-5
Pebralia, J. (2022). Analisis curah hujan menggunakan machine learning metode regresi linier berganda berbasis Python dan Jupyter Notebook. Jurnal Ilmu Fisika dan Pembelajarannya, 6(2), 23–30. https://doi.org/10.19109/jifp.v6i2.13958
Prasetyo, H. R., Palupi, I., & Wahyudi, B. A. (2023). Prediksi menggunakan model fuzzy time series: Studi kasus curah hujan di Kabupaten Bandung. LOGIC: Jurnal Penelitian Informatika, 1(1), 8–13. https://doi.org/10.25124/logic.v1i1.6405
Rafhida, S. A., & Najib, M. K. (2026). Pemodelan curah hujan bulanan Jakarta Pusat menggunakan neural network long short-term memory (LSTM). Jurnal Sains Matematika dan Statistika, 12(2). https://doi.org/10.24014/t1b6xb48
Rizki, M., Basuki, S., & Azhar, Y. (2020). Implementasi deep learning menggunakan arsitektur long short-term memory (LSTM) untuk prediksi curah hujan Kota Malang. Jurnal Repositor, 2(3), 331–338. https://doi.org/10.22219/repositor.v2i3.470
Ruslana, Z. N., Tresnawati, R., Rosyidah, R., Harmoko, I. W., & Siswanto, S. (2021). Reliabilitas prediksi curah hujan dasarian pada kejadian curah hujan ekstrim pemicu banjir 26 Oktober 2020 di Kebumen: Model statistik (HyBMG) versus model dinamik (ECMWF). Jurnal Geosains dan Teknologi, 4(2), 83–100. https://doi.org/10.14710/jgt.4.2.2021.83-100
Sari, J. R., Hairani, H., & Latif, K. A. (2024). Perbandingan model gated recurrent unit dan long short-term memory untuk prediksi curah hujan. Indonesian Journal of Computer Science and Research, 2(2), 111–123. https://doi.org/10.59095/ijcsr.v2i2.77
Sianturi, A. H., Panjaitan, E. J. B., Kaban, F. A. B., Panggabean, I. F. J., Johana, N. L., Bangun, S. J., & Panggabean, S. (2025). Analisis probabilistik untuk prediksi cuaca di Kota Medan dan Kabupaten Deli Serdang (menggunakan metode Rantai Markov). Griya Journal of Mathematics Education and Application, 5(4). https://doi.org/10.29303/griya.v5i4.970
Selle, N., Yudistira, N., & Dewi, C. (2022). Perbandingan prediksi penggunaan listrik dengan menggunakan metode long short-term memory (LSTM) dan recurrent neural network (RNN). Jurnal Teknologi Informasi dan Ilmu Komputer, 9(1), 155–162. https://doi.org/10.25126/jtiik.202295585
Suhadi, S., Mabruroh, F., Wiyanto, A., & Ikra, I. (2023). Analisis fenomena perubahan iklim terhadap curah hujan ekstrim. OPTIKA: Jurnal Pendidikan Fisika, 7(1), 94–100. https://doi.org/10.37478/optika.v7i1.2738
Supriatna, D., Anggai, S., & Tukiyat, T. (2025). Analisis prediksi curah hujan di Kota Tangerang menggunakan metode LSTM dan GRU. Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence), 5(2), 119–131. https://doi.org/10.55382/jurnalpustakaai.v5i2.1068
Tampubolon, K. (2018). Aplikasi sistem informasi geografis (SIG) sebagai penentuan kawasan rawan banjir di Kota Medan. Jurnal Pembangunan Perkotaan, 6(2), 63–68. http://ejpp.balitbang.pemkomedan.go.id/index.php/JPP
Triwahyu, M., & Firmansyah, M. R. (2026). Pemodelan SARIMA terhadap curah hujan bulanan di Provinsi Jawa Barat. Griya Journal of Mathematics Education and Application, 6(1), 272–283. https://doi.org/10.29303/griya.v6i1.1017
Wijayanto, A., Sugiharto, A., & Santoso, R. (2024). Identifikasi dini curah hujan berpotensi banjir menggunakan algoritma long short-term memory (LSTM) dan Isolation Forest. Jurnal Teknologi Informasi dan Ilmu Komputer, 11(3), 637–646. https://doi.org/10.25126/jtiik.938718
