Pengembangan Model Hibrida CNN-Transformer untuk Meningkatkan Akurasi Prediksi Curah Hujan Jangka Pendek di Kota Bogor sebagai Peringatan Dini Bencana Banjir

Ary Setyoko; Agung Budi Santoso; Taswanda Taryo

doi:10.59945/jpnm.v4i4.1598

Authors

Ary Setyoko Universitas Pamulang
Agung Budi Santoso Universitas Pamulang
Taswanda Taryo Universitas Pamulang

DOI:

https://doi.org/10.59945/jpnm.v4i4.1598

Keywords:

CNN-Transformer, Curah Hujan, Deep Learning, Peringatan Dini, Prediksi Hujan

Abstract

Prediksi curah hujan jangka pendek yang presisi diperlukan untuk memperkuat mitigasi banjir di Kota Bogor sebagai wilayah hulu Daerah Aliran Sungai Ciliwung. Penelitian ini mengembangkan model hybrid Convolutional Neural Network (CNN)-Transformer untuk memprediksi curah hujan harian pada horizon H+1 hingga H+3 menggunakan deret waktu meteorologi multivariat periode 2018-2023. Variabel masukan mencakup curah hujan, suhu, kelembaban, tekanan udara, serta arah dan kecepatan angin. Pra-pemrosesan meliputi penanganan nilai hilang, penyaringan pencilan tidak valid, normalisasi, pembentukan sliding window tujuh hari, dan pembagian data kronologis 80:10:10. CNN digunakan untuk mengekstraksi pola lokal, sedangkan Transformer memodelkan dependensi temporal melalui self-attention. Hasil pengujian menunjukkan koefisien determinasi model hybrid sebesar 0,93-0,97, lebih tinggi daripada CNN tunggal sebesar 0,62-0,69 dan Transformer tunggal sebesar 0,67-0,70. Meskipun demikian, diagnostik memperlihatkan underestimation pada hujan sangat lebat karena kejadian ekstrem jarang terwakili dalam data historis. Model ini berpotensi memperkuat prediksi kuantitatif curah hujan sebagai masukan sistem peringatan dini banjir, tetapi kalibrasi khusus untuk kejadian ekstrem tetap diperlukan sebelum penerapan operasional. Analisis feature importance juga menempatkan kelembaban sebagai prediktor dominan, sehingga temuan model tetap selaras dengan proses fisik pembentukan presipitasi tropis lokal Bogor.

References

Ayzel, G., Scheffer, T., & Heistermann, M. (2020). RainNet v1.0: A Convolutional Neural Network for Radar-Based Precipitation Nowcasting. Geoscientific Model Development, 13(6), 2631–2644. https://doi.org/10.5194/gmd-13-2631-2020

Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., & Tian, Q. (2023). Accurate Medium-Range Global Weather Forecasting With 3D Neural Networks. Nature, 619(7970), 533–538. https://doi.org/10.1038/s41586-023-06185-3

Guo, L., Pu, Y., & Zhao, W. (2025). CNN-BiLSTM Daily Precipitation Prediction Based on Attention Mechanism. Atmosphere, 16(3), 333. https://doi.org/10.3390/atmos16030333

Khyber, E., Syaufina, L., & Sunkar, A. (2021). Variability and Time Series Trend Analysis of Rainfall and Temperature in Dramaga Sub-District, Bogor, Indonesia. IOP Conference Series: Earth and Environmental Science, 771(1), 12016. https://doi.org/10.1088/1755-1315/771/1/012016

Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., & Battaglia, P. (2023). Learning Skillful Medium-Range Global Weather Forecasting. Science, 382(6677), 1416–1421. https://doi.org/10.1126/science.adi2336

Liu, H., Fung, J. C. H., Lau, A. K. H., & Li, Z. (2024). Enhancing Quantitative Precipitation Estimation of NWP Model With Fundamental Meteorological Variables and Transformer Based Deep Learning Model. Earth and Space Science, 11(4), e2023EA003234. https://doi.org/10.1029/2023EA003234

Liu, J., Shen, C., O’Donncha, F., Song, Y., Zhi, W., Beck, H. E., Bindas, T., Kraabel, N., & Lawson, K. (2025). From RNNs to Transformers: Benchmarking Deep Learning Architectures for Hydrologic Prediction. Hydrology and Earth System Sciences, 29, 6811–6828. https://doi.org/10.5194/hess-29-6811-2025

Liu, S., Liu, K., Wang, Z., Liu, Y., Bai, B., & Zhao, R. (2025). Investigation of a Transformer-Based Hybrid Artificial Neural Networks for Climate Data Prediction and Analysis. Frontiers in Environmental Science, 12, 1464241. https://doi.org/10.3389/fenvs.2024.1464241

Pavithran, M. S., Sreeram, B., Pillai, A. V, & Jothi, R. (2025). Multi-Scale Weather Forecasting Using Deep Learning Architectures With Chennai Climate Data. IEEE Access, 13, 207303–207319. https://doi.org/10.1109/ACCESS.2025.3640667

Piran, M. J., Wang, X., Kim, H. J., & Kwon, H. H. (2024). Precipitation Nowcasting Using Transformer-Based Generative Models and Transfer Learning for Improved Disaster Preparedness. International Journal of Applied Earth Observation and Geoinformation, 132, 103962. https://doi.org/10.1016/j.jag.2024.103962

Pölz, A., Blaschke, A. P., Komma, J., Farnleitner, A. H., & Derx, J. (2024). Transformer Versus LSTM: A Comparison of Deep Learning Models for Karst Spring Discharge Forecasting. Water Resources Research, 60(4), e2022WR032602. https://doi.org/10.1029/2022WR032602

Puspasari, R. L., Yoon, D., Kim, H., & Kim, K.-W. (2023). Machine Learning for Flood Prediction in Indonesia: Providing Online Access for Disaster Management Control. Economic and Environmental Geology, 56(1), 65–73. https://doi.org/10.9719/EEG.2023.56.1.65

Rachmawardani, A., Kurniawan, B., Wijaya, S. K., Sopaheluwakan, A., & Sinambela, M. (2025). Hybrid Machine Learning for Flood Prediction: Comparing CHIRPS Satellite and Ground Station Data. Journal of Water and Land Development, 64, 87–99. https://doi.org/10.24425/jwld.2025.153520

Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., & Mohamed, S. (2021). Skilful Precipitation Nowcasting Using Deep Generative Models of Radar. Nature, 597(7878), 672–677. https://doi.org/10.1038/s41586-021-03854-z

Shi, J., Wang, S., Qu, P., & Shao, J. (2024). Time Series Prediction Model Using LSTM-Transformer Neural Network for Mine Water Inflow. Scientific Reports, 14, 18284. https://doi.org/10.1038/s41598-024-69418-z

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W.-C. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Advances in Neural Information Processing Systems, 28, 802–810. https://proceedings.neurips.cc/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.html

Tekin, S. F., Fazla, A., & Kozat, S. S. (2021). Numerical Weather Forecasting Using Convolutional-LSTM With Attention and Context Matcher Mechanisms. ArXiv. https://doi.org/10.48550/arXiv.2102.00696

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems, 30, 5998–6008. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html

Wang, Y., & Zha, Y. (2024). Comparison of Transformer, LSTM and Coupled Algorithms for Soil Moisture Prediction in Shallow-Groundwater-Level Areas With Interpretability Analysis. Agricultural Water Management, 305, 109120. https://doi.org/10.1016/j.agwat.2024.109120

Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 11106–11115. https://doi.org/10.1609/aaai.v35i12.17325