Hybrid Spatio-Temporal Modeling Based on Bidirectional ConvLSTM and Attention-GRU for Daily Rainfall Prediction in Jakarta Special Capital Region (DKI Jakarta)
Keywords:
Rainfall Prediction, Deep Learning, ConvLSTM, Attention-GRU, Spatio-Temporal Modeling.Abstract
Background: Accurate daily rainfall prediction supports flood mitigation in DKI Jakarta, a tropical megacity whose rainfall is shaped by interactions between coastal (sea-breeze) and upstream orographic processes. Gap: Most previous studies rely on single-station data or purely temporal models (e.g., LSTM or GRU), which flatten the spatial layout of observation networks. Method: This study proposes a hybrid architecture that combines a bidirectional convolutional LSTM (Bi-ConvLSTM) with an attention-based GRU (Attention-GRU). Daily data of nine meteorological variables (including lagged rainfall) from four BMKG stations (Kemayoran as the target, Soekarno-Hatta, Tanjung Priok, and Citeko), covering January 2010 to April 2026 (5,964 days), were arranged into a 2×2 grid with a seven-day window, giving an input tensor of shape (7, 2, 2, 9). Results: On a chronologically held-out test set of 1,193 days, the proposed model obtained an RMSE of 16.32 mm, an MAE of 8.20 mm, and an R² of 0.1158, compared with 16.43 mm, 8.45 mm, and 0.1034 for a standard LSTM baseline (RMSE −0.67%, MAE −2.96%); the paired absolute-error difference was significant by the Wilcoxon signed-rank test (p = 0.00155). The gains are modest: ablation variants without attention reached a lower MAE but a higher RMSE, and the model strongly underpredicts rainfall above 20 mm. Contribution: The study provides a reproducible multi-station grid representation for Jakarta and evidence that upstream (Citeko) information contributes most to next-day prediction at Kemayoran. Practical implication: With an inference time of about 18 ms per sample the model is computationally light, but because it underestimates heavy rainfall it is, at this stage, a candidate supporting signal for early warning rather than a stand-alone warning engine.
References
E. Aldrian and R. D. Susanto, "Identification of three dominant rainfall regions within Indonesia and their relationship to sea surface temperature," Int. J. Climatol., vol. 23, no. 12, pp. 1435–1452, 2003, doi: 10.1002/joc.950.
X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo, "Convolutional LSTM net-work: A machine learning approach for precipitation nowcasting," in Adv. Neural Inf. Process. Syst. (NeurIPS), 2015, pp. 802–810.
J. Xiao et al., "A ConvLSTM-based model for urban flood prediction under dynamic rainfall patterns and exploration on its extrapolation capability," Int. J. Disaster Risk Sci., vol. 16, no. 6, pp. 1057–1073, 2025, doi: 10.1007/s13753-025-00685-8.
A. Y. Barrera-Animas, L. O. Oyedele, M. Bilal, T. D. Akinosho, J. M. D. Delgado, and L. A. Akanbi, "Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting," Mach. Learn. Appl., vol. 7, p. 100204, 2022, doi: 10.1016/j.mlwa.2021.100204.
S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
K. Cho et al., "Learning phrase representations using RNN encoder–decoder for statistical machine translation," in Proc. EMNLP, 2014, pp. 1724–1734, doi: 10.3115/v1/D14-1179.
F. Rezaie Adaryani, S. J. Mousavi, and F. Jafari, "Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR, LSTM and CNN," J. Hydrol., vol. 614, p. 128463, 2022, doi: 10.1016/j.jhydrol.2022.128463.
M. Schuster and K. K. Paliwal, "Bidirectional recurrent neural networks," IEEE Trans. Signal Pro-cess., vol. 45, no. 11, pp. 2673–2681, 1997, doi: 10.1109/78.650093.
D. Endalie, G. Haile, and W. Taye, "Deep learning model for daily rainfall prediction: Case study of Jimma, Ethiopia," Water Supply, vol. 22, no. 3, pp. 3448–3461, 2022, doi: 10.2166/ws.2021.391.
Y. Yang, S. Li, T. Zhou, L. Zhao, X. Shi, and B. Du, "Rainfall forecasting using a BiLSTM model opti-mized by an improved whale migration algorithm and variational mode decomposition," Mathe-matics, vol. 13, no. 15, p. 2483, 2025, doi: 10.3390/math13152483.
A. Vaswani et al., "Attention is all you need," in Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 5998–6008.
S. Bai, J. Z. Kolter, and V. Koltun, "An empirical evaluation of generic convolutional and recurrent networks for sequence modeling," arXiv preprint arXiv:1803.01271, 2018.
K. Bi, L. Xie, H. Zhang, X. Chen, X. Gu, and Q. Tian, "Accurate medium-range global weather fore-casting with 3D neural networks," Nature, vol. 619, pp. 533–538, 2023, doi: 10.1038/s41586-023-06185-3.
R. Lam et al., "Learning skillful medium-range global weather forecasting," Science, vol. 382, no. 6677, pp. 1416–1421, 2023, doi: 10.1126/science.adi2336.
L. Espeholt et al., "Deep learning for twelve hour precipitation forecasts," Nat. Commun., vol. 13, p. 5145, 2022, doi: 10.1038/s41467-022-32483-x.
P. Hess and N. Boers, "Deep learning for improving numerical weather prediction of heavy rain-fall," J. Adv. Model. Earth Syst., vol. 14, no. 3, 2022, doi: 10.1029/2021MS002765.
P. Shu, X. Duan, C. Shao, J. Liu, Y. Tian, and S. Li, "Precipitation spatio-temporal forecasting in Chi-na via DC-CNN-BiLSTM," Water, vol. 17, no. 9, p. 1381, 2025, doi: 10.3390/w17091381.
J. Zhang, M. Yin, P. Wang, and Z. Gao, "A method based on deep learning for severe convective weather forecast: CNN-BiLSTM-AM (version 1.0)," Atmosphere, vol. 15, no. 10, p. 1229, 2024, doi: 10.3390/atmos15101229.
L. Guo, Y. Pu, and W. Zhao, "CNN-BiLSTM daily precipitation prediction based on attention mech-anism," pp. 1–13, 2025.
M. Belletreche et al., "Hybrid attention-based deep neural networks for short-term wind power forecasting using meteorological data in desert regions," Sci. Rep., vol. 14, no. 1, pp. 1–17, 2024, doi: 10.1038/s41598-024-73076-6.
Q. Hu, Q. Sun, Z. H. Chen, H. X. Hu, Y. Zhang, and Z. Y. Hu, "Rainfall spatiotemporal interpolation method based on CNN-GRU with attention," in Proc. Int. Conf. Digit. Image Process. (ICDIP), ACM, 2023, doi: 10.1145/3604078.3604151.
Supriatna et al., "Analisis prediksi curah hujan di Kota Tangerang menggunakan metode LSTM dan GRU," 2025.
Abdillah et al., "Prediksi curah hujan menggunakan metode Bi-LSTM dan GRU berbasis data iklim," 2025.
D. E. Nuryanto, H. Pawitan, R. Hidayat, and E. Aldrian, "Characteristics of two mesoscale convec-tive systems (MCSs) over the Greater Jakarta: Case of heavy rainfall period 15–18 January 2013," Geosci. Lett., 2019, doi: 10.1186/s40562-019-0131-5.
P. Syahdan Nabil and Y. Ramdhani, "Application of bidirectional gated recurrent unit algorithm for rainfall prediction," J. Tek. Inform. C.I.T Medicom, vol. 15, no. 4, pp. 188–198, 2023.
