Implementation of a Hybrid TabNet–XGBoost Model Based on Radiosonde Data for Predicting Daily Rainfall Intensity in Surabaya
DOI:
https://doi.org/10.30871/jaic.v10i4.13767Keywords:
Hybrid TabNet–XGBoost, Machine Learning, Rainfall Prediction, RadiosondeAbstract
Rainfall prediction plays an important role in supporting hydrometeorological disaster mitigation and weather-related decision-making. However, accurate rainfall prediction remains challenging because atmospheric processes are highly nonlinear and governed by complex interactions among multiple meteorological variables. This study proposes a Hybrid TabNet–XGBoost model for daily rainfall prediction using integrated radiosonde and surface meteorological observations collected at the BMKG Juanda Class I Meteorological Station. The dataset covers the period from 2019 to 2025 and consists of 2,551 daily observations. TabNet was employed to select the fifteen most informative atmospheric variables based on feature importance, while temporal dependencies were incorporated through lag features generated using Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) analyses. Hyperparameter optimization was performed using Optuna with TimeSeriesSplit cross-validation prior to model training. Experimental results on the testing dataset achieved an RMSE of 19.1347 mm, an MAE of 11.9742 mm, a MAPE of 17.62%, and an R² of 0.0449. The proposed model was able to capture the general temporal pattern of daily rainfall and produced satisfactory predictions under the dominant rainfall conditions represented in the dataset. However, the model exhibited reduced sensitivity to high-intensity rainfall events, resulting in the underestimation of extreme rainfall and a relatively low R² value, primarily due to the imbalanced rainfall distribution and the complexity of rainfall processes. The optimized model was subsequently applied to generate daily rainfall projections for 2026 based on historical atmospheric observations. Since the corresponding observational data were unavailable at the time of this study, these projections should be interpreted as model-based forecasts rather than validated prediction results. Overall, the proposed Hybrid TabNet–XGBoost framework demonstrates the potential of integrating radiosonde and surface meteorological observations for daily rainfall prediction while highlighting the need for additional atmospheric and spatial information to improve the prediction of extreme rainfall events.
Downloads
References
[1] Intergovernmental Panel on Climate Change (IPCC), Climate Change 2023: Synthesis Report. Geneva, Switzerland: IPCC, 2023.
[2] World Meteorological Organization (WMO), State of the Global Climate 2023. Geneva, Switzerland: WMO, 2024.
[3] Badan Nasional Penanggulangan Bencana (BNPB), Indeks Risiko Bencana Indonesia 2024. Jakarta, Indonesia: BNPB, 2024.
[4] Badan Meteorologi, Klimatologi, dan Geofisika (BMKG), Prakiraan Musim Hujan Indonesia 2024/2025. Jakarta, Indonesia: BMKG, 2024.
[5] R. R. Rogers and M. K. Yau, A Short Course in Cloud Physics, 3rd ed. Oxford, U.K.: Butterworth-Heinemann, 1989.
[6] T. N. Krishnamurti, L. Stefanova, and V. Misra, Tropical Meteorology: An Introduction. New York, NY, USA: Springer, 2013.
[7] Pemerintah Kota Surabaya, Laporan Penanggulangan Banjir Kota Surabaya Tahun 2024. Surabaya, Indonesia, 2024.
[8] A. Abbot and J. Marohasy, "Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks," Atmospheric Research, vol. 138, pp. 166–178, 2014.
[9] H. Hersbach et al., "The ERA5 global reanalysis," Quarterly Journal of the Royal Meteorological Society, vol. 146, no. 730, pp. 1999–2049, 2020.
[10] World Meteorological Organization (WMO), Guide to Instruments and Methods of Observation (WMO-No. 8), 2021 ed. Geneva, Switzerland: WMO, 2021.
[11] R. A. Anthes, "Data assimilation and radiosonde observations in numerical weather prediction," Bulletin of the American Meteorological Society, vol. 100, no. 7, pp. 1285–1301, 2019.
[12] C. A. Doswell III, H. E. Brooks, and R. A. Maddox, "Flash flood forecasting: An ingredients-based methodology," Weather and Forecasting, vol. 11, no. 4, pp. 560–581, 1996.
[13] G. J. Haklander and A. Van Delden, "Thunderstorm predictors and their forecast skill for the Netherlands," Atmospheric Research, vol. 67–68, pp. 273–299, 2003.
[14] P. Markowski and Y. Richardson, Mesoscale Meteorology in Midlatitudes. Chichester, U.K.: Wiley-Blackwell, 2010.
[15] H. V. Gupta, S. Sorooshian, and P. O. Yapo, "Toward improved calibration of hydrologic models," Water Resources Research, vol. 34, no. 4, pp. 751–763, 1998.
[16] S. O. Arik and T. Pfister, "TabNet: Attentive Interpretable Tabular Learning," in Proc. AAAI Conf. Artificial Intelligence, vol. 35, no. 8, pp. 6679–6687, 2021.
[17] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785–794.
[18] A. Borisov, I. Seßler, T. Leemann, K. Pawelczyk, and G. Kasneci, "Deep Neural Networks and Tabular Data: A Survey," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 6, pp. 7499–7519, 2024.
[19] Mosavi, A., Ozturk, P., and K. W. Chau, "Flood prediction using machine learning models: Literature review," Water, vol. 10, no. 11, Art. no. 1536, 2018.
[20] Ke, G., et al., "LightGBM: A Highly Efficient Gradient Boosting Decision Tree," in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
[21] Hochreiter, S., and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[22] H. Hersbach et al., "The ERA5 global reanalysis," Quarterly Journal of the Royal Meteorological Society, vol. 146, no. 730, pp. 1999–2049, 2020.
[23] A. Borisov, I. Seßler, T. Leemann, K. Pawelczyk, and G. Kasneci, "Deep Neural Networks and Tabular Data: A Survey," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 6, pp. 7499–7519, 2024.
[24] X. Liu, Y. Zhang, and J. Wang, "A Hybrid TabNet-XGBoost Model for Tabular Data Prediction," Applied Soft Computing, vol. 145, Art. no. 110560, 2023.
[25] C. J. Willmott and K. Matsuura, "Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE)," Climate Research, vol. 30, pp. 79–82, 2005.
[26] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann, 2012.
[27] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021.
[28] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[29] L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[30] S. O. Arik and T. Pfister, "TabNet: Attentive Interpretable Tabular Learning," in Proc. AAAI Conf. Artificial Intelligence, vol. 35, no. 8, pp. 6679–6687, 2021.
[31] S. O. Arik and T. Pfister, "TabNet: Attentive Interpretable Tabular Learning," AAAI Conference on Artificial Intelligence, vol. 35, no. 8, pp. 6679–6687, 2021.
[32] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ, USA: Wiley, 2015.
[33] M. H. Kutner, C. J. Nachtsheim, J. Neter, and W. Li, Applied Linear Statistical Models, 5th ed. New York, NY, USA: McGraw-Hill, 2005.
[34] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021.
[35] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A Next-generation Hyperparameter Optimization Framework," in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Anchorage, AK, USA, 2019, pp. 2623–2631.
[36] X. Liu, Y. Zhang, and J. Wang, "A Hybrid TabNet-XGBoost Model for Tabular Data Prediction," Applied Soft Computing, vol. 145, Art. no. 110560, 2023.
[37] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785–794.
[38] C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.
[39] C. J. Willmott and K. Matsuura, "Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE)," Climate Research, vol. 30, pp. 79–82, 2005.
[40] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann, 2012.
[41] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Annabel Gracia Puryani, Aviolla Terza Damaliana, Alfan Rizaldy Pratama
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
