Rainfall Forecasting Using Generalized Feedforward Neural Network (GFNN) (Case Study: Rainfall Forecasting in Bandung City)

Authors

  • Reva Azzahra Pratama Mathematics Study Program, Universitas Pendidikan Indonesia
  • Dewi Rachmatin Mathematics Study Program, Universitas Pendidikan Indonesia
  • Fitri Rahmawati Mathematics Study Program, Universitas Pendidikan Indonesia

DOI:

https://doi.org/10.24252/msa.v14i2.70441

Keywords:

Rainfall Forecasting, Generalized Feedforward Neural Network (GFNN), Artificial Neural Network, Time Series Analysis, Machine Learning, Bandung City

Abstract

Accurate short-term rainfall forecasting remains challenging because daily rainfall exhibits high variability and nonlinear dependence on meteorological conditions. This study investigates the applicability of a Generalized Feedforward Neural Network (GFNN) for one-step-ahead daily rainfall forecasting in Bandung City using five meteorological variables rainfall, air temperature, relative humidity, wind speed, and wind direction from NASA POWER data covering 2016–2025. The novelty of this study lies in the application and empirical evaluation of the GFNN shortcut-connection architecture to multivariate daily rainfall forecasting in Bandung, where the model simultaneously exploits direct input–output relationships and nonlinear transformations through the hidden layer. The study further evaluates whether GFNN provides predictive information beyond a persistence baseline rather than assessing the model solely through its absolute forecasting error. After percentile-based clipping, min-max normalization, and sliding-window input construction, seven GFNN configurations with 6–11 hidden neurons were evaluated. The selected 5-6-1 architecture achieved RMSE values of 8.9018 mm for the training data and 9.8949 mm for the testing data. On the same testing period, GFNN reduced the RMSE of the persistence baseline from 12.3140 mm to 9.8949 mm, corresponding to a 19.6% reduction in prediction error. The results demonstrate that GFNN can capture useful predictive patterns in Bandung's daily rainfall data and provides a measurable improvement over the naïve persistence approach. However, the model tends to underestimate rainfall above approximately 40 mm, indicating that its current formulation is more suitable for general short-term rainfall forecasting than for extreme-rainfall prediction. The findings provide an empirical basis for further development of GFNN-based rainfall forecasting using longer temporal windows, imbalance-aware loss functions, and ground-station observations.

References

M. N. French, W. F. Krajewski, and R. R. Cuykendall, "Rainfall forecasting in space and time using a neural network," Journal of Hydrology, vol. 137, no. 1–4, pp. 1–31, 1992, doi: 10.1016/0022-1694(92)90046-X.

Geografi.org, "Kondisi Geografi Kota Bandung," 2017. [Online]. Available: https://www.geografi.org/2017/12/kondisi-geografi-kota-bandung.html

Universitas Gadjah Mada, "IABI: Banjir Bandung akibat konversi lahan DAS Citarum," 2016. [Online]. Available: https://ugm.ac.id/id/berita/12719-iabi-banjir-bandung-akibat-konversi-lahan-das-citarum/

R. Kurniawan, "Kota Bandung diterjang 12 bencana awal 2025," Metrotvnews, 2025. [Online]. Available: https://www.metrotvnews.com/read/NP6C3gE2-kota-bandung-diterjang-12-bencana-awal-2025

S. F. Rohmana, A. Rusgiyono, and S. Sugito, "Penentuan faktor-faktor yang mempengaruhi intensitas curah hujan dengan analisis diskriminan ganda dan regresi logistik multinomial," Jurnal Gaussian, vol. 8, no. 3, pp. 398–406, 2019.

H. Ihsan, Irwan, and A. I. E. Nensi, "Implementation of backpropagation and hybrid ARIMA-NN methods in predicting accuracy levels of rainfall in Makassar City," Barekeng, vol. 18, no. 4, pp. 10–14, 2024, doi: 10.30598/barekengvol18iss4pp2435-2448.

T. K. Febrianti, W. Sulandari, and H. Pratiwi, "Peramalan curah hujan di kota Bandung menggunakan singular spectrum analysis," Jurnal Ilmiah Matematika, vol. 8, no. 2, pp. 56–65, 2021.

E. Habinuddin, "Penerapan fuzzy time series untuk memprediksi curah hujan Kota Bandung," Jurnal Digit, vol. 12, no. 2, p. 115, 2022, doi: 10.51920/jd.v12i2.288.

N. A. Charaniya and S. V. Dudul, "Design of neural network models for daily rainfall prediction," International Journal of Computer Applications, vol. 61, no. 14, pp. 23–27, 2013.

M. Shoaib, "Impact of wavelet transformation on data driven rainfall-runoff models," ResearchSpace Repository, 2016.

N. A. Charaniya and S. V. Dudul, "Focused time delay neural network model for rainfall prediction using Indian ocean dipole index," in Proc. 4th Int. Conf. Computational Intelligence and Communication Networks (CICN), 2012, pp. 851–855, doi: 10.1109/CICN.2012.116.

N. Q. Hung, M. S. Babel, S. Weesakul, and N. K. Tripathi, "An artificial neural network model for rainfall forecasting in Bangkok, Thailand," Hydrology and Earth System Sciences, vol. 13, no. 8, pp. 1413–1425, 2009, doi: 10.5194/hess-13-1413-2009.

P. A. Kharat and S. V. Dudul, "Epilepsy diagnosis based on generalized feed forward neural network," Interdisciplinary Sciences – Computational Life Sciences, vol. 4, no. 3, pp. 209–214, 2012, doi: 10.1007/s12539-012-0129-6.

A. N. Celik and M. Kolhe, "Generalized feed-forward based method for wind energy prediction," Applied Energy, vol. 101, pp. 582–588, 2013, doi: 10.1016/j.apenergy.2012.06.040.

M. Shoaib et al., "A comparative study of various hybrid wavelet feedforward neural network models for runoff forecasting," Water Resources Management, vol. 32, no. 1, pp. 83–103, 2018, doi: 10.1007/s11269-017-1796-1.

G. Arulampalam and A. Bouzerdoum, "A generalized feedforward neural network architecture for classification and regression," Neural Networks, vol. 16, no. 5–6, pp. 561–568, 2003, doi: 10.1016/S0893-6080(03)00116-3.

R. Y. Tallar, Dasar-Dasar Hidrologi Terapan. Bandung: Ideas Publishing, 2023.

Badan Meteorologi, Klimatologi, dan Geofisika (BMKG), "Daftar istilah klimatologi," 2016. [Online]. Available: https://bbmkg3.bmkg.go.id/daftar-istilah-musim

L. V. Fausett, Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Englewood Cliffs, NJ: Prentice Hall, 1994.

J. J. Siang, Jaringan Syaraf Tiruan dan Pemrogramannya dengan Matlab. Yogyakarta: Penerbit Andi, 2005.

S. Haykin, Neural Networks and Learning Machines, 3rd ed. Upper Saddle River, NJ: Pearson Prentice Hall, 2009.

D. Fletcher and E. Goss, "Forecasting with neural networks," Information & Management, vol. 24, no. 3, pp. 159–167, 1993, doi: 10.1016/0378-7206(93)90064-Z.

S. Taieb, G. Bontempi, A. F. Atiya, and A. Sorjamaa, "A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition," Expert Systems with Applications, vol. 39, no. 8, pp. 7067–7083, 2012, doi: 10.1016/j.eswa.2012.01.039.

J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Waltham, MA: Morgan Kaufmann, 2012.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016.

S. An, T. Oh, E. Sohn, and D. Kim, "Deep learning for precipitation nowcasting: A survey from the perspective of time series forecasting," 2024.

M. G. Bosilovich, F. R. Robertson, L. Takacs, A. Molod, and D. Mocko, "Atmospheric water balance and variability in the MERRA-2 reanalysis," Journal of Climate, vol. 30, no. 4, pp. 1177–1196, 2017, doi: 10.1175/JCLI-D-16-0338.1.

Sudjana, Metoda Statistika, 6th ed. Bandung: Tarsito, 1996.

R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 2nd ed. Melbourne, Australia: OTexts, 2018.

Downloads

Published

2026-11-14

How to Cite

[1]
Reva Azzahra Pratama, Dewi Rachmatin, and Fitri Rahmawati, “ Rainfall Forecasting Using Generalized Feedforward Neural Network (GFNN) (Case Study: Rainfall Forecasting in Bandung City)”, MSA, vol. 14, no. 2, pp. 258–268, Nov. 2026.