THE DEVELOPMENT OF AN ARTIFICIAL NEURAL NETWORK MODEL FOR RAINFALL ESTIMATION ACCURACY USING PERSIANN SATELLITE AND METEOROLOGICAL VARIABLES AT SUNGAI PINANG CATCHMENT
DOI:
https://doi.org/10.35631/JISTM.1144056Keywords:
Artificial Neural Network (ANN) model, Flood Forecasting, PERSIANN, Rainfall Estimation, Satellite Precipitation, Sungai Pinang CatchmentAbstract
Accurate rainfall estimation is essential for flood forecasting, water resource management, and disaster risk reduction, particularly in highly urbanized tropical catchments. However, satellite-derived rainfall products often exhibit systematic estimation errors when applied at local scales. This study aims to enhance the accuracy of precipitation estimation from PERSIANN satellite rainfall estimates using an Artificial Neural Network (ANN) model at Sungai Pinang catchment, Penang, Malaysia. Historical rainfall observations from five rain gauge stations were integrated with meteorological variables, including temperature, relative humidity and wind speed. The ANN model employed a three-layer feedforward Backpropagation Neural Network with a 5–10–1 architecture and was trained using data collected between October and December 2018, while an independent dataset from September 2018 was used for model testing. The results demonstrate that the proposed ANN model significantly improved the accuracy of the satellite rainfall estimates across all five rainfall stations. The result indicates that r increased from range 0.132~0.354 (before ANN post processing) to 0.557 ~0.821 (after ANN post processing). Station Kolam Takungan Air Itam indicate the highest percentage increase which is 67.3%. The result for R2 improved from range 0.010~0.125 to 0.8769 ~0.9819 with station Kolam Bersih Pulau Pinang had the highest percentage increase of 93.83%. In addition, the RMSE decreased from range 22.634 ~53.3 to 9.85~37.643, and the MAE was reduced from range 12.929~ 26.734 to 6.281~23.247, indicating substantial reductions in rainfall estimation errors. The findings demonstrate that by integrating satellite-derived rainfall estimates with meteorological variables together with an ANN model effectively enhances rainfall estimation accuracy. The proposed approach provides a reliable tool for improving flood forecasting, hydrological modelling, and water resource management in highly urbanized tropical catchments.
Downloads
References
Aprianto, R., Fitriyanto, S., & Nurul Walidain, S. (2023). Artificial neural network backpropagation for predicting rainfall (Case study in Sultan Muhammad Kaharuddin meteorological station). Jurnal Ilmiah Multi Sciences, 15(1), 63–70.https://doi.org/10.30599/jti.v15i1.2110
Baig, F., Abrar, M., Chen, H., & Sherif, M. (2023). Evaluation of Precipitation Estimates from Remote Sensing and Artificial Neural Network Based Products (PERSIANN) Family in an Arid Region. Remote Sensing, 15(4). https://doi.org/10.3390/rs15041078
Benziane, S. (2024). Survey: Rainfall Prediction precipitation, review of statistical methods. WSEAS Transactions on Systems, 23, 47–59. https://doi.org/10.37394/23202.2024.23.5
Ceferino-Hernández, L., Magaña-Hernández, F., Campos-Campos, E., Morosanu, G. A., Torres- Aguilar, C. E., Mora-Ortiz, R. S., & Díaz, S. A. (2024). Assessment of PERSIANN satellite products over the Tulijá River Basin, Mexico. Remote Sensing, 16(14). https://doi.org/10.3390/rs16142596
Dao, V., Arellano, C. J., Nguyen, P., Almutlaq, F., Hsu, K., & Sorooshian, S. (2025). Bias correction of satellite precipitation estimation using deep neural networks and topographic information over the Western U.S. Journal of Geophysical Research: Atmospheres, 130(4). https://doi.org/10.1029/2024JD042181
Eini, M. R., Rahmati, A., & Piniewski, M. (2022). Hydrological application and accuracy evaluation of PERSIANN satellite-based precipitation estimates over a humid continental climate catchment. Journal of Hydrology:Regional Studies,41,101109.https://doi.org/10.1016/J.EJRH.2022.101109
Fuentes-Barrios, A., & Sierra-Lorenzo, M. (2021). Bias Correction Method Based on Artificial Neural Networks for Quantitative Precipitation Forecast. Environmental Sciences Proceedings, 8(1), 38. https://doi.org/10.3390/ecas2021-10356
Grosan, C., Abraham, A., Jain, L. C., & Kacprzyk, J. (2011). Intelligent systems (Vol. 17, pp. 261-268). Berlin: Springer. https://doi.org/10.1007/978-3-642-21004-4
Hsu, K. L., Gao, X., Sorooshian, S., & Gupta, H. V. (1997). Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks. Journal of Applied Meteorology, 36(9), 1176-1190. https://doi.org/10.1175/1520-0450(1997)036<1176:PEFRSI>2.0.CO;2.
Jabbari, A., & Bae, D. H. (2018). Application of Artificial Neural Networks for Accuracy Enhancements of Real-Time Flood Forecasting in the Imjin basin. Water (Switzerland), 10(11). https://doi.org/10.3390/w10111626
Kunnath-Poovakka, A., & Eldho, T. I. (2023). Bias correction of satellite precipitation products for hydrologic modeling in Western Ghats Region, India. Journal of Hydrologic Engineering, 28(4), 04023010. https://doi.org/10.1061/JHYEFF.HEENG-5699
Latif, S. D., Alyaa Binti Hazrin, N., Hoon Koo, C., Lin Ng, J., Chaplot, B., Feng Huang, Y., El-Shafie, A., & Najah Ahmed, A. (2023).Assessing rainfall prediction models: Exploring the Advantages of Machine Learning and Remote Sensing Approaches. Alexandria Engineering Journal, 82, 16–25. https://doi.org/10.1016/j.aej.2023.09.060
Lim, E. J., Misiran, S. E., Sapiri, M., & Yusof, H. (2024). Forecasting the monthly temperature and rainfall in Chuping Perlis. EDUCATUM Journal of Science, Mathematics and Technology, 11(2), 20. https://doi.org/10.37134/ejsmt.vol11.2.3.2024
Moghim, S., & Bras, R. L. (2017). Bias correction of climate modeled temperature and precipitation using artificial neural networks. Journal of Hydrometeorology, 18(7), 1867–1884. https://doi.org/10.1175/JHM-D-16-0247.1
Mohtar, I. S. A., Tahir, W., & Yusof, M. S. M. (2025a). Enhanced Flood Forecasting using Quantitative Precipitation Forecast from Weather Research Forecast-Artificial Neural Network (WRF-ANN) Model Post Processing. Journal of Water Resources Management, 3(1).
Mohtar, I. S. A., Tahir, W., Jani, J., Mohamad, I. N., Deni, S. M., & Haron, N. F. (2025b). ANN Post-Processing of WRF Model Outputs for Enhanced Rainfall and Flood Forecasting. In 2025 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT) (pp. 409-415). https://doi.org/10.1109/COMNETSAT68601.2025.11324473
Nandakumar, S. D., Valarmathi, R., Sudha Juliet, P., & Brindha, G. (2021). Artificial Neural Network for Rainfall Analysis using Deep Learning Techniques. Journal of Physics: Conference Series, 1964(4). https://doi.org/10.1088/1742-6596/1964/4/042022
Papacharalampous, G., Tyralis, H., Doulamis, A., & Doulamis, N. (2023). Comparison of Machine Learning Algorithms for Merging Gridded Satellite and Earth-Observed Precipitation Data. Water (Switzerland), 15(4). https://doi.org/10.3390/w15040634
Parsons, D., Stern, D., Ndanguza, D., Sylla, M. B., Musyoka, J., Bagiliko, J., Clarkson,G., Dorward, P. (2026). Evaluating Satellite and Reanalysis Rainfall Estimates For Climate Services in Agriculture: A Comprehensive Methodology. Meteorological Applications, 33(2), e70170.
Pratomo, A. H., Santosa, B., Tahalea, S. P., Paripurno, E. T., Peasetyo, J. D., Jayadianti, H., & Pitayandanu, M. F. (2022). Rainfall Prediction using Artificial Neural Network with Historical Weather Data as Supporting Parameters. Jurnal Informatika, 16(2),63. https://doi.org/10.26555/jifo.v16i2.a25422
Qamar, R., & Ali Zardari, B. (2023). Artificial Neural Networks: An Overview. Mesopotamian Journal of Computer Science, 2023, 130–139. https://doi.org/10.58496/MJCSC/2023/015
Rajput, N., Kasimahanthi, A., Reddy, V., Fatima, H., Devarajan, P. K., & Prasad, V. S. (2026). Evaluation and Error Correction of Satellite Rainfall Using Dense Network of Rain Gauges Over Mumbai. Journal of the Indian Society of Remote Sensing, 1-14.
Ridwan, W. M., Sapitang, M., Aziz, A., Kushiar, K. F., Ahmed, A. N., & El-Shafie, A. (2021). Rainfall Forecasting Model using Machine Learning Methods: Case Study Terengganu, Malaysia. Ain Shams Engineering Journal, 12(2), 1651–1663. https://doi.org/10.1016/j.asej.2020.09.011
Sadeghi, M., Nguyen, P., Naeini, M. R., Hsu, K., Braithwaite, D., & Sorooshian, S. (2021). PERSIANN- CCS-CDR, a 3-hourly 0.04° Global Precipitation Climate Data Record for Heavy Precipitation Studies. Scientific Data, 8(1). https://doi.org/10.1038/s41597-021-00940-9
Saleh, A., Sabtu, N., & Bunmi, M. R. (2022). Flash flood Susceptibility Mapping in Sungai Pinang Catchment Using Weight of Evidence.IOP Conference Series: Earth and Environmental Science, 1091(1). https://doi.org/10.1088/1755-1315/1091/1/012017
Sivaji, V. (2025). Sungai Pinang flood mitigation project 27% complete, on track for 2027 completion.https://penanghyperlocal.com/sungai-pinang-flood-mitigation-project-27 complete-on-track-for-2027-completion/.Accessed on 20 June 2026.
Sumith, K. V. (2025). Comprehensive Evaluation of Satellite-Based Rainfall Measurements Through Rain Gauge Validation Using Advanced Statistical Regression and Machine Learning Models by Using Python: KV Sumith. Water Resources Management, 39(9), 4563-4587.
Thakur, N., Karmakar, S., & Soni, S. (2021). Rainfall forecasting using various artificial neural network techniques. A review. International Journal of Scientific Research in Computer Science,Engineering and Information Technology,403–409. https://doi.org/10.32628/cseit2173159.
Yee, L. Z., Tan, K. W., & Huang, Y. F. (2022). Statistical downscaling of regional climate model: A case study in Penang Island, Malaysia. Global Nest Journal, 24(2), 267–275. https://doi.org/10.30955/gnj.003429
Yusoff, I. M., & Rindam, M. (2012). 3D GIS Urban Runoff Mechanism: A New Perspective using Volumetric Soft Geo-Object. Geografia, 8(5). Geografia OnlineTM Malaysia Journal of Society and Space 8 issue 5 (124- 139). Themed Issue: Masyarakat, Ruang dan Alam Sekitar (MATRA), ISSN 2180-2491.
