Identification of Atmospheric Dynamics of a Tropical Hail Event and Application of Radar Reflectivity Nowcasting Using a UNet-ConvLSTM2D Deep Learning Model

Muhizzadin Abdul Adzan; Deni Septiadi; Adi Mulsandi; Latifah Nurul  Qomariyatuzzamzami

doi:10.26877/lpt.v5i3.1087

Authors

Muhizzadin Abdul Adzan Meteorology Study Program, Sekolah Tinggi Metorologi Klimatologi dan Geofisika, Tangerang, Banten, Indonesia Author
Deni Septiadi Meteorology Study Program, Sekolah Tinggi Metorologi Klimatologi dan Geofisika, Tangerang, Banten, Indonesia Author
Adi Mulsandi Meteorology Study Program, Sekolah Tinggi Metorologi Klimatologi dan Geofisika, Tangerang, Banten, Indonesia Author https://orcid.org/0000-0003-4150-438X
Latifah Nurul Qomariyatuzzamzami Meteorology Study Program, Sekolah Tinggi Metorologi Klimatologi dan Geofisika, Tangerang, Banten, Indonesia Author

DOI:

https://doi.org/10.26877/lpt.v5i3.1087

Keywords:

deep learning, Hail, radar, satellite, Unet–ConvLSTM2D

Abstract

Hail is a small-scale hydrometeorological phenomenon threatening disaster-prone regions of Indonesia, yet understanding of its atmospheric dynamics and deep learning-based radar nowcasting remain limited. This study characterizes the atmospheric conditions of the Depok City hailstorm on 28 October 2024 and evaluates a hybrid UNet-ConvLSTM2D model in predicting radar reflectivity. The study employed Column Maximum (CMAX) radar reflectivity data in PNG and VOL formats from the Soekarno-Hatta Class I Meteorological Station, cloud-top temperature and Cloud Convective Overlay data from Himawari-9 satellite imagery, and ERA5 reanalysis data on storm thermodynamic and kinematic conditions, while radar data from January 2023 to October 2024 were used for model training and validation. Model performance was assessed using Mean Squared Error (MSE), Mean Absolute Error (MAE), Structural Similarity Index (SSIM), Critical Success Index (CSI), and Heidke Skill Score (HSS) across five reflectivity thresholds. Results show maximum radar reflectivity exceeding 55 dBZ at 08.18 UTC and 08.42 UTC, cloud-top temperatures of approximately -61°C to -73°C, and Convective Available Potential Energy (CAPE) of 524-590 J/kg with weak vertical wind shear of 2.4-2.8 m/s from ERA5, confirming a moderately unstable tropical convective environment. Prediction results yielded average values of 184.5897 for MSE, 9.7081 for MAE, and 0.3956 for SSIM, with CSI decreasing from 0.588 to 0.284 and HSS from 0.637 to 0.057 as lead time increased from 8 to 56 minutes. These findings are expected to enhance understanding of the atmospheric dynamics contributing to hail and support wider deep learning-based nowcasting for early warning in tropical Indonesia.

Downloads

Download data is not yet available.

References

Adzan, M. A., Setyowati, P. R., & Haryanto, Y. D. (2025). Analysis of Significant Weather Phenomena Triggering Diversions at Soekarno-Hatta International Airport Using Multi-Data Observations (Case Study Of January 28, 2025). Jurnal Geografi dan Pengajarannya, 23(2), 303–316. https://doi.org/10.26740/jggp.v23n2.p303-316

Aeni, P., & Anwar, M. K. (2024). Hydrometeorological Disaster: Challenges and Mitigation in Indonesia. Jurnal Indonesia Sosial Teknologi, 5(1). https://doi.org/10.59141/jist.v5i01.888

Ali, A., & Sa’adah, U. (2021). Radar-based stochastic precipitation nowcasting using the short-term ensemble prediction system (Steps)(Case Study: Pangkalan bun weather radar). International Journal of Remote Sensing and Earth Sciences, 18(1), 91–102. https://ejournal.brin.go.id/ijreses/article/view/13755

Ariwibowo, F. S., & Anang Ahmad Khairin Nur, I. (2018). Identifikasi Fenomena Hujan Es Berbasis Analisis Faktor Cuaca Menggunakan Citra Satelit Himawari-8 dan Data Upper Air Sounding (Studi Kasus: Kejadian Hujan Es Tanggal 20 Maret 2018 di Depok). JIIF (Jurnal Ilmu dan Inovasi Fisika), 2(2), 145–154. https://doi.org/10.24198/jiif.v2i2.19729

Ayzel, G., Heistermann, M., & Winterrath, T. (2019). Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0. 1). Geoscientific Model Development, 12(4), 1387–1402. https://doi.org/10.5194/gmd-12-1387-2019

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

Byers, H. R., & Braham, R. R. (1949). The thunderstorm: report of the Thunderstorm Project. US Government Printing Office.

Calota, I., Faur, D., & Datcu, M. (2023). Dimensionality Reduction of Deep Learning for Earth Observation: Smaller, Faster, Simpler. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 4484–4498. https://doi.org/10.1109/JSTARS.2023.3270384

Chen, L., Cao, Y., Ma, L., & Zhang, J. (2020). A deep learning‐based methodology for precipitation nowcasting with radar. Earth and Space Science, 7(2), e2019EA000812. https://doi.org/10.1029/2019EA000812

Dave, R., Subramanian, S. S., & Bhatia, U. (2021). Extreme precipitation induced concurrent events trigger prolonged disruptions in regional road networks. Environmental Research Letters, 16(10), 104050. https://doi.org/10.1088/1748-9326/ac2d67

Dennis, E. J., & Kumjian, M. R. (2017). The Impact of Vertical Wind Shear on Hail Growth in Simulated Supercells. Journal of the Atmospheric Sciences, 74(3), 641–663. https://doi.org/10.1175/JAS-D-16-0066.1

Diniyati, E., Fa’iz Dwitrisna, M., & Mulya, A. (2021). Analisis Kondisi Atmosfer Saat Banjir dan Tanah Longsor (Studi Kasus : Nganjuk, 14 Februari 2021). Sainstek (e-Journal), 9(1), 18–24. https://doi.org/10.35583/js.v9i1.133

Djazim Syaifullah, M., Nuryanto, S., Besar Teknologi Modifikasi Cuaca – Badan Pengkajian dan Penerapan Teknologi, B., Kunci, K., Gms, S., Kanal, M., & Modifikasi Cuaca, T. (2016). Pemanfaatan Data Satelit Gms Multi Kanal Untuk Kegiatan Teknologi Modifikasi Cuaca Utilization of Multichannel GMS Satellite Data for Weather Modification Technology Activities. Jurnal Sains & Teknologi Modifikasi Cuaca, 17(2), 47–55. https://doi.org/10.29122/jstmc.v17i2.525

Fadholi, A. (2012). Analisa Kondisi Atmosfer pada Kejadian Cuaca Ekstrem Hujan Es (Hail). Simetri: Jurnal Ilmu Fisika Indonesia, 1(2), 74–80. https://doi.org/10.24198/jiif.v2i2.19711

Frystine, M., Mulya, A., Kristianto, A., & Maulidyah, M. P. (2022). Analysis of atmospheric condition on hail event at Pelalawan (case study: September 23rd, 2019). Jurnal Meteorologi dan Geofisika, 23(2), 45. https://doi.org/10.31172/jmg.v23i3.813

Kim, D.-K., & Ushio, T. (2022). Nowcasting meso-γ-scale convective storms using convolutional LSTM models and high-resolution radar observations. Tellus, 74(1). https://doi.org/10.16993/tellusa.37

Kou, L., Lin, Z., Gao, H., Liao, S., & Ding, P. (2023). Simulation and sensitivity analysis for cloud and precipitation measurements via spaceborne millimeter-wave radar. Atmospheric Measurement Techniques, 16(6), 1723–1744. https://doi.org/10.5194/amt-16-1723-2023

Liao, Y., Lu, S., & Yin, G. (2024). Short-Term and Imminent Rainfall Prediction Model Based on ConvLSTM and SmaAT-UNet. Sensors, 24(11), 3576. https://doi.org/10.3390/s24113576

Luo, C., Li, X., & Ye, Y. (2020). PFST-LSTM: A spatiotemporal LSTM model with pseudoflow prediction for precipitation nowcasting. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 843–857. https://doi.org/10.1109/JSTARS.2020.3040648

Mason, B. J. (1972). The Bakerian Lecture, 1971. The physics of the thunderstorm. Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences, 327(1571), 433–466.

Naz, F., She, L., Sinan, M., & Shao, J. (2024). Enhancing Radar Echo Extrapolation by ConvLSTM2D for Precipitation Nowcasting. Sensors, 24(2), 459. https://doi.org/10.3390/s24020459

Naz, F., She, L., Zhang, C., & Shao, J. (2025a). A two-stage trained hybrid Unet-ConvLSTM2D for enhanced precipitation nowcasting. Environmental Modelling & Software, 192(February), 106532. https://doi.org/10.1016/j.envsoft.2025.106532

Naz, F., She, L., Zhang, C., & Shao, J. (2025b). A two-stage trained hybrid Unet-ConvLSTM2D for enhanced precipitation nowcasting. Environmental Modelling & Software, 106532. https://doi.org/10.1016/j.envsoft.2025.106532

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(May), 103962. https://doi.org/10.1016/j.jag.2024.103962

Prasetyo, S., Abdilah, S., Nugraheni, I. R., & Sagita, N. (2022). Studi Awan Konvektif Penyebab Hujan Es Menggunakan Radar Cuaca Doppler Single Polarization di Bogor (23 September 2020). Jurnal Aplikasi Meteorologi, 1(1), 32–42. https://stmkg.balai2bmkg.id/index.php/jam/article/view/17

Rahimi, R., Ravirathinam, P., Ebtehaj, A., Behrangi, A., Tan, J., & Kumar, V. (2024). Global Precipitation Nowcasting of Integrated Multi-satellitE Retrievals for GPM: A U-Net Convolutional LSTM Architecture. Journal of Hydrometeorology, 25(6), 947–963. https://doi.org/10.1175/JHM-D-23-0119.1

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

Rosyida, A., & Nurmasari, R. (2019). Analisis Perbandingan Dampak Kejadian Bencana Hidrometeorologi dan Geologi di Indonesia Dilihat Dari Jumlah Korban (Studi: Data Kejadian Bencana Indonesia 2018). Jurnal Dialog Penanggulangan Bencana, 10(1), 12–21. https://jdpb.bnpb.go.id/index.php/jurnal/article/view/127

Rumapea, H., Zarlis, M., Sihombing, P., Efendi, S., Sinambela, M., & Saragih, I. J. A. (2022). Convective Cloud Classification Model for Reconstruction of Heavy Rain That Triggers the Flood and Landslide in Parapat, North Sumatera. IOP Conference Series: Earth and Environmental Science, 1083(1), 012017. https://doi.org/10.1088/1755-1315/1083/1/012017

Sari, F. P., & Lasher‐Trapp, S. (2025). Hailstorm Events Over a Maritime Tropical Region: Storm Environments and Characteristics. Journal of Geophysical Research: Atmospheres, 130(10). https://doi.org/10.1029/2024JD042718

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W. (2015a). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28. https://arxiv.org/abs/1506.04214

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W., & Woo, W. (2015b). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Advances in Neural Information Processing Systems, 2015-Janua, 802–810. http://arxiv.org/abs/1506.04214

Shi, X., Gao, Z., Lausen, L., Wang, H., Yeung, D.-Y., Wong, W., & Woo, W. (2017). Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model. Advances in Neural Information Processing Systems, 2017-Decem(Nips), 5618–5628. http://arxiv.org/abs/1706.03458

Sokol, Z., Szturc, J., Orellana-Alvear, J., Popova, J., Jurczyk, A., & Célleri, R. (2021). The role of weather radar in rainfall estimation and its application in meteorological and hydrological modelling—A review. Remote Sensing, 13(3), 351. https://doi.org/10.3390/rs13030351

Tan, X., Ma, Z., He, K., Han, X., Ji, Q., & He, Y. (2020). Evaluations on gridded precipitation products spanning more than half a century over the Tibetan Plateau and its surroundings. Journal of Hydrology, 582, 124455. https://doi.org/10.1016/j.jhydrol.2019.124455

Thomas, G., Mahfouf, J.-F., & Montmerle, T. (2020). Toward a variational assimilation of polarimetric radar observations in a convective-scale numerical weather prediction (NWP) model. Atmospheric Measurement Techniques, 13(5), 2279–2298. https://doi.org/10.5194/amt-13-2279-2020

Trebing, K., Staǹczyk, T., & Mehrkanoon, S. (2021). SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture. Pattern Recognition Letters, 145, 178–186. https://doi.org/10.1016/j.patrec.2021.01.036

Wang, D., Prein, A. F., Giangrande, S. E., Ramos‐Valle, A., Ge, M., & Jensen, M. P. (2022). Convective Updraft and Downdraft Characteristics of Continental Mesoscale Convective Systems in the Model Gray Zone. Journal of Geophysical Research: Atmospheres, 127(16), 1–20. https://doi.org/10.1029/2022JD036746

Wang, S., Cao, J., & Philip, S. Y. (2020). Deep learning for spatio-temporal data mining: A survey. IEEE transactions on knowledge and data engineering, 34(8), 3681–3700. https://doi.org/10.1109/TKDE.2020.3025580

Wapler, K. (2017). The life-cycle of hailstorms: Lightning, radar reflectivity and rotation characteristics. Atmospheric Research, 193(April), 60–72. https://doi.org/10.1016/j.atmosres.2017.04.009

Woo, W., & Wong, W. (2017). Operational application of optical flow techniques to radar-based rainfall nowcasting. Atmosphere, 8(3), 48. https://doi.org/10.3390/atmos8030048

Yanfatriani, E., Marzuki, M., Vonnisa, M., Razi, P., Hapsoro, C. A., Ramadhan, R., & Yusnaini, H. (2024). Extreme rainfall trends and hydrometeorological disasters in tropical regions: implications for climate resilience. Emerg Sci J, 8(5), 1860–1874. https://doi.org/10.28991/ESJ-2024-08-05-012

Yin, J., Gao, Z., & Han, W. (2021). Application of a Radar Echo Extrapolation‐Based Deep Learning Method in Strong Convection Nowcasting. Earth and Space Science, 8(8), 1–23. https://doi.org/10.1029/2020EA001621

Zhang, Y., Geng, S., Tian, W., Ma, G., Zhao, H., Xie, D., Lu, H., & Lim Kam Sian, K. T. C. (2023). Weather radar echo extrapolation with dynamic weight loss. Remote Sensing, 15(12), 3138. https://doi.org/10.3390/rs15123138