KLASIFIKASI INTENSITAS HUJAN PER JAM MENGGUNAKAN 1D-CNN BERBASIS TINYML DENGAN KALIBRASI AMBANG PRECISION-RECALL
DOI:
https://doi.org/10.33480/inti.v21i1.8794Keywords:
1D-CNN, Precision-Recall Threshold Calibration, Rainfall Intensity Classification, TinyMLAbstract
Hydrometeorological disasters dominate annual disaster occurrences in Indonesia, yet local rainfall prediction remains challenging due to atmospheric complexity and limited resolution of numerical weather models. Server-based forecasting systems further depend on high-performance computing infrastructure and stable network connectivity that are not always available in the field. This study develops an hourly rainfall intensity classification model based on One-Dimensional Convolutional Neural Network (1D-CNN) deployable on an ESP32-S3 microcontroller as a proof-of-concept inference component for rainfall early warning systems. The model uses nine meteorological features arranged in an 18×9 sliding window derived from observational data from the BMKG Soekarno-Hatta Meteorological Station AWS from 2018 to 2025. Logarithmic class weighting and Precision-Recall curve threshold calibration were applied to address extreme class imbalance in hourly resolution data. The model was compared against five baseline models under identical configurations. Threshold calibration increased K2 recall from 0.037 to 0.236 and improved Macro-F1 from 0.461 to 0.530, outperforming all baseline models in terms of Macro-F1. Post-training quantization INT8 reduced model size from 185.8 KB to 64.8 KB with 99.02% decision agreement against the Float32 model. On-device inference on ESP32-S3 achieved a total latency of 13.873 ms with 36.5 KB tensor arena and 234.7 KB free heap, confirming real-time operation without dependence on servers or internet connectivity.
Downloads
References
Akbar, H., & Sanjaya, W. K. (2023). Kajian Performa Metode Class Weight Random Forest pada Klasifikasi Imbalance Data Kelas Curah Hujan. Jurnal Sains, Nalar, dan Aplikasi Teknologi Informasi, 3(1), 42–49. https://doi.org/10.20885/snati.v3i1.30
Badan Nasional Penanggulangan Bencana. (2024). Buku data bencana Indonesia tahun 2023. https://bnpb.go.id/buku/buku-data-bencana-indonesia-tahun-2023
Bauer, P. (2024). What if? Numerical weather prediction at the crossroads. Journal of the European Meteorological Society, 1, 100002. http://arxiv.org/abs/2407.03787
Chi, D. T. K., Trang, N. T. M., Son, T. B. M., Thao, N. N., & Nguyen, T. Q. (2025). Hybrid Deep Learning Framework for Robust Time-Series Classification: Integrating Inception Modules with Residual Networks. Journal of Algorithms & Computational Technology, 19, 1–20. https://doi.org/10.1177/17483026251348851
Esposito, M., Palma, L., Belli, A., Sabbatini, L., & Pierleoni, P. (2022). Recent Advances in Internet of Things Solutions for Early Warning Systems: A Review. Sensors, 22(6), 2124. https://doi.org/10.3390/s22062124
Farhadpour, S., Warner, T. A., & Maxwell, A. E. (2024). Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices. Remote Sensing, 16(3), 533. https://doi.org/10.3390/rs16030533
Glawion, L., Polz, J., Kunstmann, H., Fersch, B., & Chwala, C. (2025). Global Spatio-Temporal ERA5 Precipitation Downscaling to km and Sub-hourly Scale Using Generative AI. npj Climate and Atmospheric Science, 8(1), 219. https://doi.org/10.1038/s41612-025-01103-y
Gupta, S., & Shivhare, S. N. (2025). Embedded TinyML for Predictive Maintenance: Vibration Analysis on ESP32 with Real-Time Fault Detection in Industrial Equipment. International Journal on Computational Modelling Applications, 2(2), 1–17. https://doi.org/10.63503/j.ijcma.2025.114
Hidayat, R., Saputra, E., & Alsepan, G. (2025). The Impact of Convective Available Potential Energy (CAPE) on Spatio-Temporal Variations of Indonesian Extreme Rainfall. Journal of Mathematical and Fundamental Sciences, 57(1), 70–85. https://doi.org/10.5614/j.math.fund.sci.2025.57.1.5
Kong, L., Snášel, V., Bai, Z., Vilimek, D., Mirjalili, S., Pan, J. S., Horakova, J., Martinek, R., & Vilimkova Kahankova, R. (2025). Enhancing Cardiotocography Classification via Ensemble Learning and Threshold Optimization. Scientific Reports, 15(1), 38528. https://doi.org/10.1038/s41598-025-18990-z
Liu, J., Niu, L., Yuan, Z., Yang, D., Wang, X., & Liu, W. (2023). PD-Quant: Post-Training Quantization Based on Prediction Difference Metric. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 24427–24437. https://doi.org/10.1109/CVPR52729.2023.02340
Mdegela, L., Municio, E., De Bock, Y., Luhanga, E., Leo, J., & Mannens, E. (2023). Extreme Rainfall Event Classification Using Machine Learning for Kikuletwa River Floods. Water, 15(6), 1021. https://doi.org/10.3390/w15061021
Putra, M., Rosid, M. S., & Handoko, D. (2024). High-Resolution Rainfall Estimation Using Ensemble Learning Techniques and Multisensor Data Integration. Sensors, 24(15), 5030. https://doi.org/10.3390/s24155030
Rachmawardani, A., Wijaya, S. K., & Shopaheluwakan, A. (2022). Sistem Peringatan Dini Banjir Berbasis Machine Learning: Studi Literatur. METHOMIKA: Jurnal Manajemen Informatika dan Komputerisasi Akuntansi, 6(2), 188–198. https://doi.org/10.46880/jmika.Vol6No2.pp188-198
Rajaraman, S., Ganesan, P., & Antani, S. (2022). Deep Learning Model Calibration for Improving Performance in Class-Imbalanced Medical Image Classification Tasks. PLOS ONE, 17(1), e0262838. https://doi.org/10.1371/journal.pone.0262838
Rizal, M. E., Wigena, A. H., & Afendi, F. M. (2022). Time Series Imputation Using VAR-IM (Case Study: Weather Data in Meteorological Station of Citeko). Barekeng, 16(4), 1373–1384. https://doi.org/10.30598/barekengvol16iss4pp1373-1384
Rozzy, F., Candra Rini Novitasari, D., Yuliati, D., & Permata Sani, P. (2024). Forecasting Sea Surface Salinity in the Eastern Madura Strait Using 1D Convolutional Neural Network. Jurnal Informatika dan Teknologi Informasi, 21(1), 14–30. https://doi.org/10.31515/telematika.v21i1.8959
Shantal, M., Othman, Z., & Bakar, A. A. (2023). A Novel Approach for Data Feature Weighting Using Correlation Coefficients and Min–Max Normalization. Symmetry, 15(12), 2185. https://doi.org/10.3390/sym15122185
Taheri Moghadar, S., Gandolfi, R., & Torti, E. (2025). TinyML-Based Real-Time Doorway Activity Recognition with a Time-of-Flight Sensor. Electronics, 14(17), 3533. https://doi.org/10.3390/electronics14173533
Ullah, S., Ullah, N., Siddique, M. F., Ahmad, Z., & Kim, J. M. (2024). Spatio-Temporal Feature Extraction for Pipeline Leak Detection in Smart Cities Using Acoustic Emission Signals: A One-Dimensional Hybrid Convolutional Neural Network–Long Short-Term Memory Approach. Applied Sciences (Switzerland), 14(22). https://doi.org/10.3390/app142210339
Widiputro, R. (2022). Klasifikasi time-series data hujan harian dengan metode deep learning 1D-CNN dan LSTM pada Stasiun Soekarno Hatta, Tangerang, Indonesia [Universitas Mercu Buana]. https://repository.mercubuana.ac.id/69137/
World Meteorological Organization. (2024). Guide to Instruments and Methods of Observation Volume I-Measurement of Meteorological Variables. https://library.wmo.int/viewer/68695/
Yu, W., Sun, Y., Yue, Z., Li, Z., & Liu, Y. (2026). An Architecture-Feature-Enhanced Decision Framework for Deep Learning-Based Prediction of Extreme and Imbalanced Precipitation. Water (Switzerland), 18(2). https://doi.org/10.3390/w18020176
Zaidi, S. A. R., Hayajneh, A. M., Hafeez, M., & Ahmed, Q. Z. (2022). Unlocking Edge Intelligence Through Tiny Machine Learning (TinyML). IEEE Access, 10, 100867–100877. https://doi.org/10.1109/ACCESS.2022.3207200
Zhang, Y., Long, M., Chen, K., Xing, L., Jin, R., Jordan, M. I., & Wang, J. (2023). Skilful nowcasting of extreme precipitation with NowcastNet. Nature, 619(7970), 526–532. https://doi.org/10.1038/s41586-023-06184-4
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Revangga Kusuma Dhani, Agustina Rachmawardani, Marzuki Sinambela, Adi Widiatmoko Wastumirad
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Penulis yang menerbitkan jurnal ini menyetujui ketentuan berikut:
1. Penulis memegang hak cipta dan memberikan hak jurnal mengenai publikasi pertama dengan karya yang dilisensikan secara bersamaan di bawah Creative Commons Attribution 4.0 International License. yang memungkinkan orang lain untuk berbagi karya dengan pengakuan atas karya penulis dan publikasi awal pada jurnal.
2. Penulis dapat memasukkan pengaturan kontrak tambahan yang terpisah untuk distribusi non-eksklusif dari versi jurnal yang diterbitkan (misalnya, mengirimkannya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan atas publikasi awalnya pada Jurnal.
3. Penulis diizinkan dan didorong untuk memposting karya mereka secara online (misalnya, dalam penyimpanan institusional atau di situs web mereka) sebelum dan selama proses pengiriman, karena hal itu dapat menghasilkan pertukaran yang produktif, serta kutipan dari karya yang diterbitkan sebelumnya.
