Model Convolutional Neural Network yang Efektif dan Efisien untuk Segmentasi Semantik Awan Cumulonimbus
DOI:
https://doi.org/10.51577/acsijournal.v3i1.807Keywords:
Convolutional Neural Network, Segmentasi Semantik Awan Cumulonimbus, Gradient Discent Optimizer, Weighted Class, Data AugmentationAbstract
Awan Cumulonimbus (CB) merupakan jenis awan yang dapat mengakibatkan petir, badai, tornado, hujan lebat, turbulensi penerbangan, dan cuaca ekstrim lainnya. Oleh karenanya, prediksi/deteksi keberadaan awan CB yang akurat dan real time akan mendukung kelancaran dan keselamatan banyak aktivitas manusia. Citra infrared (IR) pada satelit Himawari-8 di Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) memiliki informasi mengenai pertumbuhan awan CB. Berbagai studi terkait telah membuktikan bahwa metode yang paling populer dan handal dalam bidang computer vision pada objek awan adalah Convolutional Neural Network (CNN). Untuk menemukan/memperoleh model CNN yang paling efektif dan efisien dalam menangani segmentasi semantik awan CB pada citra IR Himawari-8, maka berbagai pendekatan untuk CNN diuji coba, diantaranya arsitektur jaringan untuk CNN, optimalisasi pelatihan CNN berbasis Gradient Discent Optimizer (GDO), Weighted Class (WC) untuk mereduksi masalah imbalanced class, dan Data Augmentation (DA) untuk memperkaya keragaman data dan mencegah overfitting. Hasil studi menunjukkan bahwa model CNN yang paling efektif adalah dengan arsitektur jaringan U-NET, GDO menggunakan Adaptive Moment Estimation (Adam), dan WC dengan 99,56% global akurasi pengujian, 97,12% rata-rata akurasi pengujian, 94,42% rata-rata IoU, 94,48% akurasi prediksi pada class CB, 99,60% akurasi validasi, 99,61% akurasi pelatihan, 0,1071 loss validasi, dan 0.1072 loss pelatihan. Sedangkan model CNN yang paling efisien adalah dengan arsitektur jaringan Dilated, GDO menggunakan Root Mean Square Propagation (RMSProp), dan WC dengan 24 detik waktu proses/pemodelan, lebih cepat 20 detik namun dengan efektivitas yang tidak jauh berbeda daripada model CNN yang paling efektif.
References
Abidin, M. R., Dian candra Rini Novitasari, Hani Khaulasari, & Fajar Setiawan. (2023). Classification of Cumulonimbus Cloud Formation based on Himawari Images using Convolutional Neural Network Model GoogleNet. Jurnal Buana Informatika, 14(2), 127–136. https://doi.org/10.24002/jbi.v14i02.7417
Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S., & Yoon, B. (2020). Improved Handwritten Digit Recognition Using Convolutional Neural Network (CNN). Sensors, 3344(20), 1–18. https://doi.org/10.1504/IJCSM.2023.131625
Akbar, A., & Prajitno, P. (2023). Cumulonimbus cloud prediction using Artificial Neural Network (ANN) based on Grey Wolf Optimizer (GWO). THE 1ST INTERNATIONAL CONFERENCE ON SCIENCE EDUCATION AND SCIENCES. https://doi.org/https://doi.org/10.1063/5.0122544
Bankert, R. L. (1994). Cloud classification of AVHRR imagery in maritime regions using a probabilistic neural network. Journal of Applied Meteorology, 33(8), 909–918. https://doi.org/10.1175/1520-0450(1994)033<0909:CCOAII>2.0.CO;2
BMKG. (2024). Citra Satelit Himawari-8. Badan Meteorologi, Klimatologi, Dan Geofisika (BMKG). https://www.bmkg.go.id/satelit/
Brostow, G. J., Fauqueur, J., & Cipolla, R. (2009). Semantic object classes in video: A high-definition ground truth database. Pattern Recognition Letters, 30(2), 88–97. https://doi.org/10.1016/j.patrec.2008.04.005
Cai, K., & Wang, H. (2018). Cloud Classification of Satellite Image based on Convolutional Neural Networks. Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS, 874–877. https://doi.org/10.1109/ICSESS.2017.8343049
Chattopadhyay, S., Chowdhury, A., Dutta, S. P., Mukhopadhyay, K., Ghosh, J., & De, P. (2024). Cumulonimbus cloud classification using transfer learning with AlexNet. FOURTH INTERNATIONAL CONFERENCE ON ADVANCES IN PHYSICAL SCIENCES AND MATERIALS (ICAPSM). https://doi.org/https://doi.org/10.1063/5.0216143
Chattopadhyay, S., Dutta, S. P., Mishra, S., & Saha, S. (2021). Use of Marker-Controlled Watershed Segmentation to Classify Cumulonimbus Cloud with Pre-trained CNN. Soft Computing: Theories and Applications. Advances in Intelligent Systems and Computing. https://doi.org/https://doi.org/10.1007/978-981-16-1696-9_6
Chattopadhyay, S., Pal, S., Acharjya, P. P., & Bhattacharyya, S. (2021). A Comparative Study to Classify Cumulonimbus Cloud Using Pre-trained CNN. In: Kumar R., Quang N.H., Kumar Solanki V., Cardona M., Pattnaik P.K. (Eds) Research in Intelligent and Computing in Engineering. Advances in Intelligent Systems and Computing. https://doi.org/https://doi.org/10.1007/978-981-15-7527-3_11
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic. ECCV, 833–851. https://doi.org/10.1007/978-3-030-01234-2
Cheng, H. Y., & Yu, C. C. (2015). Multi-model solar irradiance prediction based on automatic cloud classification. Energy, 91, 579–587. https://doi.org/10.1016/j.energy.2015.08.075
Cote, M. P. (2022). Cloud Image Classification Using Machine Learning. Florida Institute of Technology.
Guijo-Rubio, D., Gutiérrez, P. A., Casanova-Mateo, C., Fernández, J. C., Gómez-Orellana, A. M., Salvador-González, P., Salcedo-Sanz, S., & Hervás-Martínez, C. (2020). Prediction of convective clouds formation using evolutionary neural computation techniques. Neural Computing and Applications, 32(17), 13917–13929. https://doi.org/10.1007/s00521-020-04795-w
Jin, W., Wang, L., Zeng, X., Liu, Z., & Fu, R. (2014). Classification of clouds in satellite imagery using over-complete dictionary via sparse representation. Pattern Recognition Letters, 49, 193–200. https://doi.org/10.1016/j.patrec.2014.07.015
Juncklaus Martins, B., Marian Arrais, J., Perello Ricci Neto, G., Cerentini, A., Mantelli, S., & von Wangenheim, A. (2023). Semantic Segmentation of Cloud Images captured with Horizon-Oriented Cameras for Nowcasting Applications. Research Square. https://doi.org/10.21203/rs.3.rs-3072958/v1
Lee, J., Weger, R. C., Sengupta, S. K., & Welch, R. M. (1990). A Neural Network Approach to Cloud Classification. IEEE Transactions on Geoscience and Remote Sensing, 28(5), 846–855. https://doi.org/10.1109/36.58972
Liu, Y., Xia, J., Shi, C. X., & Hong, Y. (2009). An improved cloud classification algorithm for China’s FY-2C multi-channel images using artificial neural network. Sensors, 9(7), 5558–5579. https://doi.org/10.3390/s90705558
Martus, C., & Johnson, B. (2024). Deep-learning-based cloud segmentation and classification for weather monitoring. Remote Sensing of Clouds and the Atmosphere XXIX. https://doi.org/https://doi.org/10.1117/12.3031208
Nataraja, V., Schmidt, S., Chen, H., Yamaguchi, T., Kazil, J., Feingold, G., Wolf, K., & Iwabuchi, H. (2022). Segmentation-based multi-pixel cloud optical thickness retrieval using a convolutional neural network. Atmospheric Measurement Techniques, 15(17), 5181–5205. https://doi.org/10.5194/amt-15-5181-2022
Noia, A. Di, & Hasekamp, O. P. (2018). Neural Networks and Support Vector Machines and Their Application to Aerosol and Cloud Remote Sensing: A Review. Kokhanovsky A. (Eds) Springer Series in Light Scattering. Springer Series in Light Scattering. https://doi.org/https://doi.org/10.1007/978-3-319-70796-9_4
Nugraheny, D. (2015). Metode Nilai Jarak Guna Kesamaan Atau Kemiripan Ciri Suatu Citra (Kasus Deteksi Awan Cumulonimbus Menggunakan Principal Component Analysis). Angkasa: Jurnal Ilmiah Bidang Teknologi, 7(2), 21. https://doi.org/10.28989/angkasa.v7i2.145
Nurrani, H., Nugroho, A. K., & Heranurweni, S. (2023). Image Classification of Vegetable Quality using Support Vector Machine based on Convolutional Neural Network. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 7(1), 168–178. https://doi.org/10.29207/resti.v7i1.4715
Omar, M. B., Ibrahim, R. Bin, Bingi, K., Sambaragi, S., Deshannavar, U., & Anawar, M. A. Bin. (2023). Convective Cloud Classification System using Convolution Neural Network. IEEE International Conference on Computing (ICOCO). https://doi.org/10.1109/ICOCO59262.2023.10397598
Purbantoro, B., Aminuddin, J., Manago, N., Toyoshima, K., Tetuko, J., Sumantyo, S., & Kuze, H. (2019). Evaluation of Cloud Type Classification based on Split Window Algorithm using Himawari-8 Satellite Data. IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, 170–173.
Putra, Angie; Lursinsap, C. (2014). Cumulonimbues Prediction Using Artificial Neural Network Back Propagation with Radiosome Indeces. National Remote Sensing Seminar, 96(24), 7549–7551.
Putra, R. M., Fibriantika, E., Herawati, H., Kusumayanti, Y., Afriani, E., Hidayanti, A., Wiujiana, A., Swastiko, W. A., & Andrianto, D. (2021). Cumulonimbus cloud prediction based on machine learning approach using radiosonde data in Surabaya, Indonesia. IOP Conference Series: Earth and Environmental Science, 724(1). https://doi.org/10.1088/1755-1315/724/1/012047
Rais, A. F., Putra, R. M., Fitrianto, M. A., & Hermansyah, T. (2022). A Preliminary Comparative Study on the Feasibility of a Multipurpose Numerical Weather Model for Prediction of Cumulonimbus Clouds in Indonesia. International Conference on Science and Technology (ICOSTECH). https://doi.org/10.1109/ICOSTECH54296.2022.9829049
Rajendiran, N., Sebastian, S., & Kumar, L. S. (2024). Cloud Segmentation, Validation of Weather Data, and Precipitation Prediction Using Machine Learning Algorithms. Arabian Journal for Science and Engineering, 49, 12259–12289. https://link.springer.com/article/10.1007/s13369-023-08611-0
Rozi, M. F. (2019). Prediksi Pertumbuhan Awan Cumulonimbus pada Citra Himawari IR Enhanced Menggunakan Deep Echo State Network (DEEPESN). Universitas Islam Negeri Sunan Ampel.
Rudi, A. (2014). 2014, Rudi, Hilangnya pesawat. Compas.Com. https://nasional.kompas.com/read/2014/12/29/18163231/BMKG.Ungkap.Alasan.Awan.Kumulonimbus.Bahaya.untuk.Penerbangan
Sebastian, S., Kumar, L. S., & Annadurai, P. (2021). Segmentation of satellite images using machine learning algorithms for cloud classification. Indian Journal of Radio and Space Physics, 50(1), 12–18.
Segal-Rozenhaimer, M., Li, A., Das, K., & Chirayath, V. (2020). Cloud detection algorithm for multi-modal satellite imagery using convolutional neural-networks (CNN). Remote Sensing of Environment, 237. https://doi.org/10.1016/j.rse.2019.111446
Shen, X., Tian, X., Liu, T., Xu, F., & Tao, D. (2018). Continuous Dropout. IEEE Transactions on Neural Networks and Learning Systems, 29(9), 3926–3937. https://doi.org/10.1109/TNNLS.2017.2750679
Shi, G., & Zuo, B. (2022). CloudRCNN: A Framework Based on Deep Neural Networks for Semantic Segmentation of Satellite Cloud Images. Applied Sciences (Switzerland), 12(11). https://doi.org/10.3390/app12115370
Sinko, M., Kamencay, P., Sykora, P., Benco, M., & Hudec, R. (2019). Cloud-type classification of ground-based images using deep learning. ICETA 2019 - 17th IEEE International Conference on Emerging ELearning Technologies and Applications, Proceedings, 715–720. https://doi.org/10.1109/ICETA48886.2019.9040149
Tapakis, R., & Charalambides, A. G. (2012). Equipment and methodologies for cloud detection and classification: A review. Solar Energy, 95, 392–430. https://doi.org/10.1016/j.solener.2012.11.015
Uddstrom, M. J., & Gray, W. R. (1996). Satellite cloud classification and rain-rate estimation using multispectral radiances and measures of spatial texture. In Journal of Applied Meteorology (Vol. 35, Issue 6, pp. 839–858). https://doi.org/10.1175/1520-0450(1996)035<0839:SCCARR>2.0.CO;2
Wanayumini. (2021). Supervised Image Classification untuk Fenomena Chaos Angin Puting Beliung Berdasarkan Average Correlation Angle [Universitas Sumatera Utara]. https://doi.org/10.1007/0-306-47647-9_9
Wang, C., Platnick, S., Meyer, K., Zhang, Z., & Zhou, Y. (2020). A machine-learning-based cloud detection and thermodynamic-phase classification algorithm using passive spectral observations. Atmospheric Measurement Techniques, 13(5), 2257–2277. https://doi.org/10.5194/amt-13-2257-2020
Wang, Q., & Fan, W. (2010). Cumulonimbus forecasting based on rough set and artificial immune algorithm. Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010, 6, 2856–2860. https://doi.org/10.1109/ICNC.2010.5584020
Yuwana, R. S., Fauziah, F., Heryana, A., Krisnandi, D., Kusumo, R. B. S., & Pardede, H. F. (2020). Data Augmentation using Adversarial Networks for Tea Diseases Detection. Jurnal Elektronika Dan Telekomunikasi, 20(1), 29–35. https://doi.org/10.14203/jet.v20.29-35
Zhang, J., Liu, P., Zhang, F., & Song, Q. (2018). CloudNet: Ground-Based Cloud Classification With Deep Convolutional Neural Network. Geophysical Research Letters, 45(16), 8665–8672. https://doi.org/10.1029/2018GL077787
Zhang, S., Bao, Y., Zhou, P., Jiang, H., & Dai, L. (2014). Improving Deep Neural Network for LVCSR using Dropout and Shrinking Structure. IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), 6899–6903.
Zhang, Z., Ma, Y., Li, Y., Li, F. W. B., Shum, H. P. H., Yang, B., Guo, J., & Liang, X. (2020). Cumuliform cloud formation control using parameter-predicting convolutional neural network. Graphical Models, 111(July), 101083. https://doi.org/10.1016/j.gmod.2020.101083
Zhao, M., Chang, C. H., Xie, W., Xie, Z., & Hu, J. (2020). Cloud Shape Classification System Based on Multi-Channel CNN and Improved FDM. IEEE Access, 8, 44111–44124. https://doi.org/10.1109/ACCESS.2020.2978090
Zhu, T., Wei, L., & Guo, Y. (2021). Cloud classification of ground-based cloud images based on convolutional neural network. Journal of Physics: Conference Series, 2035(1). https://doi.org/10.1088/1742-6596/2035/1/012020
Published
Issue
Section
Copyright (c) 2025 Azminuddin I. S. Azis, jeffry jeffry, Firman Aziz, Andi Taufiqurrahman Akbar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Make A Submission 
