YOLOv8-Based Detection of Convective Storm Clouds for Cumulonimbus Classification
Article Sidebar
Keywords:
aviation safety, cloud detection cumulonimbus clouds, deep learning, YOLOv8
Main Article Content
Abstract
Cumulonimbus (CB) clouds are vertically developed convective systems that are capable of producing severe weather phenomena, including turbulence, heavy rainfall, and lightning. These phenomena pose a significant threat to aviation safety. This paper considers an automated CB cloud detection approach using the deep learning algorithm You Only Look Once version 8 on NOAA-19 satellite imagery. The images of 640 × 640 pixels each were labeled into two classes: CB and non-CB. In general, rotation, flip, and random brightening are performed to develop a more robust model. After 100 training epochs, the proposed model produced reliable detection performance, as evidenced by 1,694 TP (true positives), 438 FP (false positives), and 304 FN (false negatives) cases, with a precision of 0.79, recall of 0.84, and an F1-score of 0.81. Validation using METAR reports from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG) confirmed the consistency of the model with observed weather conditions. The results demonstrated that YOLOv8 could provide a rapid and reliable framework for real-time detection and classification of CB clouds, thereby enhancing situational awareness for aviation operations and facilitating the effectiveness of satellite-based early warning systems in convectively active tropical regions.
Downloads
Download data is not yet available.
Article Details
How to Cite
Rafsyam, Y., Nurjihan, S. F., & Rinaldi, A. (2025). YOLOv8-Based Detection of Convective Storm Clouds for Cumulonimbus Classification. Communications in Science and Technology, 10(2), 467–476. https://doi.org/10.21924/cst.10.2.2025.1854
Issue
Section
Articles
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
1. C. Henken, M. Schmeits, H. Deneke, and R. Roebeling, Using MSG-SEVIRI cloud physical properties and weather radar observations for the detection of CB/TCU clouds, J. Appl. Meteorol. Climatol. 50 (2011) 349–365.
2. S. Mahajan and B. Fataniya, Cloud detection methodologies: Variants and development A review, Complex & Intelligent Systems. 6 (2020) 1–11.
3. K. M. Bedka et al., Objective satellite-based detection of overshooting tops using infrared window channel brightness temperature gradients, J. Appl. Meteorol. Climatol. 49 (2010) 181–202
4. M. Kim, J. Lee, and J. Im, Deep learning-based monitoring of overshooting cloud tops from geostationary satellite data, GIScience & Remote Sensing. 55 (2018) 763–792.
5. R. Dorfman et al, Spatio-temporal detection of cumulonimbus clouds in infrared satellite images, in Proc. IEEE Int. Conf. Science of Electrical Engineering in Israel (2018) 1–5.
6. P. Jiang et al, A review of YOLO algorithm developments, Procedia Computer Science. 199 (2022) 1066–1073.
7. M.-T, Pham et al, YOLO-fine: One-stage detector of small objects under various backgrounds in remote sensing images, Remote Sensing. vol. 12. no. 15 (2020) 2501.
8. G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLOv8, GitHub (2023).
9. K. Wada, LabelMe: Image polygonal annotation with Python, GitHub (2018).
10. Y. Zhang, S. Wistar, J. Li, M. A. Steinberg, and J. Z. Wang, Severe thunderstorm detection by visual learning using satellite images, IEEE Trans. Geosci. Remote Sens. 55 (2017) 1052.
11. M. Dewan et al, Detection of thunderstorm and its associated weather from satellite image using texture features, International Conference on Informatics, Electronics & Vision (2012) 594–598.
12. N. Aswin et al, Application of machine learning in cloud classification using satellite images, International Journal of Emerging Trends in Engineering Research, 8 (2020) 2751–2755.
13. T. Zhenwei and Z. Yadong, Remote sensing image object detection based on improved YOLOv3, EURASIP Journal on Image and Video Processing. 2020 (2020).
14. R. L. Bankert et al, Automatic cloud type classification using passive satellite data: a comparison of neural network and nearest neighbour approaches, Journal of Applied Meteorology and Climatology. 48 (2009) 1965–1981.
15. K. Khoshelham et al, A review of deep learning applications in satellite remote sensing, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-4/W18 (2020) 305–310.
16. B. Baum, V. Tovinkere, J. Titlow, dan R. Welch, Automated cloud classification of global AVHRR data using a fuzzy logic approach, J. Appl. Meteor. 36 (1997) 1519–1540.
17. R. Bankert, Cloud classification of AVHRR imagery in maritime regions using a probabilistic neural network, J. Appl. Meteor. 33 (1994) 909–918.
18. T. Berendes, J. Mecikalski, W. MacKenzie Jr., K. Bedka, dan U. Nair, Convective cloud identification and classification in daytime satellite imagery using standard deviation limited adaptive clustering, J. Geophys. Res. 113 (2008).
19. M. Donovan et al, The identification and verification of hazardous convective cells over oceans using visible and infrared satellite observations, 12th Conf. on Aviation Range and Aerospace Meteorology. AMS (2006).
20. C. K. Carbajal Henken, M. J. Schmeits, E. L. A. Wolters, dan R. A. Roebeling, Detection of Cb and TCu clouds using MSG-SEVIRI cloud physical properties and weather radar observations, KNMI WR 2009-04 (2009).
21. Li, C. et al, YOLOv6: A Single-Stage Object Detection Framework, arXiv:2209.02976 (2022).
22. He, K. et al, Spatial Pyramid Pooling in Deep Convolutional Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37 (2015) 1904–1917.
23. Lin, T.Y. et al, Feature pyramid networks for object detection, CVPR (2017).
24. Misra, D, Mish: A self regularized nonmonotonic neural activation function, arXiv:1908.08681 ( 2019).
25. Zheng, Z. et al, Distance-IoU Loss: Faster and better learning for bounding box regression, Association for the Advancement of Artificial Intelligence ( 2020).
26. J. Mecikalski dan K. Bedka, Forecasting convective initiation by monitoring the evolution of moving cumulus in daytime GOES imagery, Mon. Wea. Rev. 134 (2006) 49–78.
27. D. Rosenfeld, W. Woodley, A. Lerner, G. Kelman, dan D. Lindsey, Satellite detection of severe convective storms by their retrieved vertical profiles of cloud particle effective radius and thermodynamic phase, J. Geophys. Res. 113 (2008) D04208.
28. T. Zinner, H. Mannstein, dan A. Tafferner, Cb-TRAM: Tracking and monitoring severe convection from onset over rapid development to mature phase using multi-channel Meteosat-8 SEVIRI data, Meteor. Atmos. Phys. 101 (2008) 191–210.
29. J. Schmetz, S. Tjemkes, M. Gube, dan L. Van de Berg, Monitoring deep convection and convective overshooting with Meteosat, Adv. Space Res. 19 (1997) 433–441.
30. V. Levizzani dan M. Setvák, Multispectral, high-resolution satellite observations of plumes on top of convective storms, J. Atmos. Sci. 53 (1996) 361–369.
31. P. Alvira, E. Tomas-Pejo, M. Ballesteros and M. J. Negro, Pretreatment technologies for an efficient bioethanol production process based on enzymatic hydrolisis: A review, Bioresour. Technol. 101 (2010) 4851-4861.
32. B. Kun-Cahyonoa, M. Hidayatul-Ummaha, R. Andarua, N. Andikab, A. Pamungkasc, H. Hapsari-Handayanid, P. Atmodiwirjoe, R. Nathan, Leveraging machine learning and open accessed remote sensing data for precise rainfall forecasting, Commun. Sci. Technol. 10 (2025) 135–147.
33. Y. Rafsyam, L. G. Oktariza, I. Z. Jonifan, and E. E. Khairas, Identification of Cumulonimbus Cloud using Sensor Data of NOAA Satellite Captured by Low Cost Flower Cross Dipole, Annual Southeast Asian International Seminar (2022).
2. S. Mahajan and B. Fataniya, Cloud detection methodologies: Variants and development A review, Complex & Intelligent Systems. 6 (2020) 1–11.
3. K. M. Bedka et al., Objective satellite-based detection of overshooting tops using infrared window channel brightness temperature gradients, J. Appl. Meteorol. Climatol. 49 (2010) 181–202
4. M. Kim, J. Lee, and J. Im, Deep learning-based monitoring of overshooting cloud tops from geostationary satellite data, GIScience & Remote Sensing. 55 (2018) 763–792.
5. R. Dorfman et al, Spatio-temporal detection of cumulonimbus clouds in infrared satellite images, in Proc. IEEE Int. Conf. Science of Electrical Engineering in Israel (2018) 1–5.
6. P. Jiang et al, A review of YOLO algorithm developments, Procedia Computer Science. 199 (2022) 1066–1073.
7. M.-T, Pham et al, YOLO-fine: One-stage detector of small objects under various backgrounds in remote sensing images, Remote Sensing. vol. 12. no. 15 (2020) 2501.
8. G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLOv8, GitHub (2023).
9. K. Wada, LabelMe: Image polygonal annotation with Python, GitHub (2018).
10. Y. Zhang, S. Wistar, J. Li, M. A. Steinberg, and J. Z. Wang, Severe thunderstorm detection by visual learning using satellite images, IEEE Trans. Geosci. Remote Sens. 55 (2017) 1052.
11. M. Dewan et al, Detection of thunderstorm and its associated weather from satellite image using texture features, International Conference on Informatics, Electronics & Vision (2012) 594–598.
12. N. Aswin et al, Application of machine learning in cloud classification using satellite images, International Journal of Emerging Trends in Engineering Research, 8 (2020) 2751–2755.
13. T. Zhenwei and Z. Yadong, Remote sensing image object detection based on improved YOLOv3, EURASIP Journal on Image and Video Processing. 2020 (2020).
14. R. L. Bankert et al, Automatic cloud type classification using passive satellite data: a comparison of neural network and nearest neighbour approaches, Journal of Applied Meteorology and Climatology. 48 (2009) 1965–1981.
15. K. Khoshelham et al, A review of deep learning applications in satellite remote sensing, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-4/W18 (2020) 305–310.
16. B. Baum, V. Tovinkere, J. Titlow, dan R. Welch, Automated cloud classification of global AVHRR data using a fuzzy logic approach, J. Appl. Meteor. 36 (1997) 1519–1540.
17. R. Bankert, Cloud classification of AVHRR imagery in maritime regions using a probabilistic neural network, J. Appl. Meteor. 33 (1994) 909–918.
18. T. Berendes, J. Mecikalski, W. MacKenzie Jr., K. Bedka, dan U. Nair, Convective cloud identification and classification in daytime satellite imagery using standard deviation limited adaptive clustering, J. Geophys. Res. 113 (2008).
19. M. Donovan et al, The identification and verification of hazardous convective cells over oceans using visible and infrared satellite observations, 12th Conf. on Aviation Range and Aerospace Meteorology. AMS (2006).
20. C. K. Carbajal Henken, M. J. Schmeits, E. L. A. Wolters, dan R. A. Roebeling, Detection of Cb and TCu clouds using MSG-SEVIRI cloud physical properties and weather radar observations, KNMI WR 2009-04 (2009).
21. Li, C. et al, YOLOv6: A Single-Stage Object Detection Framework, arXiv:2209.02976 (2022).
22. He, K. et al, Spatial Pyramid Pooling in Deep Convolutional Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37 (2015) 1904–1917.
23. Lin, T.Y. et al, Feature pyramid networks for object detection, CVPR (2017).
24. Misra, D, Mish: A self regularized nonmonotonic neural activation function, arXiv:1908.08681 ( 2019).
25. Zheng, Z. et al, Distance-IoU Loss: Faster and better learning for bounding box regression, Association for the Advancement of Artificial Intelligence ( 2020).
26. J. Mecikalski dan K. Bedka, Forecasting convective initiation by monitoring the evolution of moving cumulus in daytime GOES imagery, Mon. Wea. Rev. 134 (2006) 49–78.
27. D. Rosenfeld, W. Woodley, A. Lerner, G. Kelman, dan D. Lindsey, Satellite detection of severe convective storms by their retrieved vertical profiles of cloud particle effective radius and thermodynamic phase, J. Geophys. Res. 113 (2008) D04208.
28. T. Zinner, H. Mannstein, dan A. Tafferner, Cb-TRAM: Tracking and monitoring severe convection from onset over rapid development to mature phase using multi-channel Meteosat-8 SEVIRI data, Meteor. Atmos. Phys. 101 (2008) 191–210.
29. J. Schmetz, S. Tjemkes, M. Gube, dan L. Van de Berg, Monitoring deep convection and convective overshooting with Meteosat, Adv. Space Res. 19 (1997) 433–441.
30. V. Levizzani dan M. Setvák, Multispectral, high-resolution satellite observations of plumes on top of convective storms, J. Atmos. Sci. 53 (1996) 361–369.
31. P. Alvira, E. Tomas-Pejo, M. Ballesteros and M. J. Negro, Pretreatment technologies for an efficient bioethanol production process based on enzymatic hydrolisis: A review, Bioresour. Technol. 101 (2010) 4851-4861.
32. B. Kun-Cahyonoa, M. Hidayatul-Ummaha, R. Andarua, N. Andikab, A. Pamungkasc, H. Hapsari-Handayanid, P. Atmodiwirjoe, R. Nathan, Leveraging machine learning and open accessed remote sensing data for precise rainfall forecasting, Commun. Sci. Technol. 10 (2025) 135–147.
33. Y. Rafsyam, L. G. Oktariza, I. Z. Jonifan, and E. E. Khairas, Identification of Cumulonimbus Cloud using Sensor Data of NOAA Satellite Captured by Low Cost Flower Cross Dipole, Annual Southeast Asian International Seminar (2022).