Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 22, 2025
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2025, V. 22, No. 6, pp. 52-65

Nowcasting of cloud motion based on Himawari-8/9 satellite data using the HybridCloudCast hybrid neural network model

V.D. Bloshchinskiy 1, 2 , S.I. Malkovsky 1 , L.S. Kramareva 1, 2 , A.V. Boroditskaya 1, 2 , S.P. Korolev 1 
1 Computing Center FEB RAS, Khabarovsk, Russia
2 Far Eastern Center of SRC "Planeta", Khabarovsk, Russia
Accepted: 29.09.2025
DOI: 10.21046/2070-7401-2025-22-6-52-65
The paper presents an algorithm for nowcasting cloud motion in the Asia-Pacific region using infrared satellite imagery from the geostationary Himawari-8/9 satellites. The algorithm is based on the HybridCloudCast hybrid neural network model, developed by the authors, which combines the advantages of deterministic and statistical approaches in short-term forecasting. The deterministic component ensures accurate prediction of cloud evolution through the use of a physically grounded model, while the statistical component, implemented via a diffusion neural network, enhances the detail and visual quality of forecasted images. HybridCloudCast uses input images containing brightness temperature values from channel 14 of the AHI instrument. In addition to satellite imagery, the neural network model incorporates a cloud-free composite to improve forecast accuracy by accounting for the brightness characteristics of the underlying surface. The developed HybridCloudCast model generates short-term forecasts with a temporal resolution of 10 minutes and a spatial resolution of 2 km. Validation results show that the proposed algorithm is comparable in accuracy to existing methods, while offering higher temporal resolution. The model is capable of producing forecast images over a three-hour forecast horizon with a Root Mean Squared Error (RMSE) not exceeding 12 K and a correlation coefficient of at least 0.84.
Keywords: nowcasting, cloudiness, neural network, Himawari, HybridCloudCast
Full text

References:

  1. Kuchma M. O., Malkovsky S. I., Andreev A. I., Bloshchinsky V. D., Neural network approaches to precipitation nowcasting: A review and test of existing methods, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, V. 20, No. 6, pp. 35–48, DOI: 10.21046/2070-7401-2023-20-6-35-48.
  2. Baker S., Matthews I., Lucas‒Kanade 20 years on: A unifying framework, Intern. J. Computer Vision, 2004, V. 56, pp. 221–255, DOI: 10.1023/B:VISI.0000011205.11775.fd.
  3. Chen T., On the importance of noise scheduling for diffusion models, https://arxiv.org/, arXiv:2301.10972, 2023, 12 p., DOI: 10.48550/arXiv.2301.10972.
  4. Chen H., Shi X., Nie X. et al., Tropical aviation turbulence induced by the interaction between a jet stream and deep convection, J. Geophysical Research: Atmospheres, 2024, V. 129, Iss. 18, Article e2024JD04076, DOI: 10.1029/2024JD040763.
  5. Chen H., Zhong X., Zhai Q. et al., Skillful nowcasting of convective clouds with a cascade diffusion model, https://arxiv.org/, arXiv:2502.10957, 2025, 15 p., DOI: 10.48550/arXiv.2502.10957.
  6. Chen L., Zhong X., Li H. et al., A machine learning model that outperforms conventional global subseasonal forecast models, Nature Communications, 2024, V. 15, Article 6425, DOI: 10.1038/s41467-024-50714-1.
  7. Ehsani M. R., Zarei A., Gupta H. V. et al., NowCasting-nets: Representation learning to mitigate latency gap of satellite precipitation products using convolutional and recurrent neural networks, IEEE Trans. Geoscience and Remote Sensing, 2022, V. 60, Article 4706021, 21 p., DOI: 10.1109/TGRS.2022.3158888.
  8. Gong J., Bai L., Ye P., Xu W., Liu N., Dai J., Yang X., Ouyang W., Cascast: Skillful high-resolution precipitation nowcasting via cascaded modelling, Proc. 41 st Intern. Conf. on Machine Learning, 2024, Article 633, pp. 15809–15822.
  9. Guo Y., Zhong M., Chen X. et al., A thunderstorm gale forecast method based on the objective classification and continuous probability, Atmosphere, 2022, V. 13, No. 8, Article 1308, DOI: 10.3390/atmos13081308.
  10. Heusel M., Ramsauer H., Unterthiner T. et al., GANs trained by a two time-scale update rule converge to a local Nash equilibrium, https://arxiv.org/, arXiv:1706.08500, 2018, 38 p., DOI: 10.48550/arXiv.1706.08500.
  11. Kingma D. P., Ba J. L., Adam: A method for stochastic optimization, https://arxiv.org/, arXiv:1412.6980v9, 2017, 15 p., DOI: 10.48550/arXiv.1412.6980.
  12. Leinonen J., Hamann U., Nerini D. et al., Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification, https://arxiv.org/, arXiv:2304.12891, 2023, 18 p., DOI: 10.48550/arXiv.2304.12891.
  13. Nai C., Pan B., Chen X. et al., Reliable precipitation nowcasting using probabilistic diffusion models, Environmental Research Letters, 2024, V. 19, No. 3, Article 034039, DOI: 10.1088/1748-9326/ad2891.
  14. Peebles W., Xie S., Scalable diffusion models with transformers, IEEE/CVF Intern. Conf. on Computer Vision (ICCV), Paris, France, 2023, pp. 4195–4205, DOI: 10.1109/ICCV51070.2023.00387.
  15. Prudden R., Adams S., Kangin D. et al., A review of radar-based nowcasting of precipitation and applicable machine learning techniques, https://arxiv.org/, arXiv:2005.04988, 2020, 17 p., DOI: 10.48550/arXiv.2005.04988.
  16. Shi X., Chen Z., Wang H., Yeung D., Wong W., Woo W., Convolutional LSTM Network: A machine learning approach for precipitation nowcasting, Proc. 29 th Intern. Conf. on Neural Information Processing Systems, 2015, V. 1, pp. 802–810.
  17. Smith J., Birch C., Marsham J. et al., Evaluating pySTEPS optical flow algorithms for convection nowcasting over the Maritime Continent using satellite data, Natural Hazards and Earth System Sciences, 2024, V. 24, pp. 567–582, DOI: 10.5194/nhess-24-567-2024.
  18. Tran Q.-K., Song S.-k., Computer vision in precipitation nowcasting: Applying image quality assessment metrics for training deep neural networks, Atmosphere, 2019, V. 10, No. 5, Article 244, DOI: 10.3390/atmos10050244.
  19. Wang R., Su L., Wong W. K. et al., Skillful radar-based heavy rainfall nowcasting using task-segmented generative adversarial network, IEEE Trans. Geoscience and Remote Sensing, 2023, V. 61, Article 4103613, 13 p., DOI: 10.1109/TGRS.2023.3295211.
  20. Wang Y., Wu H., Zhang J. et al., PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning, IEEE Trans. Pattern Analysis and Machine Intelligence, 2023, V. 45, No. 2, pp. 2208–2225, DOI: 10.1109/TPAMI.2022.3165153.
  21. Wei X., Zhang F., Zhang R. et al., DaYu: Data-driven model for geostationary satellite observed cloud images forecasting, https://arxiv.org/, arXiv:2411.10144, 2024, 12 p., DOI: 10.48550/arXiv.2411.10144.
  22. Wen P., He M., Filippi P., DuoCast: Duo-probabilistic diffusion for precipitation nowcasting, https://arxiv.org/, arXiv:2412.01091, 2025, 9 p., DOI: 10.48550/arXiv.2412.01091.
  23. Wood-Bradley P., Zapata J., Pye J., Cloud tracking with optical flow for short-term solar forecasting, Proc. 50 th Annual AuSES Conf. (Solar 2012), Australian Solar Energy Soc., 2012, 6 p.
  24. Zhang Y., Long M., Chen K. et al., Skilful nowcasting of extreme precipitation with NowcastNet, Nature, 2023, V. 619, pp. 526–532, DOI: 10.1038/s41586-023-06184-4.
  25. Zhuk S., Tchrakian T., Akhriev A. et al., Where computer vision can aid physics: dynamic cloud motion forecasting from satellite images, https://arxiv.org/, arXiv:1710.00194, 2017, 17 p., DOI: 10.48550/arXiv.1710.00194.