Articles | Volume 16, issue 8
https://doi.org/10.5194/gmd-16-2167-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-16-2167-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Forecasting tropical cyclone tracks in the northwestern Pacific based on a deep-learning model
Liang Wang
State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, 100029, China
College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing, 100049, China
Bingcheng Wan
School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing, 210044, China
Shaohui Zhou
School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing, 210044, China
Haofei Sun
State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, 100029, China
College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing, 100049, China
Zhiqiu Gao
CORRESPONDING AUTHOR
State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, 100029, China
School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing, 210044, China
Related authors
No articles found.
Yunfan Yang, Wei Han, Haofei Sun, Jun Li, Jiapeng Yan, and Zhiqiu Gao
Atmos. Meas. Tech., 18, 4249–4269, https://doi.org/10.5194/amt-18-4249-2025, https://doi.org/10.5194/amt-18-4249-2025, 2025
Short summary
Short summary
Our research improves satellite-based precipitation monitoring by using deep learning to reconstruct radar observations from passive microwave radiances. Active radar is costly, so we focus on a more accessible approach. Using data from the Fengyun-3G satellite, we successfully tracked severe weather like Typhoon Khanun and heavy rainfall in Beijing in 2023. This method enhances global precipitation data and helps better understand extreme weather.
Xiaoze Xu, Wei Han, Jincheng Wang, Zhiqiu Gao, Fenghui Li, Yan Cheng, and Naifeng Fu
Atmos. Meas. Tech., 18, 1339–1353, https://doi.org/10.5194/amt-18-1339-2025, https://doi.org/10.5194/amt-18-1339-2025, 2025
Short summary
Short summary
Commercial Global Navigation Satellite System (GNSS) radio occultation (RO) satellites are generally cheap and can generate a large volume of globally distributed observations in a short period of time. To evaluate the practical application value of these data, we must assess their quality. We evaluate the quality of YUNYAO RO data. By using the “three-cornered hat” method and comparing with data from Metop-C and COSMIC-2, it was found that the YUNYAO GNSS-RO data are of high quality.
Minghua Liu, Wei Han, Yunfan Yang, Haofei Sun, and Ruoying Yin
EGUsphere, https://doi.org/10.5194/egusphere-2025-680, https://doi.org/10.5194/egusphere-2025-680, 2025
Short summary
Short summary
This research develops a machine learning approach to estimate atmospheric temperature and humidity profiles using satellite and weather data. The results showed that our method could accurately retrieve profiles with a high degree of precision. However, we found some limitations in very humid conditions, suggesting that further improvements to the model are needed. Our findings could help enhance the reliability of atmospheric measurements and contribute to better weather predictions.
Yongbo Zhou, Yubao Liu, Wei Han, Yuefei Zeng, Haofei Sun, Peilong Yu, and Lijian Zhu
Atmos. Meas. Tech., 17, 6659–6675, https://doi.org/10.5194/amt-17-6659-2024, https://doi.org/10.5194/amt-17-6659-2024, 2024
Short summary
Short summary
The study explored differences between the visible reflectance provided by the Fengyun-4A satellite and its equivalent derived from the China Meteorological Administration Mesoscale model using a forward operator. The observation-minus-simulation biases were able to monitor the performance of the satellite visible instrument. The biases were corrected based on a first-order approximation method, which promotes the data assimilation of satellite visible reflectance in real-world cases.
Shaohui Zhou, Chloe Yuchao Gao, Zexia Duan, Xingya Xi, and Yubin Li
Geosci. Model Dev., 16, 6247–6266, https://doi.org/10.5194/gmd-16-6247-2023, https://doi.org/10.5194/gmd-16-6247-2023, 2023
Short summary
Short summary
The proposed wind speed correction model (VMD-PCA-RF) demonstrates the highest prediction accuracy and stability in the five southern provinces in nearly a year and at different heights. VMD-PCA-RF evaluation indices for 13 months remain relatively stable: the forecasting accuracy rate FA is above 85 %. In future research, the proposed VMD-PCA-RF algorithm can be extrapolated to the 3 km grid points of the five southern provinces to generate a 3 km grid-corrected wind speed product.
Jianbin Zhang, Zhiqiu Gao, Yubin Li, and Yuncong Jiang
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2023-187, https://doi.org/10.5194/gmd-2023-187, 2023
Preprint withdrawn
Short summary
Short summary
This study developed a deep learning model called CNN-BiLSTM-AM for convective weather forecasting. The results showed that the CNN-BiLSTM-AM model outperformed traditional machine learning algorithms in predicting convective weather, with higher accuracy as the forecast lead time increased. When compared to subjective forecasts by forecasters, the objective approach of the CNN-BiLSTM-AM model also demonstrated advantages in various metrics.
Zexia Duan, Zhiqiu Gao, Qing Xu, Shaohui Zhou, Kai Qin, and Yuanjian Yang
Earth Syst. Sci. Data, 14, 4153–4169, https://doi.org/10.5194/essd-14-4153-2022, https://doi.org/10.5194/essd-14-4153-2022, 2022
Short summary
Short summary
Land–atmosphere interactions over the Yangtze River Delta (YRD) in China are becoming more varied and complex, as the area is experiencing rapid land use changes. In this paper, we describe a dataset of microclimate and eddy covariance variables at four sites in the YRD. This dataset has potential use cases in multiple research fields, such as boundary layer parametrization schemes, evaluation of remote sensing algorithms, and development of climate models in typical East Asian monsoon regions.
Hamidreza Omidvar, Ting Sun, Sue Grimmond, Dave Bilesbach, Andrew Black, Jiquan Chen, Zexia Duan, Zhiqiu Gao, Hiroki Iwata, and Joseph P. McFadden
Geosci. Model Dev., 15, 3041–3078, https://doi.org/10.5194/gmd-15-3041-2022, https://doi.org/10.5194/gmd-15-3041-2022, 2022
Short summary
Short summary
This paper extends the applicability of the SUEWS to extensive pervious areas outside cities. We derived various parameters such as leaf area index, albedo, roughness parameters and surface conductance for non-urban areas. The relation between LAI and albedo is also explored. The methods and parameters discussed can be used for both online and offline simulations. Using appropriate parameters related to non-urban areas is essential for assessing urban–rural differences.
Shaohui Zhou, Yuanjian Yang, Zhiqiu Gao, Xingya Xi, Zexia Duan, and Yubin Li
Atmos. Meas. Tech., 15, 757–773, https://doi.org/10.5194/amt-15-757-2022, https://doi.org/10.5194/amt-15-757-2022, 2022
Short summary
Short summary
Our research has determined the possible relationship between Weibull natural wind mesoscale parameter c and shape factor k with height under the conditions of a desert steppe terrain in northern China, which has great potential in wind power generation. We have gained an enhanced understanding of the seasonal changes in the surface roughness of the desert grassland and the changes in the incoming wind direction.
Cited articles
Alemany, S., Beltran, J., Perez, A., and Ganzfried, S.: Predicting Hurricane Trajectories Using a Recurrent Neural Network, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2–7 February 2018, Lousiana, USA, 33, 468–475, https://doi.org/10.1609/aaai.v33i01.3301468, 2018.
Ali, M. M., Kishtawal, C. M., and Jain, S.: Predicting cyclone tracks in the north Indian Ocean: An artificial neural network approach, Geophys. Res. Lett., 34, 545–559, https://doi.org/10.1029/2006gl028353, 2007.
Bathla, G.: Stock Price prediction using LSTM and SVR, 2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC), 6–8 November 2020, Himachal Pradesh, India, 211–214, https://doi.org/10.1109/PDGC50313.2020.9315800, 2020.
Boussioux, L., Zeng, C., Guenais, T., and Bertsimas, D.: Hurricane Forecasting: A Novel Multimodal Machine Learning Framework, Weather Forecast., 37, 817–831, https://doi.org/10.1175/WAF-D-21-0091.1, 2022.
Brand, S., Buenafe, C. A., and Hamilton, H. D.: Comparison of Tropical Cyclone Motion and Environmental Steering, Mon. Weather Rev., 109, 908–909, https://doi.org/10.1175/1520-0493(1981)109<0908:cotcma>2.0.co;2, 1981.
Chan, J. and Kepert, J.: Global Perspectives on Tropical Cyclones: From Science to Mitigation, in: World Scientific Series on Asia-Pacific Weather and Climate, World Scientific, 4, 448 pp., https://doi.org/10.1142/7597, 2010.
Chan, J. C.-L.: An Observational Study of the Physical Processes Responsible for Tropical Cyclone Motion, J. Atmos. Sci., 41, 1036–1048, https://doi.org/10.1175/1520-0469(1984)041<1036:aosotp>2.0.co;2, 1984.
Chan, J. C. L., Gray, W. M., and Kidder, S. Q.: Forecasting Tropical Cyclone Turning Motion from Surrounding Wind and Temperature Fields, Mon. Weather Rev., 108, 778–792, https://doi.org/10.1175/1520-0493(1980)108<0778:FTCTMF>2.0.CO;2, 1980.
Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y.: Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 25–29 October 2014, Doha, Qatar, 1724–1734, https://doi.org/10.3115/v1/D14-1179, 2014.
Climate Data Store: Welcome to the Climate Data Store, https://cds.climate.copernicus.eu (last access: 20 April 2023), 2018.
Díaz-Uriarte, R. and Alvarez de Andrés, S.: Gene selection and classification of microarray data using random forest, BMC Bioinformatics, 7, 3, https://doi.org/10.1186/1471-2105-7-3, 2006.
Emanuel, K.: Will Global Warming Make Hurricane Forecasting More Difficult?, B. Am. Meteorol. Soc., 98, 495–501, https://doi.org/10.1175/bams-d-16-0134.1, 2017.
Galarneau, T. J. and Davis, C. A.: Diagnosing Forecast Errors in Tropical Cyclone Motion, Mon. Weather Rev., 141, 405–430, https://doi.org/10.1175/mwr-d-12-00071.1, 2013.
Gao, S., Zhao, P., Pan, B., Li, Y., Zhou, M., Xu, J., Zhong, S., and Shi, Z.: A nowcasting model for the prediction of typhoon tracks based on a long short term memory neural network, Acta Oceanol. Sin., 37, 8–12, https://doi.org/10.1007/s13131-018-1219-z, 2018.
Genuer, R., Poggi, J.-M., and Tuleau-Malot, C.: Variable selection using random forests, Pattern Recogn. Lett., 31, 2225–2236, https://doi.org/10.1016/j.patrec.2010.03.014, 2010.
George, J. E. and Gray, W. M.: Tropical Cyclone Motion and Surrounding Parameter Relationships, J. Appl. Meteorol. Clim., 15, 1252–1264, https://doi.org/10.1175/1520-0450(1976)015<1252:TCMASP>2.0.CO;2, 1976.
Giffard-Roisin, S., Yang, M., Charpiat, G., Kégl, B., and Monteleoni, C.: Fused Deep Learning for Hurricane Track Forecast from Reanalysis Data, Climate Informatics Workshop Proceedings 2018, Boulder, United States, 19 September 2018, https://hal.science/hal-01851001 (last access: 21 September 2018), 69–72, 2018.
Giffard-Roisin, S., Yang, M., Charpiat, G., Kumler Bonfanti, C., Kégl, B., and Monteleoni, C.: Tropical Cyclone Track Forecasting Using Fused Deep Learning From Aligned Reanalysis Data, Front. Big Data, 3, 1, https://doi.org/10.3389/fdata.2020.00001, 2020.
Goerss, J. S.: Tropical Cyclone Track Forecasts Using an Ensemble of Dynamical Models, Mon. Weather Rev., 128, 1187–1193, https://doi.org/10.1175/1520-0493(2000)128<1187:tctfua>2.0.co;2, 2000.
Goldenberg, S. B., Landsea, C. W., Mestas-Nuñez, A. M., and Gray, W. M.: The Recent Increase in Atlantic Hurricane Activity: Causes and Implications, Science, 293, 474–479, https://doi.org/10.1126/science.1060040, 2001.
Graves, A., Jaitly, N., and Mohamed, A.: Hybrid speech recognition with Deep Bidirectional LSTM, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 8–12 December 2013, Olomouc, Czech Republic, 273–278, https://doi.org/10.1109/ASRU.2013.6707742, 2013.
Gray, W. M.: Global View of the Origin of Tropical Disturbances and Storms, Mon. Weather Rev., 96, 669–700, https://doi.org/10.1175/1520-0493(1968)096<0669:GVOTOO>2.0.CO;2, 1968.
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Holland, G. J.: Tropical Cyclone Motion: Environmental Interaction Plus a Beta Effect, J. Atmos. Sci., 40, 328–342, https://doi.org/10.1175/1520-0469(1983)040<0328:tcmeip>2.0.co;2, 1983.
Holland, G. J.: Tropical Cyclone Motion. A Comparison of Theory and Observation, J. Atmos. Sci., 41, 68–75, https://doi.org/10.1175/1520-0469(1984)041<0068:tcmaco>2.0.co;2, 1984.
Huang, C., Bai, C., Chan, S., and Zhang, J.: MMSTN: A Multi-Modal Spatial-Temporal Network for Tropical Cyclone Short-Term Prediction, Geophys. Res. Lett., 49, e2021GL096898, https://doi.org/10.1029/2021gl096898, 2022.
Ioffe, S. and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, in: Proceedings of the 32nd International Conference on International Conference on Machine Learning, The 32nd International Conference on Machine Learning, 6–11 July 2015, Lille, France, 37, 448–456, https://doi.org/10.48550/arXiv.1502.03167, 2015.
Katsube, K. and Inatsu, M.: Response of Tropical Cyclone Tracks to Sea Surface Temperature in the Western North Pacific, J. Climate, 29, 1955–1975, https://doi.org/10.1175/jcli-d-15-0198.1, 2016.
Kim, S., Kang, J.-S., Lee, M., and Song, S.-K.: DeepTC: ConvLSTM Network for Trajectory Prediction of Tropical Cyclone using Spatiotemporal Atmospheric Simulation Data, in: Spatiotemporal Workshop at 31st Conference on Neural Information Processing Systems, 2–8 December 2018, Montréal, Canada, https://openreview.net/pdf?id=HJlCVoPAF7 (last access: 20 April 2023), 2018.
Kitade, T.: A Numerical Study of the Vortex Motion with Barotropic Models, J. Meteorol. Soc. Jpn. Ser. II, 59, 801–807, https://doi.org/10.2151/jmsj1965.59.6_801, 1981.
Klein, B., Wolf, L., and Afek, Y.: A Dynamic Convolutional Layer for short rangeweather prediction, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7–12 June 2015, Boston, US, 4840–4848, https://doi.org/10.1109/CVPR.2015.7299117, 2015.
Krizhevsky, A., Sutskever, I., and Hinton, G.: ImageNet Classification with Deep Convolutional Neural Networks, Neural Information Processing Systems, 3–6 December 2012, Nevada, USA, 25, 84–90, https://doi.org/10.1145/3065386, 2012.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P.: Gradient-Based Learning Applied to Document Recognition, P. IEEE, 86, 2278–2324, https://doi.org/10.1109/5.726791, 1998.
Li-min, S., Gang, F. U., Xiang-chun, C., and Jian, Z.: Application of BP neural network to forecasting typhoon tracks, Journal of Natural Disasters, 18, 104–111, https://doi.org/10.3969/j.issn.1004-4574.2009.06.018, 2009.
Liu, H., Mi, X., and Li, Y.: Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition, singular spectrum analysis, LSTM network and ELM, Energ. Convers. Manage., 159, 54–64, https://doi.org/10.1016/j.enconman.2018.01.010, 2018.
Liu, Z., Hao, K., Geng, X., Zou, Z., and Shi, Z.: Dual-Branched Spatio-Temporal Fusion Network for Multihorizon Tropical Cyclone Track Forecast, IEEE J. Sel. Top. Appl., 15, 3842–3852, https://doi.org/10.1109/JSTARS.2022.3170299, 2022.
Lownam, C.: The NCAR-AFWA tropical cyclone bogussing scheme. A report prepared for the Air Force Weather Agency (AFWA), National Center for Atmospheric Research, https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=45979165eea27836ac82671f2e5dedb275eabcab (last access: 20 April 2023), 2001.
Moradi Kordmahalleh, M., Gorji Sefidmazgi, M., Homaifar, A., and Liess, S.: Hurricane Trajectory Prediction Via a Sparse Recurrent Neural Network, in: Proceedings of the 5th International Workshop on Climate Informatics, 19–21 September 2015, Boulder, USA, 2–3, https://www.researchgate.net/publication/320456406_Hurricane_Trajectory_Prediction_Via_a_Sparse_Recurrent_Neural_Network (last access: 20 April 2023), 2015.
Neumann, C. J. and Hope, J. R.: Performance Analysis of the HURRAN Tropical Cyclone Forecast System, Mon. Weather Rev., 100, 245–255, https://doi.org/10.1175/1520-0493(1972)100<0245:paotht>2.3.co;2, 1972.
NOAA: Index of /data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r00, https://www.ncei.noaa.gov/data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r00/access/netcdf/IBTrACS.WP.v04r00.nc (last access: 20 April 2023), 2009.
Ortega, L. C., Otero, L. D., Solomon, M., Otero, C. E., and Fabregas, A.: Deep learning models for visibility forecasting using climatological data, Int. J. Forecasting, 39, 992–1004, https://doi.org/10.1016/j.ijforecast.2022.03.009, 2022.
Roy, C. and Kovordányi, R.: Tropical cyclone track forecasting techniques – A review, Atmos. Res., 104–105, 40–69, https://doi.org/10.1016/j.atmosres.2011.09.012, 2012.
Ruttgers, M., Lee, S., Jeon, S., and You, D.: Prediction of a typhoon track using a generative adversarial network and satellite images, Sci. Rep.-UK, 9, 6057, https://doi.org/10.1038/s41598-019-42339-y, 2019.
Schulthess, T. C., Bauer, P., Wedi, N., Fuhrer, O., Hoefler, T., and Schär, C.: Reflecting on the Goal and Baseline for Exascale Computing: A Roadmap Based on Weather and Climate Simulations, Comput. Sci. Eng., 21, 30–41, https://doi.org/10.1109/MCSE.2018.2888788, 2019.
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W. K., and Woo, W.-C.: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, in: Proceedings of the 28th International Conference on Neural Information Processing Systems, 7–12 December 2015, Montreal, Canada, 1, 802–810, https://doi.org/10.48550/arXiv.1506.04214, 2015.
Sun, Y., Zhong, Z., Li, T., Yi, L., Camargo, S. J., Hu, Y., Liu, K., Chen, H., Liao, Q., and Shi, J.: Impact of ocean warming on tropical cyclone track over the western north pacific: A numerical investigation based on two case studies, J. Geophys. Res.-Atmos., 122, 8617–8630, https://doi.org/10.1002/2017JD026959, 2017.
Wang, C. and Fu, Y.: Ship Trajectory Prediction Based on Attention in Bidirectional Recurrent Neural Networks, in: 2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT), 13–15 November 2020, Shenyang, China, 529–533, https://doi.org/10.1109/isctt51595.2020.00100, 2020.
Wang, L.: Hush980/TCs_DL_code: Second release of my code (v2.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.7454324, 2022.
Wang, Y., Zhang, W., and Fu, W.: Back Propogation(BP)-neural network for tropical cyclone track forecast, Proceedings – 2011 19th International Conference on Geoinformatics, Geoinformatics 2011, 24–26 June 2011, Shanghai, China, 1–4, https://doi.org/10.1109/GeoInformatics.2011.5981095, 2011.
Zhang, Y., Chandra, R., and Gao, J.: Cyclone Track Prediction with Matrix Neural Networks, 2018 International Joint Conference on Neural Networks (IJCNN), 8–13 July 2018, Rio, Brazil, 1–8, https://doi.org/10.1109/IJCNN.2018.8489077, 2018.
Short summary
The past 24 h TC trajectories and meteorological field data were used to forecast TC tracks in the northwestern Pacific from hours 6–72 based on GRU_CNN, which we proposed in this paper and which has better prediction results than traditional single deep-learning methods. The historical steering flow of cyclones has a significant effect on improving the accuracy of short-term forecasting, while, in long-term forecasting, the SST and geopotential height will have a particular impact.
The past 24 h TC trajectories and meteorological field data were used to forecast TC tracks in...