Home Journal of Meteorological Research Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
References
Show full outline
Hide outline
Original Paper

Deep Learning-Based Automatic Identification of Gust Fronts from Weather Radar Data

School of Atmospheric Sciences, Chengdu University of Information Technology, Chengdu 610225
China Meteorological Administration Key Laboratory for Aviation Meteorology, Beijing 100081
Henan Meteorological Observatory, Zhengzhou 450003
Henan Key Laboratory of Agrometeorological Support and Applied Technique, China Meteorological Administration, Zhengzhou 450003
Show Author Information

Abstract

Gust fronts, which are characterized by strong winds and intense wind shear, pose a threat to both aviation and public safety. To aid forecasters in issuing timely warnings for this hazardous weather phenomenon, a deep learning-based automatic gust front identification algorithm is proposed in this study. The algorithm utilizes Mask Region-based Convolutional Neural Network (Mask R-CNN), a state-of-the-art instance segmentation model, trained on a large dataset of 2623 gust front samples from S-band weather radar volume scans in East China and the North China Plain between 2009 and 2016. Extensive data preprocessing and manual annotation are performed to prepare the training dataset. The optimized model achieves impressive performance on a test set of 604 samples, with a detection probability of 93.21%, a false alarm rate of 3.60%, a missed alarm rate of 6.79%, and a critical success index of 90.08%. The algorithm demonstrates robust identification capabilities across gust fronts of varying scales, types, and parent thunderstorm systems, highlighting its operational applicability.

Keywords

gust frontsdeep learningautomatic identification algorithmweather radar

References

 

Arul, M., A. Kareem, M. Burlando, et al., 2022: Machine learning based automated identification of thunderstorms from anemometric records using shapelet transform. J. Wind Eng. Ind. Aerod., 220, 104856, doi: 10.1016/j.jweia.2021.104856.

Crossref Google Scholar
 

Bresch, J. F., J. G. Powers, C. S. Schwartz, et al., 2021: Objective identification of thunderstorm gust fronts in numerical weather prediction models for fire weather forecasting. Int. J. Wildland. Fire, 30, 513–535, doi: 10.1071/WF20059.

Crossref Google Scholar
 

Craig Goff, R., 1976: Vertical structure of thunderstorm outflows. Mon. Wea. Rev., 104, 1429–1440, doi: 10.1175/1520-0493(1976)104<1429:VSOTO>2.0.CO;2.

Crossref Google Scholar
 

Delanoy, R. L., and S. W. Troxel, 1993: Machine intelligent gust front detection. Lincoln Lab J., 6, 187–212.

Google Scholar
 

Fournier, M. B., and J. O. Haerter, 2019: Tracking the gust fronts of convective cold pools. J. Geophys. Res. Atmos., 124, 11,103–11,117, doi: 10.1029/2019JD030980.

Crossref Google Scholar
 
Girshick, R., 2015: Fast R-CNN. Proceedings of 2015 IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, 1440–1448, doi: 10.1109/ICCV.2015.169.
Crossref
 
Girshick, R., J. Donahue, T. Darrell, et al., 2014: Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Columbus, OH, USA, 580–587, doi: 10.1109/CVPR.2014.81.
Crossref
 

Han, Y. L., J. Liu, D. S. Sun, et al., 2020: Fine gust front structure observed by coherent Doppler lidar at Lanzhou airport (103°49′E, 36°03′N). Appl. Opt., 59, 2686–2694, doi: 10.1364/AO.384634.

Crossref Google Scholar
 

He, K. M., X. Y. Zhang, S. Q. Ren, et al., 2015: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell., 37, 1904–1916, doi: 10.1109/TPAMI.2015.2389824.

Crossref Google Scholar
 
He, K. M., G. Gkioxari, P. Dollár, et al., 2017: Mask R-CNN. Proceedings of 2017 IEEE International Conference on Computer Vision, IEEE, Venice, Italy, 2980–2988, doi: 10.1109/ICCV.2017.322.
Crossref
 

He, N., Q. L. Ding, X. D. Yu, et al., 2020: Statistical analysis of thunderstorm gust front characteristics in Beijing and surrounding areas. Acta Meteor. Sinica, 78, 250–259, doi: 10.11676/qxxb2020.013. (in Chinese)

Crossref Google Scholar
 

Hwang, Y., T. Y. Yu, V. Lakshmanan, et al., 2017: Neuro-fuzzy gust front detection algorithm with S-band polarimetric radar. IEEE. Trans. Geosci. Remote Sens., 55, 1618–1628, doi: 10.1109/TGRS.2016.2628520.

Crossref Google Scholar
 

Kolios, S., 2023: Hail detection from Meteosat satellite imagery using a deep learning neural network and a new remote sensing index. Adv. Space Res., 72, 3009–3021, doi: 10.1016/j.asr.2023.06.016.

Crossref Google Scholar
 

Kwon, D. K., and A. Kareem, 2019: Towards codification of thunderstorm/downburst using gust front factor: Model-based and data-driven perspectives. Eng. Struct., 199, 109608, doi: 10.1016/j.engstruct.2019.109608.

Crossref Google Scholar
 

Leng, L., Y. J. Xiao, and T. Wu, 2016: Automatic recognition of gust fronts based on mathematical morphology. Meteor. Sci. Technol., 44, 1–6, 46, doi: 10.3969/j.issn.1671-6345.2016.01.001. (in Chinese)

Crossref Google Scholar
 

Liu, R. F., H. N. Dai, Y. Y. Chen, et al., 2024: A study on the DAM-EfficientNet hail rapid identification algorithm based on FY-4A_AGRI. Sci. Rep., 14, 3505, doi: 10.1038/s41598-024-54142-5.

Crossref Google Scholar
 

Luchetti, N. T., K. Friedrich, C. E. Rodell, et al., 2020: Characterizing thunderstorm gust fronts near complex terrain. Mon. Wea. Rev., 148, 3267–3286, doi: 10.1175/MWR-D-19-0316.1.

Crossref Google Scholar
 

Ren, S. Q., K. M. He, R. Girshick, et al., 2017: Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell., 39, 1137–1149, doi: 10.1109/TPAMI.2016.2577031.

Crossref Google Scholar
 

Rotunno, R., J. B. Klemp, and M. L. Weisman, 1988: A theory for strong, long-lived squall lines. J. Atmos. Sci., 45, 463–485, doi: 10.1175/1520-0469(1988)045<0463:ATFSLL>2.0.CO;2.

Crossref Google Scholar
 
Smalley, D. J., B. J. Bennett, and R. Frankel, 2005: 8.4 MIGFA: The Machine Intelligent Gust Front Algorithm for NEXRAD. Available online at https://ams.confex.com/ams/pdfpapers/96098.pdf. Accessed on 12 December 2024.
 

Tian, H. Y., Z. Q. Hu, F. Z. Wang, et al., 2024: Radar echo recognition of gust front based on deep learning. Remote Sens., 16, 439, doi: 10.3390/rs16030439.

Crossref Google Scholar
 
Troxel, S. W., and R. L. Delanoy, 1994: Machine intelligent approach to automated gust-front detection for Doppler weather radars. Proceedings of SPIE 2220, Sensing, Imaging, and Vision for Control and Guidance of Aerospace Vehicles, SPIE, Orlando, FL, USA, 182–193, doi: 10.1117/12.179602.
Crossref
 

Uyeda, H., and D. S. Zrnić, 1986: Automatic detection of gust fronts. J. Atmos. Oceanic Technol., 3, 36–50, doi: 10.1175/1520-0426(1986)003<0036:ADOGF>2.0.CO;2.

Crossref Google Scholar
 

Wakimoto, R. M., 1982: The life cycle of thunderstorm gust fronts as viewed with Doppler radar and rawinsonde data. Mon. Wea. Rev., 110, 1060–1082, doi: 10.1175/1520-0493(1982)110<1060:TLCOTG>2.0.CO;2.

Crossref Google Scholar
 

Wilson, J. W., and W. E. Schreiber, 1986: Initiation of convective storms at radar-observed boundary-layer convergence lines. Mon. Wea. Rev., 114, 2516–2536, doi: 10.1175/1520-0493(1986)114<2516:IOCSAR>2.0.CO;2.

Crossref Google Scholar
 

Wilson, J. W., T. M. Weckwerth, J. Vivekanandan, et al., 1994: Boundary layer clear-air radar echoes: Origin of echoes and accuracy of derived winds. J. Atmos. Oceanic Technol., 11, 1184–1206, doi: 10.1175/1520-0426(1994)011<1184:BLCARE>2.0.CO;2.

Crossref Google Scholar
 
Witt, A., and S. D. Smith, 1987: Development and Testing of the Gust Front Algorithm. DOT/FAA/PS-87/4, National Severe Storms Laboratory, Washington, 1–43.
 
Witt, A., S. D. Smith, M. D. Eilts, et al., 1989: Gust Front/Wind Shift Detection Algorithm for the Terminal Doppler Weather Radar. DOT/FAA/NR-91/4, National Severe Storms Laboratory, Norman, 1–74.
 

Xi, B. Z., X. D. Yu, L. Sun, et al., 2015: Generating mechanism and type of gust front and its subjective identification methods. Meteor. Mon., 41, 133–142. (in Chinese)

Google Scholar
 

Xie, J. L., C. X. Lan, H. L. Yang, et al., 2022: Tower-observed structural evolution of the low-level boundary layer before, during, and after gust front passage in a coastal area at low latitude. Wea. Climate Extrem., 36, 100429, doi: 10.1016/j.wace.2022.100429.

Crossref Google Scholar
 

Xu, Y. F., F. Zhao, C. Y. Mao, et al., 2020: Gust front detection algorithm based on deep convolutional neural network. Torrential Rain and Disasters, 39, 81–88, doi: 10.3969/j.issn.1004-9045.2020.01.009. (in Chinese)

Crossref Google Scholar
 

Yuan, Y., P. Wang, D. Wang, et al., 2018: An algorithm for automated identification of gust fronts from Doppler radar data. J. Meteor. Res., 32, 444–455, doi: 10.1007/s13351-018-7089-7.

Crossref Google Scholar
 

Zeng, Q. Y., Z. P. Qing, M. Zhu, et al., 2022: Application of random forest algorithm on tornado detection. Remote Sens., 14, 4909, doi: 10.3390/rs14194909.

Crossref Google Scholar
 

Zheng, J. F., J. Zhang, K. Y. Zhu, et al., 2014: Gust front statistical characteristics and automatic identification algorithm for CINRAD. J. Meteor. Res., 28, 607–623, doi: 10.1007/s13351-014-3240-2.

Crossref Google Scholar
Journal of Meteorological Research
Volume 38 Issue 6,
December 2024
Pages 1021-1031
DOI: 10.1007/s13351-024-4054-5
Cite this article:
ZHANG H, ZHENG J, LIU C, et al. Deep Learning-Based Automatic Identification of Gust Fronts from Weather Radar Data. Journal of Meteorological Research, 2024, 38(6): 1021-1031. https://doi.org/10.1007/s13351-024-4054-5
Metrics & Citations  
Article History
Copyright
Return