Doppler processing in weather radar using deep learning (2024)

Home> > IET Signal Processing> Volume 14, Issue 9> Article

View Fulltext

Author(s):Arturo Collado Rosell^{1, 2}; Jorge Cogo³; Javier Alberto Areta^{3, 4};Juan Pablo Pascual^{1, 2, 4}
- Affiliations: 1:Instutito Balseiro, Universidad Nacional de Cuyo , Av. Bustillo 9500, Bariloche , Argentina ;
  2:Departamento de Ingeniería en Telecomunicaciones , GDTyPE, GAIyANN, CNEA , Av. Bustillo 9500, Bariloche , Argentina ;
  3:Universidad Nacional de Río Negro , Anasagasti 1463, Bariloche , Argentina ;
  4:Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET) , Godoy Cruz 2290, Buenos Aires , Argentina
Source: Volume 14, Issue 9,December2020, p.672 – 682
DOI:10.1049/iet-spr.2020.0095,Print ISSN 1751-9675,Online ISSN 1751-9683

« Previous Article
Table of contents
Next Article »

Received04/03/2020,Accepted 02/09/2020,Revised 01/09/2020,Published 03/09/2020

Article
References (36)
Cited By (0)
Supplementary material (0)
Keywords
Related Content

A deep learning approach to estimate the mean Doppler velocity and spectral width in weather radars is presented. It can operate in scenarios with and without the presence of ground clutter. The method uses a deep neural network with two branches, one for velocity and the other for spectral width estimation. Different network architectures are analysed and one is selected based on its validation performance, considering both serial and parallel implementations. Training is performed using synthetic data covering a wide range of possible scenarios. Monte Carlo realisations are used to evaluate the performance of the proposed method for different weather conditions. Results are compared against two standard methods, pulse-pair processing (PPP) for signals without ground clutter and Gaussian model adaptive processing (GMAP) for signals contaminated with ground clutter. Better estimates are obtained when comparing the proposed algorithm against GMAP and comparable results when compared against PPP. The performance is also validated using real weather data from the C-band radar RMA-12 located in San Carlos de Bariloche, Argentina. Once trained, the proposed method requires a moderate computational load and has the advantage of processing all the data at once, making it a good candidate for real-time implementations.

Inspec keywords: Doppler radar;meteorological radar;neural nets;atmospheric techniques;geophysical signal processing;radar clutter

Other keywords: weather data;GMAP;deep learning approach;Monte Carlo realisations;C-band radar RMA-12;Doppler processing;San Carlos de Bariloche;weather radar;mean Doppler velocity;spectral width estimation;pulse-pair processing;synthetic data;Gaussian model adaptive processing;PPP;deep neural network;ground clutter

Subjects:Radar equipment, systems and applications;Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research;Signal processing and detection;Atmospheric, ionospheric and magnetospheric techniques and equipment

References

1. 1)
  - 1. Meischner, P.: ‘Weather radar: principles and advanced applications’ (Springer, Berlin, Heidelberg, 2013).
2. 2)
  - 29. Nair, V., Hinton, G.E.: ‘Rectified linear units improve restricted Boltzmann machines’. Proc. of the 27th Int. Conf. on Machine Learning (ICML-10), Haifa, Israel, 2010, pp. 807–814.
3. 3)
  - 18. Kononenko, I.: ‘Machine learning for medical diagnosis: history, state of the art and perspective’, Artif. Intell. Med., 2001, 23, (1), pp. 89–109.
4. 4)
  - 6. Mahapatra, P.R., Zrnić, D.S.: ‘Practical algorithms for mean velocity estimation in pulse Doppler weather radars using a small number of samples’, IEEE Trans. Geosci. Remote Sens., 1983, GE-21, (4), pp. 491–501.
5. 5)
  - 22. Wang, H., Ran, Y., Deng, Y., et al: ‘Study on deep-learning-based identification of hydrometeors observed by dual polarization Doppler weather radars’, J. Wirel. Commun. Netw., 2017, 173, pp. 1–9.
6. 6)
  - 5. Ryzhkov, A.V., Zrnic, D.S.: ‘Radar polarimetry for weather observations’, Springer Atmospheric Sciences (Springer International Publishing, Switzerland, 2019).
7. 7)
  - 23. Li, H., Ren, J., Han, J., et al: ‘Ground clutter suppression method based on FNN for dual-polarisation weather radar’, J. Eng., 2019, 2019, (19), pp. 6043–6047.
8. 8)
  - 15. Warde, D.A., Torres, S.M.: ‘The autocorrelation spectral density for Doppler-weather-radar signal analysis’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (1), pp. 508–518.
9. 9)
  - 14. Ice, R.L., Rhoton, R.D., Krause, J.C., et al: ‘Automatic clutter mitigation in the WSR-88D, design, evaluation, and implementation’. Proc. 34th Radar Meteorology, Williamsburg, VA, USA, 2009, pp. P5.3 1–12.
10. 10)
  - 13. Hubbert, J.C., Dixon, M., Ellis, S.M.: ‘Weather radar ground clutter. Part II: real-time identification and filtering’, J. Atmos. Oceanic Technol., 2009, 26, pp. 1181–1197.
11. 11)
  - 25. Zrnic, D.S.: ‘Simulation of weatherlike Doppler spectra and signals’, J. Appl. Meteorol., 1975, 14, (4), pp. 619–620.
12. 12)
  - 3. Doviak, R.J., Zrnic, D.S.: ‘Doppler radar and weather observations’ (Courier Corporation, USA, 2014).
13. 13)
  - 30. Kingma, D.P., Ba, J.: ‘Adam: a method for stochastic optimization’, arXiv preprint arXiv:14126980, 2014.
14. 14)
  - 35. Hailong, W., Shouyuan, D., Xu, W., et al: ‘Sea clutter recognition based on dual-polarization weather radar’. 2019 Int. Conf. on Meteorology Observations (ICMO), Chengdu, China, 2019.
15. 15)
  - 28. Chollet, F.: ‘Keras’. GitHub, 2015. Available at https://github.com/fchollet/keras.
16. 16)
  - 20. Goodfellow, I., Bengio, Y., Courville, A.: ‘Deep learning’ (MIT Press, USA, 2016).
17. 17)
  - 32. Uysal, F., Selesnick, I., Isom, B.M.: ‘Mitigation of wind turbine clutter for weather radar by signal separation’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (5), pp. 2925–2934.
18. 18)
  - 33. Hood, K., Torres, S., Palmer, R.: ‘Automatic detection of wind turbine clutter for weather radars’, J. Atmos. Oceanic Technol., 2010, 27, (11), pp. 1868–1880.
19. 19)
  - 2. Andrews, C.: ‘The future of weather forecasting [communications met office supercomputer]’, Eng. Technol., 2015, 2, (10), pp. 65–67.
20. 20)
  - 4. f*ckao, S., Hamazu, K., Doviak, R.: ‘Radar for meteorological and atmospheric observations’ (Springer Japan, Japan, 2013).
21. 21)
  - 31. Hildebrand, P.H., Sekhon, R.: ‘Objective determination of the noise level in Doppler spectra’, J. Appl. Meteorol., 1974, 13, (7), pp. 808–811.
22. 22)
  - 36. Radhakrishna, B., Fabry, F., Kilambi, A.: ‘Fuzzy logic algorithms to identify birds, precipitation, and ground clutter in S-band radar data using polarimetric and nonpolarimetric variables’, J. Atmos. Oceanic Technol, 2019, 36, (12), pp. 2401–2414.
23. 23)
  - 12. Torres, S.M., Warde, D.A.: ‘Ground clutter mitigation for weather radars using the autocorrelation spectral density’, J. Atmos. Oceanic Technol., 2014, 31, (10), pp. 2049–2066.
24. 24)
  - 27. Abadi, M., Agarwal, A., Barham, P.: ‘Tensorflow: large-scale machine learning on heterogeneous systems’, 2015. Available at https://www.tensorflow.org/.
25. 25)
  - 10. Siggia, A., Passarelli, R.: ‘Gaussian model adaptive processing (GMAP) for improved ground clutter cancellation and moment calculation’. Proc. ERAD, Visby, Sweden, 2004, pp. 421–424.
26. 26)
  - 8. Janssen, L., Van Der Spek, G.A.: ‘The shape of Doppler spectra from precipitation’, IEEE Trans. Aerosp. Electron. Syst., 1985, AES-21, (2), pp. 208–219.
27. 27)
  - 24. Pan, S.J., Yang, Q.: ‘A survey on transfer learning’, IEEE Trans. Knowl. Data Eng., 2010, 22, (10), pp. 1345–1359.
28. 28)
  - 34. Dutta, A., Chandrasekar, V.: ‘Detection, analysis and mitigation of sea clutter in polarimetric weather radar’. 2019 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2019, pp. 1–2.
29. 29)
  - 11. Nguyen, C.M., Chandrasekar, V.: ‘Gaussian model adaptive processing in time domain (GMAP-TD) for weather radars’, J. Atmos. Oceanic Technol., 2013, 30, pp. 2571–2584.
30. 30)
  - 26. Welch, P.: ‘The use of fast Fourier Transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms’, IEEE Trans. Audio Electroacoust., 1967, 15, (2), pp. 70–73.
31. 31)
  - 16. Kon, S., Tanaka, T., Mizutani, H., et al: ‘A machine learning based approach to weather parameter estimation in Doppler weather radar’. 2011 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 2011, pp. 2152–2155.
32. 32)
  - 17. Zhang, L., Tan, J., Han, D., et al: ‘From machine learning to deep learning: progress in machine intelligence for rational drug discovery’, Drug Discov. Today, 2017, 22, (11), pp. 1680–1685.
33. 33)
  - 19. Gyorfi, L., Ottucsak, G., Walk, H.: ‘Machine learning for financial engineering’, Advances in Computer Science and Engineering: Texts (Imperial College Press, England, 2011).
34. 34)
  - 7. Zrnić, D.S.: ‘Spectral moment estimates from correlated pulse pairs’, IEEE Trans. Aerosp. Electron. Syst., 1977, AES-13, (4), pp. 344–354.
35. 35)
  - 21. Islam, T., Rico-Ramirez, M.A., Han, D., et al: ‘Artificial intelligence techniques for clutter identification with polarimetric radar signatures’, Atmos. Res., 2012, 109–110, pp. 95–113.
36. 36)
  - 9. Groginsky, H.L., Glover, K.M.: ‘Weather radar canceller design’. 19th Conf. on Radar Meteorology, Miami Beach, FL, USA, 1980, pp. 192–198.

http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2020.0095

Doppler processing in weather radar using deep learning (2024)

References

Related content