volume | PIER Journals

Abstract

Since the performance of the spectral moment estimation algorithm commonly used in engineering degrades under the conditions of low SNR, this paper introduces the Extreme Learning Machine (ELM) to the spectral moment estimation of weather signals based on the correlation of the signals of adjacent range cells. To solve the problem that the hidden layer nodes of ELM algorithm are difficult to be determined, the Bidirectional Extreme Learning Machine (B-ELM) algorithm is applied to achieve the high resolution of spectral moments. Firstly, to improve the SNR of the training samples, time-domain pulse signals are converted into weather power spectrum by Welch method. Then, the parameters of the B-ELM hidden layer nodes are directly calculated by backpropagation of network residuals. The model parameters are optimized according to the least-squares solution, where the optimal number of hidden layer nodes is determined adaptively. Finally, the optimized B-ELM model is employed for the spectral moment estimation of weather signals. The algorithm is validated to be fast and accurate for spectral moment estimation using the measured IDRA weather radar data and is easy to implement in engineering.

1. Klimenko, D. E., "Studying the areal rainfall reduction in the Urals based on radar data," Russian Meteorology and Hydrology, Vol. 44, 484-493, 2019.

2. Da Silva, Fabricio Polifke, Otto Corrêa Rotunno Filho, Maria Gertrudes Alvarez Justi da Silva, Rafael João Sampaio, Gisele Dornelles Pires, and Afonso Augusto Magalhães de Araújo, "Real-time river level estimation based on variations of radar reflectivity --- A case study of the Quitandinha River watershed, Petrópolis, Rio de Janeiro (Brazil)," Bulletin of Atmospheric Science and Technology, Vol. 2, No. 1, 2021.

3. Li, B., "Development and challenge of weather radar technology in China," Progress in Meteorological Science and Technology, Vol. 12, No. 5, 37-46, 2022.

4. Zhao, J., X. G. Lu, H. Li, and Z. Zhang, "A fast spectral moments estimation approach of radar echoes with low signal-to-noise ratio," Signal Processing, Vol. 36, No. 5, 703-709, 2020.

5. Miller, Kenneth and M. Rochwarger, "A covariance approach to spectral moment estimation," IEEE Transactions on Information Theory, Vol. 18, No. 5, 588-596, 1972.

6. Dias, J. M. B. and J. M. N. Leitao, "Nonparametric estimation of mean Doppler and spectral width," IEEE Transactions on Geoscience and Remote Sensing, Vol. 38, No. 1, 271-282, 2000.
doi:10.1109/36.823919

7. Lu, Xiaoguang, Zhe Zhang, and Ping Han, "Low complexity spectral moments estimator under low SNR condition," 2016 Integrated Communications Navigation and Surveillance (ICNS), Herndon, VA, 2016.

8. Boyer, Eric, Monique Petitdidier, and Pascal Larzabal, "Stochastic Maximum Likelihood (SML) parametric estimation of overlapped Doppler echoes," Annales Geophysicae, Vol. 22, No. 11, 3983-3993, 2004.

9. Li, Fulin, Shaohua Hong, Yujie Gu, and Lin Wang, "An optimization-oriented algorithm for sparse signal reconstruction," IEEE Signal Processing Letters, Vol. 26, No. 3, 515-519, 2019.

10. Zhang, Changjiang, Huiyuan Wang, Jing Zeng, Leiming Ma, and Li Guan, "Short-term dynamic radar quantitative precipitation estimation based on wavelet transform and support vector machine," Journal of Meteorological Research, Vol. 34, 413-426, 2020.

11. Zhang, Yan, Zhong Ji, Bing Xue, and Ping Wang, "A novel fusion forecast model for hail weather in plateau areas based on machine learning," Journal of Meteorological Research, Vol. 35, No. 5, 896-910, 2021.

12. Nilesh, Rathod and Wankhade Sunil, "Improving extreme learning machine through optimization a review," 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), 906-912, Coimbatore, India, 2021.

13. Yaseen, Zaher Mundher, Sadeq Oleiwi Sulaiman, Ravinesh C. Deo, and Kwok-Wing Chau, "An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction," Journal of Hydrology, Vol. 569, 387-408, 2019.

14. Ahmad, Iftikhar, Mohammad Basheri, Muhammad Javed Iqbal, and Aneel Rahim, "Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection," IEEE Access, Vol. 6, 33789-33795, 2018.

15. Huang, Guang-Bin, "Learning capability and storage capacity of two-hidden-layer feedforward networks," IEEE Transactions on Neural Networks, Vol. 14, No. 2, 274-281, 2003.

16. Abramova, Elena S., Alexey A. Orlov, and Kirill V. Makarov, "Research of the extreme learning machine as incremental learning," 2022 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), 1068-1072, Sochi, Russian Federation, 2022.

17. Yang, Yimin, Yaonan Wang, and Xiaofang Yuan, "Bidirectional extreme learning machine for regression problem and its learning effectiveness," IEEE Transactions on Neural Networks and Learning Systems, Vol. 23, No. 9, 1498-1505, 2012.

18. Cao, Weipeng, Zhong Ming, Xizhao Wang, and Shubin Cai, "Improved bidirectional extreme learning machine based on enhanced random search," Memetic Computing, Vol. 11, 19-26, 2019.

19. Kaloev, Martin and Georgi Krastev, "Comparative analysis of activation functions used in the hidden layers of deep neural networks," 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 1-5, Ankara, Turkey, 2021.

20. Zhang, Le and Ponnuthurai N. Suganthan, "A comprehensive evaluation of random vector functional link networks," Information Sciences, Vol. 367-368, 1094-1105, 2016.

21. Nair, Vinod and Geoffrey E. Hinton, "Rectified linear units improve restricted boltzmann machines," Proceedings of the 27th International Conference on Machine Learning, 807-814, 2010.

22. Ventura, J. Figueras I. and H. W. J. Russchenberg, "IDRA: IRCTR drizzle radar," 2006 European Radar Conference, 174-177, Manchester, UK, 2006.

23. Xu, Xiangjun, Mingwei Shen, Xiaohuan Wu, Di Wu, and Daiyin Zhu, "Direction of arrival estimation based on modified fast off-grid L1-SVD," Electronics Letters, Vol. 58, No. 1, 32-34, 2022.

Dr. Zhongyuan Wang

Dr. Ling Qiao

Dr. Yu Jiang

Prof. Mingwei Shen

Dr. Guodong Han