Advertisement

Cluster Computing

, Volume 22, Supplement 4, pp 8207–8216 | Cite as

Estimation method for \(\hbox {ET}_{0}\) with PSO-LSSVM based on the HHT in cold and arid data-sparse area

  • Pengxiang Wang
  • Chang Liu
  • Yunkai LiEmail author
Article

Abstract

A coupled particle swarm optimization (PSO) least squares support vector machine (LSSVM) model based on the Hilbert–Huang transform (HHT) was established to provide accurate estimations of reference crop evapotranspiration \((\hbox {ET}_{0})\) in cold and arid areas that lack the required meteorological data. Daily data (2000–2009) from the Hetian Xinjiang meteorological station (China) were used for training and double-day data used for validation. The accuracy of the method was compared with two machine models, the conventional PSO-LSSVM model and a generalized regression neural network, and three empirical methods, the Hargreaves, FAO-24 Penman, and Priestley–Taylor models. Under the condition of the same parameters of meteorological data, the accuracies of the machine models were found better than the empirical models, and the precision of the PSO-LSSVM coupled algorithm based on the HHT was the highest. The relative importance of the prediction elements was Rs > Tmax > Tmin > RH > Wn. When the deletion combination was Tmax/Tmin/RH/Wn, Tmax/RH/Wn, Tmin/Wn, and Wn, the mean square error was 0.407, 0.185, 0.149, 0.135, respectively, which shows this method is adequate for estimating \(\hbox {ET}_{0}\) in data-sparse areas.

Keywords

Reference crop evapotranspiration (\(\hbox {ET}_{0}\)HHT PSO-LSSVM Prediction model 

Notes

Acknowledgements

This work was supported by Science and Technology Promotion Plan of PRC Ministry of Water Resources (No. TG1510).

References

  1. 1.
    Allen, R.G., Walter, L.A., Elliott, R., et al.: Issues, requirements and challenges in selecting and specifying a standardized ET equation. In: Evans, R.G., Benham, B.L., Trooien, T.P. (ed.), Proceedings of the National Irrigation Symposium, ASAE, Nov, 14–16, 2000, Phoenix, Az, pp. 201–208 (2000)Google Scholar
  2. 2.
    Gorka, L., Amaia, O.B., Jose, J.L.: Comparison of artificial neural network models and empirical and semi-empirical equations for daily reference evapotranspiration estimation in the Basque Country (Northern Spain). Agric. Water Manag. 95(5), 553–565 (2008)CrossRefGoogle Scholar
  3. 3.
    Hou, Z.Q., Yang, P.L., Su, Y.P., Ren, S.M.: Simulation of \(\text{ ET }_{0}\) based on LS-SVM method. Shuili Xuebao 42(6), 743–749 (2011)Google Scholar
  4. 4.
    Kumar, M., Raghuwanshi, N.S., Siongh, R.: Estimating evapotranspiration using artificial neural network. J. Irrig. Drain. Eng. 128(4), 224–233 (2002)CrossRefGoogle Scholar
  5. 5.
    Khoob, A.R.: Comparative study of Hargreaves’s and artificialneural network‘s methodologies in estimating reference evapotranspiration in a semiarid environment. Irrig. Sci. 26(3), 253–259 (2008)CrossRefGoogle Scholar
  6. 6.
    Huang, N.E., Shen, Z., Long, S.R., et al.: The empirical mode decomposition and the Hilbert spectrum for non-linear and non-stationary time series analysis. Proc. R. Soc. Lond. A: Math. Phys. Eng. Sci. 454, 903–995 (1998)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Zhao, C.X.: The Research of Time-Frequency Analysis Method Based on Hilbert-Huang Transform, pp. 11–13. China University of Petroleum, Beijing (2011)Google Scholar
  8. 8.
    Kumar, M., Bandyopadhyay, A., Raghuwanshi, N.S., et al.: Comparative study of conventional and artificial neural network-based \(\text{ ET }_{0}\) estimation models. Irrig. Sci. 26(6), 531–545 (2008)CrossRefGoogle Scholar
  9. 9.
    Chi, D.C., Li, S.Y., Yu, M., et al.: Predicting reference evaportranspiration based on LS-SVM. J. Shenyang Agric. Univ. 40(2), 206–209 (2009)Google Scholar
  10. 10.
    Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, pp. 1942–1948 (1995)Google Scholar
  11. 11.
    Ren, J.T.: Simultaneous feature selection and SVM parameters optimization algorithm based on binary PSO. Comput. Sci. 34(6), 179–182 (2007)Google Scholar
  12. 12.
    Li, Y.K., Tian, Y.J., Ouyang, Z.Y., et al.: Analysis of soil erosion characteristics in small watersheds with particle swarm optimization, support vector machine, and artificial neuronal networks. Environ. Earth Sci. 60(7), 1559–1568 (2009)Google Scholar
  13. 13.
    Yao, Q.Z., Cai, J.: Feature selection and LS–SVM parameters optimization algorithm based on PSO. Comput. Eng. Appl. 46(1), 134–136 (2010)Google Scholar
  14. 14.
    Wang, X.H., Guo, M.H., Xu, Z.M.: Comparison of estimating ET\(_{0 }\)in arid-area of Northwest China by Hargreaves and Penman–Monteith equation. Trans. CSAE 22(10), 21–25 (2006)Google Scholar
  15. 15.
    Sun, Q.Y., Tong, L., Zhang, B.Z., Tang, B.: Comparison of methods for calculating reference crop evapotranspiration in Haihe River basin of China. Trans. CSAE 26(11), 68–72 (2010)Google Scholar
  16. 16.
    Zhao, X., Li, Y., Liu, J.M.: Prediction of reference crop evapotranspiration with grey model in Xinjiang region. Trans. CSAE 25(10), 50–56 (2009)Google Scholar
  17. 17.
    Shi, X.N., Wang, Q.J., Wang, X., et al.: Adaptability of different reference evapo-transpiration estimation methods in XinJiang region. Trans. CSAE 22(6), 19–23 (2006)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Water Resources and Civil EngineeringChina Agricultural UniversityBeijingChina

Personalised recommendations