Natural Hazards

, Volume 91, Issue 1, pp 201–220 | Cite as

Fuzzy neural network and LLE Algorithm for forecasting precipitation in tropical cyclones: comparisons with interpolation method by ECMWF and stepwise regression method

  • Ying Huang
  • Long Jin
  • Hua-sheng Zhao
  • Xiao-yan Huang
Original Paper


A tropical cyclone (TC) precipitation prediction scheme has been developed based on the physical quantities of the NCEP/NCAR reanalysis data as potential predictors and using fuzzy neural network (FNN) model. TC precipitation samples from 172 tropical cyclones (TCs) affecting Guangxi, China, spanning 1980–2015 are used for model development. The FNN model input is constructed from potential predictors by employing both a stepwise regression method (SRM) and a locally linear embedding (LLE) algorithm. The LLE algorithm is capable of finding meaningful low-dimensional architectures hidden in their nonlinear high-dimensional data space and separating the underlying factors. In this scheme, the newly developed model, which is termed the FNN–LLE model, is used for daily TC precipitation prediction from 20:00 (Beijing Time, or BT) of the previous day to 20:00 BT of the current day at 89 stations covering Guangxi, China. Using identical modeling samples and independent samples, predictions of the FNN–LLE model are compared with the widely used SRM and interpolation method using the fine-mesh data of the European Centre for Medium-Range Weather Forecasts (ECMWF) in terms of the performance of TC rainfall prediction at 89 stations in Guangxi. The root-mean-square error (RMSE), bias, and equitable threat score (ETS) results were employed to assess the predicted outcomes. Results show that the FNN–LLE model is superior to the interpolation method by ECMWF and SRM for TC precipitation prediction with RMSE values of 21.94, 24.07, and 25.22 in FNN–LLE model, interpolation method by ECMWF and SRM, respectively. Moreover, FNN–LLE model having average bias and ETS values close to 1.0 gave better predictions than did the interpolation method by ECMWF and SRM.


Tropical cyclone precipitation prediction Quantitative precipitation forecasts Fuzzy neural network Locally linear embedding algorithm Interpretation and application of ECMWF Forecasting techniques 



Bias score


Back-propagation neural network


European Centre for Medium-Range Weather Forecasts


Equitable threat score


Fuzzy neural network


FNN with employing both stepwise regression method and LLE algorithm for constructing model input


Guangxi Zhuang Autonomous Region, China


Locally linear embedding


Multidimensional scaling


Numerical weather prediction


Principal component analysis


Root-mean-square error


Stepwise regression method


Tropical cyclone


Tropical cyclones



This work was supported by the National Natural Science Foundation of China (Grant 41575051, Grant 41765002 and Grant 41565005), and the Program of Guangxi Meteorological Service (Grant 2017M08 and Grant 2016Z03).


  1. Chen G-Y, Ding X-X, Zhao L-Y (2005) An automatical pattern recognition techniques of cloud based on fuzzy neural network. Chin J Atmos Sci 29:837–844 (in Chinese) Google Scholar
  2. Chen J-F, Yuan B-Z, Pei B-N (2008) Face recognition using two dimensional laplacian eigenmap. J Electron 25:616–621Google Scholar
  3. Ebert EE, Damrath U, Wergen W, Baldwin ME (2003) The WGNE assessment of short-term quantitative precipitation forecasts. Bull Am Meteorol Soc 84:481–492CrossRefGoogle Scholar
  4. Guangxi Climate Center (2007) The climate of the Guangxi Zhuang autonomous region. China Meteorological Press, Beijing, p 60Google Scholar
  5. Han X, Yang Y, Feng J, Yuan Q (2017) Soybean pest diagnosis based on optimized weights of fuzzy neural network. J Agric Mech Res 3:247–252Google Scholar
  6. Huang Y, Jin L (2013) A prediction scheme with genetic neural network and isomap algorithm for tropical cyclone intensity change over western north pacific. Meteorol Atmos Phys 121:143–152CrossRefGoogle Scholar
  7. Huang X-Y, Shi X-M, Liu S-D, Jin L (2009) Research and applying of forecasting tropical cyclone intensity based on fuzzy neural network. Plateau Meteorol 28(6):1408–1413Google Scholar
  8. Huang Y, Jin L, Huang X, Shi X, Jin J (2014) An artificial intelligence ensemble prediction scheme for typhoon intensity using the locally linear embedding. Meteorol Mon 40:806–815Google Scholar
  9. Jian G, Shieh S, McGinley JA (2003) Precipitation simulation associated with Typhoon Sinlaku (2002) in the Taiwan area using the LAPS diabatic initialization for MM5. Terr Atmos Ocean Sci 14:261–288CrossRefGoogle Scholar
  10. Jin L, Kuang X, Huang H, Qin Z, Wang Y (2004) Study on the overfitting of the artificial neural network forecast model. Acta Meteorol Sin 62(1):62–70Google Scholar
  11. Kalnay E, Kanamitsu M, Kistler R, Collins W, Deaven D, Gandin L, Iredell M, Saha S, White G, Woollen J, Zhu Y, Leetmaa A, Reynolds R, Chelliah M, Ebisuzaki W, Higgins W, Janowiak J, Mo KC, Ropelewski C, Wang J, Jenne Roy, Joseph Dennis (1996) The NCEP/NCAR 40-year reanalysis project. Bull Am Meteorol Soc 77:437–470CrossRefGoogle Scholar
  12. Konrad II, Charles E, Baker Perry L (2009) Relationships between tropical cyclones and heavy rainfall in the Carolina region of the USA. Int J Climatol 30:522–534Google Scholar
  13. Kruse R (2008) Fuzzy neural network. Scholarpedia 3:6043CrossRefGoogle Scholar
  14. Kwong KM, Wong MHY, Liu NKJ, Chan PW (2012) An artificial neural network with chaotic oscillator for wind shear alerting. J Atmos Ocean Technol 29:1518–1531CrossRefGoogle Scholar
  15. Lee C-S, Huang L-R, Shen H-S, Wang S-T (2006) A climatology model for forecasting typhoon rainfall in Taiwan. Nat Hazards 37:87–105CrossRefGoogle Scholar
  16. Li RCY, Zhou W (2015) Interdecadal changes in summertime tropical cyclone precipitation over Southeast China during 1960–2009. J Clim 28:1494–1509CrossRefGoogle Scholar
  17. Li Q, Lan H, Chan JCL, Cao C, Li C, Wang X (2015) An operational statistical scheme for tropical cyclone induced rainfall forecast. J Trop Meteorol 21:101–110Google Scholar
  18. Lin G-F, Chen L-H (2005) Application of artificial neural network to typhoon rainfall forecasting. Hydrol Process 19:1825–1837CrossRefGoogle Scholar
  19. Lonfat M, Rogers R, Marchok T, Marks FD Jr (2007) A parametric model for predicting hurricane rainfall. Mon Weather Rev 135:3086–3097CrossRefGoogle Scholar
  20. Lund IA (1971) An application of stagewise and stepwise regression procedures to a problem of estimating precipitation in California. J Appl Meteorol 10:892–902CrossRefGoogle Scholar
  21. Marchok T, Rogers R, Tuleya R (2007) Validation schemes for tropical cyclone quantitative precipitation Forecasts: evaluation of operational models for U.S. landfalling cases. Weather Forecast 22:726–746CrossRefGoogle Scholar
  22. McBride JL, Ebert EE (2000) Verification of quantitative precipitation forecasts from operational numerical weather prediction models over Australia. Weather Forecast 15:103–121CrossRefGoogle Scholar
  23. Roweis ST, Saul Lawrence K (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326CrossRefGoogle Scholar
  24. Schaefer JT (1990) The critical success index as an indicator of warning skill. Weather Forecast 5:570–575CrossRefGoogle Scholar
  25. Shi X-M, Jin L, Zhu Y (2009) A fuzzy neural network precipitation model based on rough set. Comput Simul 26:178–180Google Scholar
  26. Si J-P, Ma J-C, Niu J-H, Wang E-M (2017) An intelligent fault diagnosis expert system based on fuzzy neural network. J Vib Shock 36:164–171Google Scholar
  27. Taniguchi A, Shige S, Yamamoto MK, Mega T, Kida S, Kubota T, Kachi M, Ushio T, Aonashi K (2013) Improvement of high-resolution satellite rainfall product for Typhoon Morakot (2009) over Taiwan. J Hydrometeorol 14:1859–1871CrossRefGoogle Scholar
  28. Wang S-T (1998) Neural fuzzy systems and its applications. Beihang University Press, BeijingGoogle Scholar
  29. Wei C-C (2012) Wavelet support vector machines for forecasting precipitation in tropical cyclones: comparisons with GSVM, regression, and MM5. Weather Forecast 27:438–450CrossRefGoogle Scholar
  30. Xinhuanet News (2014) Super typhoon Rammasun batters China, killing 14. Accessed 19 July 2014Google Scholar
  31. Xinhuanet News (2014) Death toll from super typhoon Rammasun rises to 17 in China. Accessed 20 July 2014Google Scholar
  32. Xu A-B, Guo P (2006) Isomap and neural networks based image registration scheme. Adv Neural Netw ISNN 3972:486–491Google Scholar
  33. Ying M, Zhang W, Hui Y, Xiao-qin L, Feng J, Fan Y-X, Zhu Y-T, Chen D-Q (2014) An overview of the China meteorological administration tropical cyclone database. J Atmos Ocean Technol 31:287–301CrossRefGoogle Scholar
  34. Yip ZK, Yau MK (2012) Application of artificial neural networks on North Atlantic tropical cyclogenesis potential index in climate change. J Atmos Ocean Technol 29:1202–1220CrossRefGoogle Scholar
  35. Yu B, Feng M, Chen B (1996) The application of fuzzily neural network to picture recognition of typhoon clouds. Meteorol Mon 22:22–25Google Scholar
  36. Yue C (2009) A quantitative study of asymmetric characteristic genesis of precipitation associated with Typhoon Haitang. Chin J Atmos Sci 33:51–70 (in Chinese) Google Scholar
  37. Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353CrossRefGoogle Scholar
  38. Zhang F, Weng Y, Kuo Y-H, Whitaker JS, Xie B (2010) Predicting Typhoon Morakot’s catastrophic rainfall with a convection-permitting mesoscale ensemble system. Weather Forecast 25:1816–1825CrossRefGoogle Scholar
  39. Zhao H, Jin L, Huang Y, Jin J (2014) An objective prediction model for typhoon rainstorm using particle swarm optimization: neural network ensemble. Nat Hazards 73:427–437CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2017

Authors and Affiliations

  • Ying Huang
    • 1
  • Long Jin
    • 1
  • Hua-sheng Zhao
    • 1
  • Xiao-yan Huang
    • 1
  1. 1.Guangxi Research Institute of Meteorological Disasters MitigationNanningChina

Personalised recommendations