A PNN prediction scheme for local tropical cyclone intensity over the South China Sea

详细信息    查看全文

• 作者：Xiaoyan Huang ; Zhaoyong Guan ; Li He ; Ying Huang ; Huasheng Zhao
• 关键词：Probabilistic neural network (PNN) ; South China Sea local tropical cyclone (SLTC) ; TC intensity ; Climatology and persistence (CLIPER) ; Multiple linear regression (MLR)
• 刊名：Natural Hazards
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：81
• 期：2
• 页码：1249-1267
• 全文大小：1,074 KB
• 参考文献：Aberson SD, Sampson CR (2003) On the predictability of tropical cyclone tracks in the northwest pacific basin. Mon Weather Rev 131(7):1491–1497CrossRef
  Adeli H, Panakkat A (2009) A probabilistic neural network for earthquake magnitude prediction. Neural Netw 22(7):1018–1024CrossRef
  Bankert RL (1994) Cloud classification of AVHRR imagery in maritime regions using a probabilistic neural network. J Appl Meteorol 33(8):909–918CrossRef
  Bessafi M, Lasserre-Bigorry A (2002) Statistical prediction of tropical cyclone motion: an analog-CLIPER approach. Weather Forecast 17(4):821–831CrossRef
  Bhatia KT, Nolan DS (2013) Relating the skill of tropical cyclone intensity forecasts to the synoptic environment. Weather Forecast 28:961–980CrossRef
  Bigdeli M, Vakilian M, Rahimpour E (2013) A probabilistic neural network classifier-based method for transformer winding fault identification through its transfer function measurement. Int Trans Electr Energy Syst 23(3):392–404CrossRef
  Cangialosi JP, Franklin JL (2012) 2011 National Hurricane Center forecast verification report. NOAA/NWS/NHC, 76
  DeMaria M, Kaplan J (1999) An updated statistical hurricane intensity prediction scheme (SHIPS) for the Atlantic and eastern North Pacific basins. Weather Forecast 14:326–337CrossRef
  DeMaria M, Sampson CR et al (2014) Is tropical cyclone intensity guidance improving? Bull Am Meteorol Soc 95(3):387–398CrossRef
  Ding S, Chang XH, Wu QH (2014) Application of probabilistic neural network in pattern classification. Appl Mech Mater 441:738–741CrossRef
  Dong X, Zheng W (2002) System analysis and design-neural network based on MATLAB6.X. Xi an University of Electronic Science and Technology Press, Xi’an (in Chinese)
  Falvey R, (2012) Summary of the 2011 western pacific/indian ocean tropical cyclone season. In: Proceedings of the 66th interdepartmental Hurricane Conference, Charleston, SC, OFCM. www.​ofcm.​gov/​ihc12/​Presentations/​01b-Session/​05-JTWC_​2012_​IHC_​Final.​pdf
  Freedman A, (2012) Storm intensity forecasts lag; Communities more at risk. www.​climatecentral.​org/​news/​storm-intensity-forecasts-lag-putting-communities-more-at-risk/​
  Goh ATC (2002) Probabilistic neural network for evaluating seismic liquefaction potential. Can Geotech J 39(1):219–232CrossRef
  Harnos DS, Nesbitt SW (2011) Convective structure in rapidly intensifying tropical cyclones as depicted by passive microwave measurements. Geophys Res Lett 38(7). doi:10.​1029/​2011GL047010
  Ito K, Kuroda T, Saito K (2015) Forecasting a large number of tropical cyclone intensities around Japan using a high-resolution atmosphere-ocean coupled model. Weather Forecast 30(3):793–808
  Jin L (2004) Modeling theory method and application for weather forecast based on neural network. China Meteorological Press, Beijing (in Chinese)
  Knaff JA, Sampson CR, DeMaria M (2005) An operational statistical typhoon intensity prediction scheme for the Western North Pacific. Weather Forecast 20:688–699CrossRef
  Kotal SD, Bhowmik SKR, Kundu PK et al (2008) A statistical cyclone intensity prediction (SCIP) model for the Bay of Bengal. J Earth Syst Sci 117(2):157–168CrossRef
  Lee YK, Hamzah N, Jailani R (2002) Prediction of water quality index based on artificial neural network. Research and Development, Selangor, pp 157–161
  Mohapatra M, Bandyopadhyay BK, Nayak DP (2013) Evaluation of operational tropical cyclone intensity forecasts over north Indian Ocean issued by India Meteorological Department. Nat Hazards 68(2):433–451CrossRef
  Petty KR, Hobgood JS (2000) Improving tropical cyclone intensity guidance in the Eastern North Pacific. Weather Forecast 15:233–244CrossRef
  Sharma et al (2013) A soft-computing cyclone intensity prediction scheme for the Western North Pacific Ocean. Atmos Sci Lett 14:187–192CrossRef
  Specht DF (1988) Probabilistic neural networks for classification, mapping, or associative memory. IEEE Int Conf IEEE Neural Netw 1988:525–532CrossRef
  Specht DF (1990) Probabilistic neural networks. Neural Netw 3(2):109–118CrossRef
  Tripathy M, Maheshwari RP, Verma HK (2010) Power transformer differential protection based on optimal probabilistic neural network. IEEE Trans Power Deliv 25(1):102–112CrossRef
  Villarini G, Vecchi GA (2013) Projected increases in North Atlantic tropical cyclone intensity from CMIP5 models. J Clim 26:3231–3240CrossRef
  Wang JS, Chiang WC, Hsu YL et al (2013) ECG arrhythmia classification using a probabilistic neural network with a feature reduction method. Neuro Comput 116:38–45
  Wu SG, Bao FS, Xu EY, et al. (2007) A leaf recognition algorithm for plant classification using probabilistic neural network. In: IEEE international symposium on signal processing and information technology, IEEE, pp 11–16
  Xiuzhi Z (1996) Climatic characteristics of tropical cyclone intensification in northwest pacific. Mar Forecasts 13(1):1–9 (in Chinese)
  Yenugu M, Fisk JC, Marfurt KJ (2010) Probabilistic Neural Network inversion for characterization of coalbed methane[C]//2010 SEG Annual Meeting. Society of Exploration Geophysicists, pp 2906–2910
  Zhang F, Tao D (2013) Effects of vertical wind shear on the predictability of tropical cyclones. J Atmos Sci 70(3):975–983CrossRef
  Zhang Y, Meng Z, Zhang F et al (2014) Predictability of tropical cyclone intensity evaluated through 5-yr forecasts with a convection-permitting regional-scale model in the Atlantic basin. Weather Forecast 29(4):1003–1023CrossRef
  
• 作者单位：Xiaoyan Huang (1) (2)
  Zhaoyong Guan (1)
  Li He (2)
  Ying Huang (2)
  Huasheng Zhao (2)
  
  1. Key Laboratory of Meteorological Disaster of Ministry of Education, Nanjing University of Information Science and Technology, 219 Ningliu Road, Nanjing, 210044, China
  2. Guangxi Research Institute of Meteorological Disasters Mitigation, Nanning, China
  
• 刊物类别：Earth and Environmental Science
• 刊物主题：Earth sciences
  Hydrogeology
  Geophysics and Geodesy
  Geotechnical Engineering
  Civil Engineering
  Environmental Management
  
• 出版者：Springer Netherlands
• ISSN：1573-0840

文摘

A nonlinear tropical cyclone (TC) intensity scheme is introduced with probabilistic neural network (PNN) approach and is based on climatology and persistence (CLIPER) factors to predict local TC intensity in the South China Sea from May to October in 1949 to 2012. In this study, we investigate the local TCs that generate over the South China Sea and the maximum wind speeds near the center of TCs. The performance of the new prediction model is assessed with mean absolute error and forecast trend consistency rate. Results indicate the followings: (1) the new model is effective because of its low error rate. The absolute forecast error proportion of samples, which is less than or equal to 5 m/s, is more than 80 % in 24 h, 60 % in 48 h, and 50 % in 72 h. (2) The prediction capacity of the PNN model is more powerful than that of the CLIPER model and the multiple linear regression model based on the same samples and predictors. (3) The maximum skill level based on 17 forecasts is over 0.6, which is suitable for operational TC intensity application. Keywords Probabilistic neural network (PNN) South China Sea local tropical cyclone (SLTC) TC intensity Climatology and persistence (CLIPER) Multiple linear regression (MLR)