Abstract
This paper proposes a new prediction model for severe natural disasters, especially typhoon using daily weather analysis. Hainan province in China is selected to be a typical application region, where natural disasters, especially typhoons take place frequently. These disasters have great impacts on the life and property safety of the residents, and therefore are in specific need of accurate prediction. A new prediction model of daily weather in Hainan province under the typhoon weather is proposed in this paper based on the best track datasets of typhoons and the corresponding daily weather data. This model utilizes the statistical methods and data mining technology in combination with the dynamic migration information of tropical cyclones and can provide the dynamic prediction of daily weather elements in any designated location. Three surface meteorological observation stations of Hainan province during the years 1951–1920 are used to test the model. Test results show that the prediction equations established for the vast majority of daily weather elements have passed the significant test. Besides, Typhoon Damrey is used as a case to illustrate the whole daily weather prediction model in detail and comparisons between the model and other official forecast (such as JTWC, UKMO and CMA) are performed thoroughly. It is worth noting that the model proposed in this paper is not limited to Hainan province and can be generalized to other areas in the world.
This is a preview of subscription content, log in via an institution to check access.
(Note The forecast leading time is about 72 h)
Similar content being viewed by others
References
Akpabio LE, Etuk SE (2003) Relationship between global solar radiation and sunshine duration for Onne, Nigeria. Turk J Phys 27:161–167
Allen DM (1971) Mean square error of prediction as a criterion for selecting variables. Technometrics 13:469–475. https://doi.org/10.1080/00401706.1971.10488811
Barbounis TG, Theocharis JB (2007) Locally recurrent neural networks for wind speed prediction using spatial correlation. Inf Sci 177:5775–5797. https://doi.org/10.1016/j.ins.2007.05.024
Beccali M, Cirrincione G, Marvuglia A, Serporta C (2010) Estimation of wind velocity over a complex terrain using the generalized mapping regressor. Appl Energy 87:884–893. https://doi.org/10.1016/j.apenergy.2009.05.026
Carta JA, Velázquez S (2011) A new probabilistic method to estimate the long-term wind speed characteristics at a potential wind energy conversion site. Energy 36:2671–2685. https://doi.org/10.1016/j.energy.2011.02.008
Chen XX, Xu AM (2011) Temperature and humidity of air in mine roadways prediction based on BP neural network. https://doi.org/10.1109/ICMT.2011.6002598
Chen JD, Zheng ZG (2007) Regression analysis. Probability and Statistics. Beijing University Press, Beijing, pp 446–493
Chevalier RF, Hoogenboom G, Mcclendon RW, Paz JA (2011) Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks. Neural Comput Appl 20:151–159. https://doi.org/10.1007/s00521-010-0363-y
Dabhi VK, Chaudhary S (2014) Hybrid wavelet-postfix-GP Model for rainfall prediction of anand region of India. Lect Notes Artif Int. https://doi.org/10.1155/2014/717803
Damousis IG, Alexiadis MC, Theocharis JB, Dokopoulos PS (2004) A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation. Energ Convers 19:352–361. https://doi.org/10.1109/TEC.2003.821865
Ferreira PM, Faria EA, Ruano AE (2002) Neural network models in greenhouse air temperature prediction. Neurocomputing 43:51–75. https://doi.org/10.1016/S0925-2312(01)00620-8
Guo QC, He ZF, Hui Y, Li X (2013) Application of artificial neural network to relative humidity prediction. Modern Food Sci Technol 29:1297–1301. https://doi.org/10.13982/j.mfst.1673-9078.2013.06.002
Jie WH, Wu TW, Wang J, Li WJ, Polivka T (2015) Using a deterministic time-lagged ensemble forecast with a probabilistic threshold for improving 6–15 day summer precipitation prediction in China. Atmos Res 14:142–159. https://doi.org/10.1016/j.atmosres.2015.01.004
Liang FZ, Song ZJ, Zhang YH (2004) Regression analysis and variance analysis. Appl probability and statistics. Tianjin University Press, Tianjin, pp 363–381
Mustafaraj G, Lowry G, Chen J (2011) Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural network models for an open office. Energy Build 43:1452–1460. https://doi.org/10.1016/j.enbuild.2011.02.007
Ortiz-Garcia EG, Salcedo-Sanz S, Casanova-Mateo C (2014) Accurate precipitation prediction with support vector classifiers: a study including novel predictive variables and observational data. Atmos Res 139:128–136. https://doi.org/10.1016/j.atmosres.2014.01.012
Salcedo-Sanz S, Ortiz-Garcia EG, Perez-Bellido AM, Portilla-Figueras A, Prieto L (2011) Short term wind speed prediction based on evolutionary support vector regression algorithms. Expert Syst Appl 38:4052–4057. https://doi.org/10.1016/j.eswa.2010.09.067
Sen Z, Oztopal A (2003) Terrestrial irradiation–sunshine duration clustering and prediction. Energ Convers Manag 44:2159–2174. https://doi.org/10.1016/S0196-8904(02)00236-4
Seo JH, Lee YH, Kim YH (2014) Feature selection for very short-term heavy rainfall prediction using evolutionary computation. Adv Meteorol. https://doi.org/10.1155/2014/203545
Singh S, Gill J (2014) An optimized neural network model for relative humidity prediction. Int J Res Advent Technol 2:381–385. http://www.ijrat.org/downloads/april-2014/paper%20id-242014165.pdf
Troncoso A, Salcedo-Sanz S, Casanova-Mateo C, Riquelme JC, Prieto L (2015) Local models-based regression trees for very short-term wind speed prediction. Renew Energy 81:589–598. https://doi.org/10.1016/j.renene.2015.03.071
Wu YJ, Xue YS, Wang HH, Xie YY, Xue F, Wen FS, Dong ZY (2012) Extension of power system early-warning defense schemes by integrating typhoon information. Int Conf Sustain Power Gener Supply. https://doi.org/10.1049/cp.2012.1822
Xiong P (2011) Categorising methods of decision tree. The algorithms of data mining and Clementine practice. Tsinghua University Press, Beijing, pp 40–53
Xu GW, Xiu CB, Wan ZK (2015) Hysteretic chaotic operator network and its application in wind speed series prediction. Neurocomputing 165:384–388. https://doi.org/10.1016/j.neucom.2015.03.027
Ying M, Zhang W, Yu H, Lu XQ, Feng JX, Fan YX, Zhu YT, Chen DQ (2014) An overview of the China Meteorological Administration tropical cyclone database. J Atmos Ocean Technol 31:287–301. https://doi.org/10.1175/JTECH-D-12-00119.1
Zhang Y, Chen LF, Liu QH, Li XW (2004) Topographic and spatial-scaling effects on the sunlit time of the different terrains. In: IEEE International Geoscience and Remote Sensing Symposium. https://doi.org/10.1109/IGARSS.2004.1370042
Zhou RX, Gao WS, Zhang BW, Fu XG, Chen QZ, Huang S, Liang YF (2014) Prediction of tropical cyclones’ characteristic factors on Hainan Island using data mining technology. Adv Meteorol. https://doi.org/10.1155/2014/735491
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Funding and support
This study was funded by Hainan Power Grid Corporation through “Integrated demonstration project of regional smart grid” (No. 2013BAA01B03.). Electric Power Research Institute of China Southern Power Grid Corporation, also makes contributions to collecting part of research data in the process of completing this article. Thanks for all of their efforts.
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Responsible Editor: M. Kaplan.
Rights and permissions
About this article
Cite this article
Zhou, R., Gao, W., Zhang, B. et al. A new prediction model of daily weather elements in Hainan province under the typhoon weather. Meteorol Atmos Phys 131, 137–156 (2019). https://doi.org/10.1007/s00703-017-0567-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00703-017-0567-0