Abstract
It is necessary for mining meteorological big data to build a machine learning model by using historical data to predict the future meteorological elements. This work is significant and has a technical challenge. However, the maintained data of the small cities and the medium cities are very limited due to historical reasons. It is adverse to build an accurate forecast model. Aiming at this problem, a temperature forecast method based on transfer learning technique is proposed. It extends the data of the target city by transferring the data from related cities. It builds a forecast model based on the extended dataset, and then solves the problem of the insufficient samples in machine learning. In this experiment, the temperature sequence of Gaoyao weather station in Zhaoqing area is extended according to the yearly average temperature from 1884 to 1997 of Hongkong. It is corrected by Macau data. Temperature trend of Zhaoqing area is modeled by the time power function and the least square method. The fitting curves and the regression function of the temperature change are obtained. The forecasting model is tested by the actual temperature data of 2014, 2015 and 2016. The results support the effectiveness of the proposed method and they also justify the superiority of applying data transfer to temperature forecast.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Wang, M., Li, W., Wang, X.: Transferring a generic pedestrian detector towards specific scenes. In: Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, pp. 3274–3281, IEEE (2012)
Zhang, Z., Jin, X., Li, L., et al.: Multi-domain active learning for recommendation. In: Proceeding of 30th AAAI Conference on Artificial Intelligence (2016)
Wan, C., Jin, X., Ding, G., et al.: Gaussian cardinality restricted boltzmann machines. In: Proceeding of 29th AAAI Conference on Artificial Intelligence (2015)
Zhang, S., Jin, X., Shen, D., et al.: Short text classification by detecting information path. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge Management (2013)
Wang, X., Wang, M., Li, W.: Scene-specific pedestrian detection for static video surveillance. IEEE Trans on PAMI 36(2), 361–374 (2014)
Jin, X., Lu, Y., Shi, C.: Distribution discovery: Local analysis of temporal rules. PAKDD 2002, 469–480 (2002)
Jin, X., Lu, Y., Shi, C.: Similarity measure based on partial information of time series. In: Proceedings of 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2002)
Wang, Y.: Application of fuzzy time series model in short-term climate prediction. J. Nanjing Univ. Inf. Sci. Technol. 4, 316–320 (2012). Chinese
Haylock, M., Peterson, T., Alves, L., et al.: Trends in total and extreme South American rainfall in 1960–2000 and links with sea surface temperature. J. Clim. 19(8), 1490–1512 (2006)
Thorne, P., Willett, K., Allsn, R., et al.: Guiding the creation of a comprehensive surface temperature resource for twenty-first-century climate science. Bull. Amer. Meteor. Soc. 92, ES40–ES47 (2001)
Muller, R., Rohde, R., Jacobsen, R., et al.: A new estimate of the average earth surface land temperature spanning 1753 to 2011. Geoinfor. Geosta. Overview (2013). doi:10.4172/gigs.1000101
He, Q., Zhao, X., Shi, Z.: Minimal consistent subset for hyper surface classification method. J. Pattern Recogn. Artif. Intell. 22(1), 95–108 (2008). doi:10.1142/S0218001408006132
Xiong, B., Yin, Z.: Fast non-localmeans for image de-noising on moving average and modified weight function. J. Image Graph. 17(5), 628–634 (2012). Chinese
Kruger, U., Xie, L.: Partial least squares. In: Statistical monitoring of complex multivariate processes: With applications in industrial process control, pp. 375–409 (2012)
Cleophas, T., Zwinderman, A.: Partial least squares, pp. 197–213. Machine learning in medicine. Springer, Netherlands (2013)
Abdi, H.: Partial least squares regression and projection on latent structure regression (PLS Regression). Wiley Interdisc. Rev. Comput. Stat. 2(1), 97–106 (2010)
Qu, F., Meng, X.: Source localization using TDOA and FDOA measurements based on constrained total least squares algorithm. J. Electron. Inf. Technol. 36(5), 1075–1081 (2014). Chinese
Seghouane, A.: New AIC corrected variants for multivariate linear regression model selection. IEEE Trans. Aerosp. Electron. Syst. 47(2), 1154–1165 (2011)
Aköz, O., Karsligil, M.: Severity detection of traffic accidents at intersections based on vehicle motion analysis and ultiphase linear regression. In: Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems. Piscataway, pp. 474–479, IEEE (2010)
Nandi, A., Yu, C., Bohannon, P., Ramakrishnan, R.: Data cube materialization and mining over Map Reduce. IEEE Trans. Knowl. Data Eng. 24(20), 1747–1759 (2012)
Wang, Z., Agrawal, D., Tan, K.: COSAC: A framework for combinatorial statistical analysis on cloud. IEEE Trans. Knowl. Data Eng. 25(9), 2010–2023 (2013)
Acknowledgments
This research was supported by Science and technology research project of Guangdong Meteorological Bureau (Grant No.2016B51), Science and technology research project of Zhaoqing Meteorological Bureau (Grant No.201609), Science and technology innovation project of Zhaoqing (Grant No.201624030904).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Huang, T., Jiao, F. (2017). Data Transfer and Extension for Mining Big Meteorological Data. In: Huang, DS., Bevilacqua, V., Premaratne, P., Gupta, P. (eds) Intelligent Computing Theories and Application. ICIC 2017. Lecture Notes in Computer Science(), vol 10361. Springer, Cham. https://doi.org/10.1007/978-3-319-63309-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-63309-1_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63308-4
Online ISBN: 978-3-319-63309-1
eBook Packages: Computer ScienceComputer Science (R0)