Abstract
In this paper, we proposed two improved methods to solve the problems of current machine learning algorithm in the study of weather forecast revision. So this study can be divided into two parts. First of all, contrary to the previous machine learning algorithm with only one machine learning model applied for a vast area, a clustering algorithm is proposed to divide the vast area into multiple areas with different models for forecast correction. Secondly, Considering ECMWF the forecast of ECMWF with multiple initial times, a double-model correction model based on XGBoost machine learning algorithm is proposed. To test the new approach for the daily max and min temperature forecasts, the 2-m surface air temperature in the China area from the ECMWF (European Centre for Medium-Range Weather Forecasts) and the observatory meteorological observation data from china national stations are used. The data ranged from July 2017 to September 2019. We used meal weight interpolation method and sliding time window method to construct sample data. The new approach is compared with the multiple linear regression, random forest and SVM algorithms which are often used in weather forecast correction, it shows better numerical performance. The root mean square error (RMSE) and forecast accuracy are used to evaluate the model, and the forecast is better after the model is revised. The applicability of the model is verified by continuous test data (September 2019), and the experimental results show that the model has good practical value.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Betts, A.K., Ball, J.H., Beljaars, A.C.M., et al.: The land surface-atmosphere interaction: a review based on observational and global modeling perspectives. J. Geophys. Res. 101(D3), 7209 (1996)
Cassola, F., Burlando, M.: Wind speed and wind energy forecast through kalman filtering of numerical weather prediction model output. Appl. Energy 99, 154–166 (2012)
Chen, T., He, T.: Higgs boson discovery with boosted trees. In: Proceedings of the 2014 International Conference on High-Energy Physics and Machine Learning - Volume 42, HEPML 2014, pp. 69–80 (2014). JMLR.org
Delle Monache, L., Eckel, F.A., Rife, D.L., et al.: Probabilistic weather prediction with an analog ensemble. Mon. Weather Rev. 141(10), 3498–3516 (2013)
Glahn, H.R., Lowry, D.A.: The use of model output statistics (MOS) in objective weather forecasting. J. Appl. Meteorol. 11(8), 1203–1211 (1972)
Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Trans. Image Process. 13(10), 1327–1344 (2004)
Haupt, S.E., Kosovic, B.: Big data and machine learning for applied weather forecasts forecasting solar power for utility operations. In: IEEE Symposium Series on Computational Intelligence. IEEE (2015)
Peng, K., Leung, V.C.M., Huang, Q.: Clustering approach based on mini batch kmeans for intrusion detection system over big data. IEEE Access 6, 11897–11906 (2018)
Sun, L., Ge, C., Huang, X., Yingjie, W., Gao, Y.: Differentially private real-time streaming data publication based on sliding window under exponential decay. Comput. Mater. Continua 58(1), 61–78 (2019)
Lemcke, C., Kruizinga, S.: Model output statistics forecasts: three years of operational experience in the Netherlands. Mon. Weather Rev. 116(5), 1077–1090 (1988)
Li, H., Yu, C., Xia, J., et al.: A model output machine learning method for grid temperature forecasts in the Beijing area. Adv. Atmos. Sci. 36(10), 1156–1170 (2019)
Liangmin, F., Qiuxue, Z., Lan, K., et al.: Study on 2Â m temperature bias correction of EC model in sichuan province. Plateau and Mountain Meteorology Research (2019)
Bahrami, K., Shi, F., Rekik, I., Shen, D.: Convolutional neural network for reconstruction of 7T-like Images from 3T MRI using appearance and anatomical features. Springer (2016)
Lupo, A.R., Market, P.S.: The application of a simple method for the verification of weather forecasts and seasonal variations in forecast accuracy. Weather Forecast. 17(4), 891–889 (2002)
Ning, M., Guan, J., Liu, P., Zhang, Z., O’Hare, G.M.P.: GA-BP air quality evaluation method based on fuzzy theory. Comput. Mater. Continua 58(1), 215–227 (2019)
Luo, M., Wang, K., Cai, Z., Liu, A., Li, Y., Cheang, C.F.: Using imbalanced triangle synthetic data for machine learning anomaly detection. Comput. Mater. Continua 58(1), 15–26 (2019)
Rasp, S., Lerch, S.: Neural networks for post-processing ensemble weather forecasts. Monthly Weather Rev. (2018)
Young-Kyungseo, D.K.: The 3-hour-interval prediction of ground-level temperature in south korea using dynamic linear models 20(4), 575–582 (2003)
Acknowledgment
This work is supported by National Major Project (No. 2017ZX03001021-005), Sichuan science and Technology Program (2019YFG0212) and Sichuan Science and Technology Program (2018GZ0184).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Mao, K., Xue, C., Zhao, C., He, J. (2020). A Research for 2-m Temperature Prediction Based on Machine Learning. In: Sun, X., Wang, J., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2020. Lecture Notes in Computer Science(), vol 12239. Springer, Cham. https://doi.org/10.1007/978-3-030-57884-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-57884-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57883-1
Online ISBN: 978-3-030-57884-8
eBook Packages: Computer ScienceComputer Science (R0)