Wavelet-based prediction method for ground temperature in South Korea†
Jieun Choi 1· Yaeji Lim 2
12Department of Statistics, Chung-Ang University
Correspondence to: † This research was supported by the Chung-Ang University Research Scholarship Grants in 2021.
1 Postgraduate student, Department of Statistics, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Korea.
2 Associate professor, Department of Statistics, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. E-mail: yaeji.lim@gmail.com
1 Postgraduate student, Department of Statistics, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Korea.
2 Associate professor, Department of Statistics, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Korea. E-mail: yaeji.lim@gmail.com
Received January 7, 2023; Revised February 8, 2023; Accepted February 9, 2023.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- The ground temperature is mainly used as input and verification data for agriculture, numerical forecasts, and climate models. As the importance of ground temperature is highlighted in various application fields such as numerical models and agricultural fields, prediction accuracy of the ground temperature is being raised. In this paper, the ground temperature values of five cities in South Korea are predicted using a wavelet decomposition-based prediction model. For each component obtained through the wavelet decomposition, ARIMA, SVR, and ANN methods are applied. Then the results are compared with the results of applying the prediction methodology directly to the original data. We observe the superiority of the methodologies applied with the wavelet decomposition in the prediction of ground temperature. Based on the results of the paper, the ground temperature can be predicted more accurately using wavelet-based methods, and we expect that the results may contribute to the agricultural field.
- Keywords : ANN, ARIMA, climate prediction, ground temperature, SVR, wavelet decomposition.
Full Text(PDF) Free
