Korean Journal of Agricultural and Forest Meteorology (한국농림기상학회지)

Korean Society of Agricultural and Forest Meteorology (한국농림기상학회)
권호 표지
DOI QR코드

DOI QR Code

Error Characteristic Analysis and Correction Technique Study for One-month Temperature Forecast Data

1개월 기온 예측자료의 오차 특성 분석 및 보정 기법 연구

  • Yongseok Kim (Climate Change Assessment Division, National Institute of Agricultural Sciences) ;
  • Jina Hur (Climate Change Assessment Division, National Institute of Agricultural Sciences) ;
  • Eung-Sup Kim (Climate Change Assessment Division, National Institute of Agricultural Sciences) ;
  • Kyo-Moon Shim (Climate Change Assessment Division, National Institute of Agricultural Sciences) ;
  • Sera Jo (Climate Change Assessment Division, National Institute of Agricultural Sciences) ;
  • Min-Gu Kang (Climate Change Assessment Division, National Institute of Agricultural Sciences)
  • 김용석 (국립농업과학원 기후변화평가과) ;
  • 허지나 (국립농업과학원 기후변화평가과) ;
  • 김응섭 (국립농업과학원 기후변화평가과) ;
  • 심교문 (국립농업과학원 기후변화평가과) ;
  • 조세라 (국립농업과학원 기후변화평가과) ;
  • 강민구 (국립농업과학원 기후변화평가과)
  • Received : 2023.12.11
  • Accepted : 2023.12.21
  • Published : 2023.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we examined the error characteristic and bias correction method for one-month temperature forecast data produced through joint development between the Rural Development Administration and the H ong Kong University of Science and Technology. For this purpose, hindcast data from 2013 to 2021, weather observation data, and various environmental information were collected and error characteristics under various environmental conditions were analyzed. In the case of maximum and minimum temperatures, the higher the elevation and latitude, the larger the forecast error. On average, the RMSE of the forecast data corrected by the linear regression model and the XGBoost decreased by 0.203, 0.438 (maximum temperature) and 0.069, 0.390 (minimum temperature), respectively, compared to the uncorrected forecast data. Overall, XGBoost showed better error improvement than the linear regression model. Through this study, it was found that errors in prediction data are affected by topographical conditions, and that machine learning methods such as XGBoost can effectively improve errors by considering various environmental factors.

본 연구에서는 농촌진흥청과 홍콩과학기술대학교의 공동 개발로 생산된 1개월 예측 자료의 오차를 분석하고, 통계적 보정 기법을 활용한 오차 개선 효과를 살펴보고자 하였다. 이를 위해 2013년부터 2021년까지의 과거 예측(hindcast) 자료, 기상관측자료, 다양한 환경정보들을 수집하고 다양한 환경 조건에서의 오차 특성을 분석하였다. 최고기온과 최저기온의 경우, 해발고도와 위도가 높을 수록 예측 오차가 더 크게 나타났다. 평균적으로, 선형회귀모형과 XGBoost로 보정한 예측자료는 보정 전 예측자료보다 각각 0.203, 0.438(최고기온) 및 0.069, 0.390(최저기온) 정도의 RMSE가 감소했으며, 높은 고도와 위도에서의 오차 개선이 더 크게 나타났다. 모든 분석 조건에서 XGBoost가 선형회귀모형보다 우수한 오차 개선 효과를 나타냈다. 본 연구를 통해 예측 자료의 오차가 지형적 조건에 영향을 받는다는 사실을 확인하였고, XGBoost와 같은 기계학습법이 다양한 환경인자들을 고려하여 효과적으로 오차를 개선할 수 있다는 것을 확인하였다.

Keywords

Acknowledgement

본 연구는 농촌진흥청 국립농업과학원 "농업과학기반기술연구(과제번호: PJ016772)"의 지원으로 수행되었습니다.

References

  1. Chen T., C. Guestrin, 2016: Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 785-794.
  2. Ha, S., Y. T. Kim, E. S. Im, J. Hur, S. Jo, Y. S. Kim, and K. M. Shim, 2023: Impacts of meteorological variables and machine learning algorithms on rice yield prediction in Korea, International Journal of Biometeorology, https://doi.org/10.1007/s00484-023-02544-x
  3. Hur J., E.-S. Im, S. Ha, Y.-S. Kim, E.-S. Kim, J. Lee, S. Jo, K.-M. Shim, and M.-G. Kang, 2023: 1-month prediction on rice harvest date in South Korea based on dynamically downscaled temperature, Korean Journal of Agricultural and Forest Meteorology 25(4), 267-275 (in Korean with English abstract)
  4. Hur J., Y. S. Kim, S. Jo, K. M. Shim, J.-B. Ahn, M.-J. Choi, Y.-H. Kim, M. Kang, and W. J. Choi, 2021: Estimation of Waxy Corn Harvest Date over South Korea Using PNU CGCM-WRF Chain, Korean Journal of Agricultural and Forest Meteorology 23(4), 405-414 (in Korean with English abstract)
  5. Im, E. S., S. Ha, L. Qiu, J. Hur, S. Jo, and K. M. Shim, 2021: An evaluation of temperature-based agricultural indices over Korea from the high-resolution WRF simulation. Front Earth Sci 9, 656787. https://doi.org/10.3389/feart.2021.656787
  6. Jo S., J. Lee, K. M. Shim, J.-B. Ahn, J. Hur, Y. S. Kim, W. J. Choi, and M. Kang, 2022: The Advanced Bias Correction Method based on Quantile Mapping for Long-Range Ensemble Climate Prediction for Improved Applicability in the Agriculture Field, Korean Journal of Agricultural and Forest Meteorology 24(3), 155-163 (in Korean with English abstract)
  7. Pan Bingyue 2018: Application of XGBoost algorithm in hourly PM2.5 concentration prediction, Earth and Environmental Science 113, 012127.
  8. Qiu, L., E. S. Im, J. Hur, and K. M. Shim, 2020: Added value of very high resolution climate simulations over South Korea using WRF modeling system. Climate Dynamics 54(1), 173-189. https://doi.org/10.1007/s00382-019-04992-x
  9. Saha, S., S. Moorthi, X. Wu, J. Wang, S. Nadiga, P. Tripp, D. Behringer, Y.-T. Hou, H.-y. Chuang, M. Iredell, M. Ek, J. Meng, R. Yang, M. P. Mendez, H. Dool, O. Zhang, W. Wang, M. Chen, and E. Becker, 2014: The NCEP climate forecast system version 2. Journal of Climate 27, 2185-2208. https://doi: 10.1175/JCLI-D-12-00823.1
  10. Skamarock, W. C., J. B. Klemp, J. Dudhia, D. O. Gill, D. M. Barker, M. G. Duda, X.-Y. Huang, W. Wang, and J. G. Powers, 2008: A description of the advanced research WRF version 3. NCAR Tech. Note, NCAR/TN- 475+STR, 125 pp.