Korean Journal of Agricultural and Forest Meteorology (한국농림기상학회지)

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

DOI QR Code

Study on Improvement of Frost Occurrence Prediction Accuracy

서리발생 예측 정확도 향상을 위한 방법 연구

  • Kim, Yongseok (Climate change Assessment Division, National Institute of Agricultural Sciences) ;
  • Choi, Wonjun (Climate change Assessment Division, National Institute of Agricultural Sciences) ;
  • Shim, Kyo-moon (Climate change Assessment Division, National Institute of Agricultural Sciences) ;
  • Hur, Jina (Climate change Assessment Division, National Institute of Agricultural Sciences) ;
  • Kang, Mingu (Climate change Assessment Division, National Institute of Agricultural Sciences) ;
  • Jo, Sera (Climate change Assessment Division, National Institute of Agricultural Sciences)
  • 김용석 (국립농업과학원 기후변화평가과) ;
  • 최원준 (국립농업과학원 기후변화평가과) ;
  • 심교문 (국립농업과학원 기후변화평가과) ;
  • 허지나 (국립농업과학원 기후변화평가과) ;
  • 강민구 (국립농업과학원 기후변화평가과) ;
  • 조세라 (국립농업과학원 기후변화평가과)
  • Received : 2021.11.01
  • Accepted : 2021.12.20
  • Published : 2021.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we constructed using Random Forest(RF) by selecting the meteorological factors related to the occurrence of frost. As a result, when constructing a classification model for frost occurrence, even if the amount of data set is large, the imbalance in the data set for development of model has been analyzed to have a bad effect on the predictive power of the model. It was found that building a single integrated model by grouping meteorological factors related to frost occurrence by region is more efficient than building each model reflecting high-importance meteorological factors. Based on our results, it is expected that a high-accuracy frost occurrence prediction model will be able to be constructed as further studies meteorological factors for frost prediction.

본 연구에서는 서리발생과 관련된 기상요인을 선정하여 랜덤포레스트(RF)를 이용한 서리발생 유무 분류모형을 구축하였고, 이와 더불어 기상인자의 중요도와 데이터 세트를 구성하는 방법들을 비교하는 실험을 수행하였다. 그 결과, 서리발생에 대한 분류 모형을 구축할 경우에 데이터 세트의 양이 많더라도 모형 구축을 위해 학습하기 위한 데이터 세트에서 특정 값이 월등히 많은 불균형은 모형의 예측력에 좋지 못한 영향을 미치는 것으로 분석되었다. 또한, 이번 연구에서 수집된 25지역의 서리발생과 관련된 기상요인에 대해 지역별로 그룹화하여 중요도가 높은 기상요인을 반영한 모형 구축하는 것보다 하나의 통합된 모형을 구축하는 것이 더 효율적인 것으로 나타났다. 이번 연구를 통해 분석된 결과와 서리예측을 위한 기상요인에 대한 추가분석 연구를 수행한다면 정확도 높은 서리발생 예측모형을 구축할 수 있을 것이라 예상한다.

Keywords

Acknowledgement

이 연구는 농촌진흥청 국립농업과학원 농업과학기술 연구개발사업(과제번호: PJ015151)의 지원으로 수행되었습니다.

References

  1. Chun, J. A., H. J. Lee, S. H. Im, D. Kim, and S. S. Baek, 2021: Comparative assessment of frost event prediction models using logistic regression, random forest, and LSTM networks. Journal of Korea Water Resources Association 54(9), 667-680. https://doi.org/10.3741/JKWRA.2021.54.9.667
  2. Chung, U., H. C. Seo, and J. I. Yun, 2004: Site-specific frost warning based on topoclimatic estimation of daily minimum temperature. Korean Journal of Agricultural and Forest Meteorology 6(3), 164-169.
  3. Han, J. H., J. J. Choi., U. Chung., K. S. Cho, and J. P. Chun, 2009: Frostfall forecasting in the Naju pear production area based on discriminant analysis of climate data. Korean Journal of Agricultural and Forest Meteorology 11(1), 13-18. https://doi.org/10.5532/KJAFM.2009.11.1.013
  4. Kim, Y., K. M. Shim, M. P. Jung, and I. T. Choi, 2017: Study on the estimation of frost occurrence classification using machine learning methods. Korean Journal of Agricultural and Forest Meteorology 19(3), 86-92. https://doi.org/10.5532/KJAFM.2017.19.3.86
  5. Kwon, Y. A., H. S. Lee., W. T. Kwon, and K. O. Boo, 2008: The weather characteristics of frost occurrence days for protecting crops against frost damage. Journal of the Korean Geographical Society 43(6), 824-842.
  6. Lee, H., J. A. Chun, H. H. Han, and S. Kim, 2016: Prediction of frost occurrences using statistical modeling approaches. Advances in Meteorology 2016.
  7. Masaki, Y., 2021: Probability of frost occurrence based on meteorological observation in Japan. Meteorology and Atmospheric Physics 133, 693-705. https://doi.org/10.1007/s00703-020-00775-w
  8. Mort, N., and C. Robinson, 1996: A neural network system for the protection of citrus crops from frost damage. Computer and Electronics in Agriculture 16(3), 177-187. https://doi.org/10.1016/S0168-1699(96)00037-3
  9. Temeyer, B. R., W. A. Gallus Jr, K. A. Jungbluth, D. Burkheimer, and D. McCauley, 2003: Using an artificial neural network to predict parameters for frost deposition on Iowa bridgeways. Proceedings of the 2003 Mid-Continent Transportation Research Symposium, Iowa state University, Ames, IA, 2003.
  10. Zeinali, B., M. Teymouri, S. Asghari, M. Mohammadi, and V. Gupta, 2019: A study of frost occurrence and minimum temperatures in Iran. Journal of Earth System Science 128, 134. https://doi.org/10.1007/s12040-019-1152-3