집중호우 시기 기계학습 및 PM기법을 이용한 수문학적 강우보정에 관한 연구
A Study on Hydrological Rainfall Adjustment using Machine Learning and Probability Matching Method during Heavy Rainfall Season
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In meteorological data, various studies are being conducted to improve the prediction performance of rainfall with irregular patterns, unlike temperature and solar radiation with certain patterns. Especially in the case of the short-term forecast model for Dong-Nae Forecasts provided by the Korea Meteorological Administration (KMA), forecast data are provided at 6-hour intervals, and there is a limit to analyzing the impact of disasters. In this study, Hydrological Quantitative Precipitation Forecast (HQPF) information was generated by applying the machine learning method to Local ENsemble prediction system (LENS), Radar-AWS Rainrates (RAR), AWS and ASOS observation data and Dong-Nae Forecast provided by the KMA. Through the preprocessing process, the temporal and spatial resolutions of all the data were converted to the same resolution, and the predictor of machine learning was derived through the factor analysis of the predictor. Considering the processing speed and expandability, the XGBoost method of machine learning was applied, and the Probability Matching (PM) method was applied to improve the prediction accuracy of heavy rainfall. As a result of evaluating the HQPF performance produced for 14 heavy rainfall events that occurred in 2020, it was found that the predicted performance of HQPF was improved quantitatively and qualitatively.
Abstract
In meteorological data, various studies are being conducted to improve the prediction performance of rainfall with irregular patterns, unlike temperature and solar radiation with certain patterns. Especially in the case of the short-term forecast model for Dong-Nae Forecasts provided by the Korea Meteorological Administration (KMA), forecast data are provided at 6-hour intervals, and there is a limit to analyzing the impact of disasters. In this study, Hydrological Quantitative Precipitation Forecast (HQPF) information was generated by applying the machine learning method to Local ENsemble prediction system (LENS), Radar-AWS Rainrates (RAR), AWS and ASOS observation data and Dong-Nae Forecast provided by the KMA. Through the preprocessing process, the temporal and spatial resolutions of all the data were converted to the same resolution, and the predictor of machine learning was derived through the factor analysis of the predictor. Considering the processing speed and expandability, the XGBoost method of machine learning was applied, and the Probability Matching (PM) method was applied to improve the prediction accuracy of heavy rainfall. As a result of evaluating the HQPF performance produced for 14 heavy rainfall events that occurred in 2020, it was found that the predicted performance of HQPF was improved quantitatively and qualitatively.
참고문헌 (11)
- Chen, T., "Xgboost: extreme gradient boosting, R package version 0.4-2", 1~4 (2015)
- Ebert, E. E., "Ability of a Poor Man’s ensemble to predict the probability and distribution of precipitation", Monthly Weather Review, 129(10), pp.2461~2480 (2001)
- Friedman, J. H., "Additive logistic regression : a statistical view of boosting", The Annals of Statistics, 28(2), pp.337~407 (2000)
- Ghada, W., "Machine learning approach to classify rain type based on this disdrometers and cloud observations", Atmosphere, 10(5), pp.251~ (2019)
- Hong, W. C., "Rainfall forecasting by technological machine learning models", Applied Mathematics and Computation, 200(1), pp.41~57 (2008)
- 장동호, "가변적 지역평균 단순 크리깅을 이용한 남한 지역 고해상도 기온 및 강수 분포도 작성 및 평가", 기후연구, 10(2), pp.165~182 (2015), 기후연구소[DOI]
- 강부식, "중규모수치예보자료의 정량적 강수추정량 개선을 위한 인공신경망기법", 한국수자원학회 논문집, 44(2), pp.97~107 (2011), 한국수자원학회
- Ke, G., "LightGBM : A Highly efficient gradient boosting decision tree", 31st Conference on Neural Information Processing Systems, pp.3149~3157 (2017)
- 김세현, "기상청 고해상도 국지 앙상블 예측 시스템 구축 및 성능 검증", 대기, 25(1), pp.67~83 (2015), 한국기상학회
- Ko, C. M., "The Development of a quantitative precipitation forecast correction technique based on machine learning for hydrological applications", Atmosphere, 11(1), pp.111~ (2020)
- "KMA" (2020)[URL]