머신러닝 기반의 강우추정 방법 개발
Development of Machine Learning Based Precipitation Imputation Method
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
강우 데이터는 습지관리, 수문모의, 수자원 관리와 같은 다양한 분야에서 활용되는 필수 입력자료 중 하나이다. 강우데이터를 활용하여 효율적인 수자원관리를 위해서는 기본적으로 데이터의 결측률을 최소화 시킴으로써 최대한 많은데이터를 확보하는 것이 필수적이다. 또한 미계측 지역에 대한 강우 데이터를 확보한다면 보다 효율적인 수문모의가가능하다. 그러나 결측 강우 데이터는 주로 통계학적 기법에 의해 추정되어 왔다. 본 연구의 목적은 데이터 간의 상관관계를 기반으로 새로운 데이터를 예측할 수 있는 머신러닝 알고리즘을 활용하여 결측 강우 데이터를 복원할 수 있는새로운 방법을 제안하고자 한다. 또한, 기존의 통계적 방법들과 비교하여 머신러닝 기법의 결측 강우 데이터 복원을위한 활용가치를 평가하고자 한다. 평가를 위해 대표적인 머신러닝 알고리즘인 Artificial Neural Network (ANN)과Random Forest (RF)을 적용하였다. 강우의 발생 유무를 분류하는 성능은 RF 알고리즘이 ANN 알고리즘보다 강우발생유무의 분류 정확도가 높은 것으로 나타났다. 분류 모형의 평가 지표인 F1-score나 Accuracy값이 RF는 0.80, 0.77인 반면에, ANN은 0.76, 0.71로 계산되었다. 또한 강우량을 추정하는 성능 역시 RF가 ANN 알고리즘보다 보다높은 정확도를 보였다. RF과 ANN 알고리즘의 RMSE은 2.8mm/day과 2.9mm/day이고, 값은 0.73, 0.68으로 계산되었다.
Abstract
Precipitation data is one of the essential input datasets used in various fields such as wetland management, hydrological simulation, and water resource management. In order to efficiently manage water resources using precipitation data, it is essential to secure as much data as possible by minimizing the missing rate of data. In addition, more efficient hydrological simulation is possible if precipitation data for ungauged areas are secured. However, missing precipitation data have been estimated mainly by statistical equations. The purpose of this study is to propose a new method to restore missing precipitation data using machine learning algorithms that can predict new data based on correlations between data. Moreover, compared to existing statistical methods, the applicability of machine learning techniques for restoring missing precipitation data is evaluated. Representative machine learning algorithms, Artificial Neural Network (ANN) and Random Forest (RF), were applied. For the performance of classifying the occurrence of precipitation, the RF algorithm has higher accuracy in classifying the occurrence of precipitation than the ANN algorithm. The F1-score and Accuracy values, which are evaluation indicators of the classification model, were calculated as 0.80 and 0.77, while the ANN was calculated as 0.76 and 0.71. In addition, the performance of estimating precipitation also showed higher accuracy in RF than in ANN algorithm. The RMSE of the RF and ANN algorithms was 2.8 mm/day and 2.9 mm/day, and the values were calculated as 0.68 and 0.73.
참고문헌 (27)
- Juan Antonio Bellido-Jiménez, "Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain", Atmosphere, 12(9), pp.1158~ (2021), MDPI AG[DOI]
- Breiman, L., "Random forests", Mach. Learn, 45, pp.5~32 (2001)
- Chris Funk, "The climate hazards infrared precipitation with stations—a new environmental record for monitoring extremes", Scientific Data, 2(1) (2015), Springer Science and Business Media LLC[DOI]
- George J. Huffman, "The TRMM Multisatellite Precipitation Analysis (TMPA): Quasi-Global, Multiyear, Combined-Sensor Precipitation Estimates at Fine Scales", Journal of Hydrometeorology, 8(1), pp.38~55 (2007), American Meteorological Society[DOI]
- 황석환, "강우레이더 자료를 이용한 면적 강수량 추정 내삽 기법의 오차 발생 특성 연구", 한국방재학회논문집, 22(6), pp.273~283 (2022), 한국방재학회[DOI]
- 장상민, "미계측지역의 위성강우 기반 가뭄감시 평가", 한국농공학회논문집, 60(2), pp.55~63 (2018), 한국농공학회[DOI]
- Robert J. Joyce, "CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal Resolution", Journal of Hydrometeorology, 5(3), pp.487~503 (2004), American Meteorological Society[DOI]
- 강나래, "레이더 강우 자료를 이용한 도시유역의 유출 모의", 한국습지학회지, 15(3), pp.413~422 (2013), 한국습지학회
- Jungho Kim, "Hybrid machine learning framework for hydrological assessment", Journal of Hydrology, 577, pp.123913~ (2019), Elsevier BV[DOI]
- Kim, B. S., "Combining radar and rain gauge rainfall estimates for flood forecasting using conditional merging method", World Environmental and Water Resources Congress 2007: Restoring Our Natural Habitat, pp.1~16 (2007)
- Kim, S. J., "Satellite rainfall monitoring : recent progress and its potential applicability", Korean Journal of Agricultural and Forest Meteorology, 1, pp.142~150 (1999)
- Jungho Kim, "Evaluation of the CMORPH high-resolution precipitation product for hydrological applications over South Korea", Atmospheric Research, 258, pp.105650~ (2021), Elsevier BV[DOI]
- Kim, K. T, "ntroduction of rainfall observation data and utilization cases using artificial satellites", Water and the Future: J. Korean Soc. Water Res, 46, pp.66~75 (2013)
- 권태용, "정량적 강우 추정을 위한 표준유역별 레이더 합성장 선택: 한강유역을 중심으로", 한국데이터정보과학회지, 33(6), pp.1021~1030 (2022), 한국데이터정보과학회
- Lee W. Larson, "Accuracy of precipitation measurements for hydrologic modeling", Water Resources Research, 10(4), pp.857~863 (1974), American Geophysical Union (AGU)[DOI]
- Mark New, "Precipitation measurements and trends in the twentieth century", International Journal of Climatology, 21(15), pp.1889~1922 (2001), Wiley[DOI]
- Hamidreza Mosaffa, "Application of machine learning algorithms in hydrology", Computers in Earth and Environmental Sciences, pp.585~591 (2022), Elsevier[DOI]
- 오승철, "수문학적 관점에서의 지반 변위 분석: 인공위성 강우데이터와 지하수위 연계", 한국수자원학회 논문집, 55(12), pp.1031~1039 (2022), 한국수자원학회
- 박기수, "강우유출수 처리목적 인공습지의 강우시 오염물질 저감특성에 관한 연구", 한국습지학회지, 15(1), pp.79~90 (2013), 한국습지학회
- Polishchuk, B., "The rain prediction in Australia based Big Data analysis and machine learning technology", 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), 1, pp.97~100 (2021)
- Rosenblatt, F., "The perceptron : a probabilistic model for information storage and organization in the brain", Psychological review, 65, pp.386~ (1958)
- Mahmood Sadat-Noori, "Groundwater level prediction using genetic programming: the importance of precipitation data and weather station location on model accuracy", Environmental Earth Sciences, 79(1) (2019), Springer Science and Business Media LLC[DOI]
- Abinash Sahoo, "Imputation of missing precipitation data using KNN, SOM, RF, and FNN", Soft Computing, 26(12), pp.5919~5936 (2022), Springer Science and Business Media LLC[DOI]
- Chaopeng Shen, "Editorial: Broadening the Use of Machine Learning in Hydrology", Frontiers in Water, 3 (2021), Frontiers Media SA[DOI]
- Soroosh Sorooshian, "Evaluation of PERSIANN System Satellite–Based Estimates of Tropical Rainfall", Bulletin of the American Meteorological Society, 81(9), pp.2035~2046 (2000), American Meteorological Society[DOI]
- Teegavarapu, R. S., "Infilling of rain gage records using radar (NEXRAD) data: Influence of spatial and temporal variability of rainfall processes", World Environmental and Water Resources Congress 2008: Ahupua'A, pp.1~9 (2008)
- Hristos Tyralis, "A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources", Water, 11(5), pp.910~ (2019), MDPI AG[DOI]