[논문]1시간 호우피해 규모 예측을 위한 AI 기반의 1ST-모형 개발

이준학; 이하늘; 강나래; 황석환; 김형수; 김수전

doi:10.3741/jkwra.2023.56.5.311

[국내논문] 1시간 호우피해 규모 예측을 위한 AI 기반의 1ST-모형 개발
Development of 1ST-Model for 1 hour-heavy rain damage scale prediction based on AI models 원문보기

Journal of Korea Water Resources Association = 한국수자원학회논문집, v.56 no.5, 2023년, pp.311 - 323

이준학 (인하대학교 스마트시티공학과) , 이하늘 (인하대학교 스마트시티공학과) , 강나래 (한국건설기술연구원 수자원하천연구본부) , 황석환 (한국건설기술연구원 수자원하천연구본부) , 김형수 (인하대학교 사회인프라공학과) , 김수전 (인하대학교 사회인프라공학과)

초록
AI-Helper

집중호우, 홍수 및 도시침수와 같은 재해를 저감시키기 위하여 자연 재난으로 인한 재해의 발생 여부를 사전에 파악하는 것은 중요하다. 현재 국내는 기상청에서 운영하고 있는 호우주의보 및 호우경보를 발령하고 있지만, 이는 전국에 일괄적인 기준으로 적용하고 있어 사전에 호우로 인한 피해를 명확하게 인지하지 못하고 있는 실정이다. 따라서, 일괄된 기준을 지역적 특성을 반영한 호우특보 기준으로 재설정하고 1시간 후에 강우로 발생할 수 있는 피해의 규모를 예측하고자 하였다. 연구 대상 지역으로는 호우피해가 가장 빈번하게 발생하였던 경기도 지역으로 선정하였고, 강우량 및 호우 피해액 자료를 활용하여 지역적 특성을 고려한 시간단위 재해 유발 강우를 설정하였다. 강우에 의한 호우피해 발생 여부를 예측하는 모형을 개발하기 위해 재해 유발 강우 및 강우 자료를 활용하였으며, 머신러닝 기법인 의사 결정 나무 모형과 랜덤 포레스트 모형을 활용하여 분석 및 비교하였다. 또한 1시간 후의 강우를 예측하기 위한 모형으로는 장단기 메모리, 심층 신경망 모형을 활용하여 분석 및 비교하였다. 최종적으로 예측 모형을 통해 예측된 강우를 훈련된 분류 모형에 적용하여 1시간 후 호우에 의한 규모별 피해 발생 여부를 예측하였고, 이를 1ST-모형이라고 정의하였다. 본 연구를 통해 개발된 1ST-모형을 활용하여 예방 및 대비 차원의 재난관리를 실시한다면 호우로 인한 피해를 저감하는데 기여 할 수 있을 것으로 판단된다.

Abstract ▼ AI-Helper

In order to reduce disaster damage by localized heavy rains, floods, and urban inundation, it is important to know in advance whether natural disasters occur. Currently, heavy rain watch and heavy rain warning by the criteria of the Korea Meteorological Administration are being issued in Korea. However, since this one criterion is applied to the whole country, we can not clearly recognize heavy rain damage for a specific region in advance. Therefore, in this paper, we tried to reset the current criteria for a special weather report which considers the regional characteristics and to predict the damage caused by rainfall after 1 hour. The study area was selected as Gyeonggi-province, where has more frequent heavy rain damage than other regions. Then, the rainfall inducing disaster or hazard-triggering rainfall was set by utilizing hourly rainfall and heavy rain damage data, considering the local characteristics. The heavy rain damage prediction model was developed by a decision tree model and a random forest model, which are machine learning technique and by rainfall inducing disaster and rainfall data. In addition, long short-term memory and deep neural network models were used for predicting rainfall after 1 hour. The predicted rainfall by a developed prediction model was applied to the trained classification model and we predicted whether the rain damage after 1 hour will be occurred or not and we called this as 1ST-Model. The 1ST-Model can be used for preventing and preparing heavy rain disaster and it is judged to be of great contribution in reducing damage caused by heavy rain.

주제어

표/그림 (28)

그림 Fig. 1. Flow chart of this study
그림 Fig. 2. Gyeonggi-do province and rainfall stations
그림 Fig. 3. Structure of random forest
그림 Fig. 4. Structure of decision tree
그림 Fig. 5. Structure of long short-term memory
그림 Fig. 6. Structure of deep neural network
표 Table 1. Confusion matrix for performance evaluation of the model
표 Table 2. Each performance evaluation index
표 Table 3. Frequency of heavy rain damage on the provinces and cities
그림 Fig. 7. Cumulative distribution functions for rainfall and rain damage
표 Table 4. Estimated hazard-triggering rainfall on the cities
표 Table 5. Confusion matrix for the estimation of hazard-triggering rainfall (21.4 mm/12 hr)
표 Table 6. Confusion matrix for the estimation of hazard-triggering rainfall (24.6 mm/12 hr)
표 Table 7. Confusion matrix for the estimation of hazard-triggering rainfall (50.6 mm/12 hr)
표 Table 8. Confusion matrix for watch of KMA (110 mm/12 hr)
표 Table 9. Confusion matrix for warning of KMA (180 mm/12 hr)
표 Table 10. Comparison of F1-Score for standard criteria and Hazard- triggering rainfall
그림 Fig. 8. Comparison of rainfall predicted by long short-term memory model and observed values
표 Table 11. Confusion matrix for evaluating predictive performance of decision tree
표 Table 12. Confusion matrix for evaluating predictive performance of random forest
표 Table 13. Model summary of long short-term memory model
표 Table 14. Configuring the parameters of the long short-term memory model
그림 Fig. 9. Comparison of rainfalls predicted by deep neural network model and observed values
표 Table 15. Evaluation for predictive performance of long short-term memory model
표 Table 16. Model summary of deep neural network model
표 Table 17. Configuring the parameters of the deep neural network model
표 Table 18. Evaluation for predictive performance of the deep neural network model
표 Table 19. Confusion matrix for evaluating predictive performance of 1ST-Model

참고문헌 (44)

Bae, S.W., and Yu, J.S. (2018). "Predicting the real estate price index？using machine learning methods and time series analysis？model." Korean Association for Housing Policy Studies, Vol.？26, No. 1, pp. 107-133.
Bae, Y.H., Koh, D.K., and Cho, Y.S. (2005). "Numerical simulations？of flood inundations with FLUMEN." Journal of Korea Water？Resources Association, Vol. 38, No. 5, pp. 355-364.
Cepeda, J., Hoeg, K., and Nadim. F. (2010). "Landslide-triggering？rainfall thresholds: A conceptual framework." Quarterly？Journal of Engineering Geology and Hydrogeology, Vol. 43,？No. 1, pp. 69-84.
Choi, C.H., Kim, J.S., Kim, D.H., Lee, J.H., Kim, D.H., and Kim,？H.S. (2018). "Development of heavy rain damage prediction？functions in the seoul capital Area using machine learning？techniques." Journal of The Korean Society of Hazard？Mitigation, vol. 18, no. 7, pp. 435-447.
Choi, J.H., and Kim S.K. (2009). "A Study on exploration of the？recommended model of decision tree to predict a hard-tomeasure mesurement in anthropometric survey." The Korean？Journal of Applied Statistics, Vol. 22, No. 5, pp. 923-935.
Choo, T.H. (2019). Development of estimation functions for wind？wave damage based on disaster statistics. Methodology development for the estimation and prediction of direct and indirect？damages/losses from flood and wind disasters report, Inha？University Industry-University Cooperation Foundation.
Chun, B.S., Lee, T.W., Kim, S.W., Kim, J.G., Jang, K.C., Chun, J.W.,？Jang, W.S., and Shin, Y.C. (2020). "Estimation of DNN-based？soil moisture at mountainous regions." Journal of The Korean？Society of Agricultural Engineers, Vol. 62, No. 5, pp. 93-103.
Chung, G.H. (2019). Development of estimation functions for heavy？snow damage based on disaster statistics. Methodology development for the estimation and prediction of direct and indirect？damages/losses from flood and wind disasters report, Inha？University Industry-University Cooperation Foundation.
Garcia-Urquia, E. (2016). "Establishing rainfall frequency contour？lines as thresholds for rainfall-induced landslides in Tegucigalpa, Honduras, 1980-2005," Natural Hazards, Vol. 82,？No. 3, pp. 2107-2132.

상세보기
Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory."？Neural Computation, Vol. 9, No. 8, pp. 1735-1780.

상세보기
Joo, D.H., Na, R., Kim, H.Y., Choi, G.H., Kwon, J.H., and Yoo, S.H.？(2022). "Analysis of the optimal window size of hampel filter？for calibration of real-time water level in agricultural reservoirs."？Journal of The Korean Society of Agricultural Engineers, Vol.？64, No. 3, pp. 9-24.

원문보기 상세보기
Jung, J.W., Mo, H.R., Lee, J.H., Yoo, Y.H., and Kim, H.S. (2021).？"Flood stage forecasting at the Gurye-Gyo station in Sumjin？River using LSTM-based deep learning models." Journal of？the Korean Society of Hazard Mitigation, Vol. 21, No. 3, pp.？193-201.
Jung, S.H., Cho, H.S., Kim, J.Y., and Lee, G.H. (2018). "Prediction？of water level in a tidal river using a deep-learning based？LSTM model." Journal of Korea Water Resources Association,？Vol. 51, No. 12, pp. 1207-1216.

원문보기 상세보기
Kang, S.M., Park, M.J., Kim, S. H., and Kim, S.J. (2007). "A study？on the mitigation of inundation damage using flood inundation？analysis model FLUMEN-for the part of Jinwi+cheon reach."？Journal of The Korean Society of Civil Engineers, Vol. 27, No.？6B, pp. 583-590.
Kim, D.H., Kim J.W., Kwak, J.W., Aimi, Kim, J.S., and Kim, H.S.？(2020). "Development of water level prediction models using？deep neural network in mountain wetlands." Journal of the？Korean Wetland Society, Vol. 22, No. 2, pp. 106-112.
Kim, D.H., Lee, K.S., Hwang-Bo, J.G., Kim, H.S., and Kim, S.J.？(2022). "Development of the method for flood water level？forecasting and flood damage warning using an AI-based？model." Journal of Korean Society of Hazard Mitigation, Vol.？25, No. 4, pp. 163-168.
Kim, H.I., and Kim, B.H., (2020). "Analysis of major rainfall factors？affecting inundation based on observed rainfall and random？forest." Journal of the Korean Society of Hazard Mitigation,？Vol. 20, No. 6, pp. 301-310.
Kim, H.S. (2019a). Development of heavy rain damage prediction？function based on disaster statistics. Methodology development for the estimation and prediction of direct and indirect？damages/losses from flood and wind disasters report, Inha？University Industry-University Cooperation Foundation.
Kim, J.S. (2021). Development of prediction and warning technique？of heavy rain damage risk based on ensemble machine？learning and risk matrix. Ph. D. dissertation, Graduate School？of Inha University.
Kim, J.S., Choi, C.H., Kim, D.H., Joo, H.J., Kim, J.U., and Kim,？H.S. (2018). "Establishment of hazard-triggering rainfall according to heavy rain damage scale: Focused on Gyeonggido." Journal of Climate Research, Vol. 13, No. 4, pp. 297-311.

상세보기
Kim, J.S., Kim, D.H, Wang, W.J., Lee, H.N., Lee, M.J., and Kim,？H.S. (2021). "Comparative analysis of linear model and deep？learning algorithm for water usage prediction." Journal of？Korea Water Resources Association, Vol. 54, pp. 1083-1093.
Kim, J.S., Lee, J.H., Kim, D.H., Choi, C.H., Lee, M.J., and Kim,？H.S. (2019a). "Developing a prediction model (Heavy rain？damage occurrence probability) based on machine learning."？Journal of the Korean Society of Hazard Mitigation, Vol. 19,？No. 6, pp. 115-127.
Kim, S.H., Kim, H.J., Lee, S.H., and Cho, Y.S. (2007). "Numerical？simulation of flood inundation with quadtree grid." Journal of？the Korean Society of Hazard Mitigation, Vol. 7, No. 2, pp.？45-52.
Kim, S.J., and Kim, S.H. (2021). "A review of the methodology for？sophisticated data classification." Journal of the Chosun？Natural Science, Vol. 14, No. 1, pp. 27-34.
Kim, T.G. (2019b). Development of typhoon damage prediction？technology based on disaster statistics. Methodology development for the estimation and prediction of direct and indirect？damages/losses from flood and wind disasters report, Inha？University Industry-University Cooperation Foundation.
Kim, Y.H., Choi, D.Y., Chang, D.E., Yoo, H.D., and Jin, G.B. (2011).？"An improvement on the criteria of special weather report for？heavy rain considering the possibility of rainfall damage and？the recent, meteorological characteristics." Journal of Atmosphere, Vol. 21, No. 4, pp. 481-495.
Kim, Y.J., Kim, T.W., Yoon, J.S., and Kim, M.K. (2019b). "Study？of the construction of a coastal disaster prevention system？using deep learning." Journal of Ocean Engineering and？Technology, Vol. 33, No. 6, pp. 590-596.
Korea Meteorological Administration (KMA) (2007). A policy study？on the modification of the weather.
Lee, H.J., Jin, M.K., Lee, S.H., Moon, J.M., Lee, G.H., Lee, J.E., and？Lee, J.W. (2021). "A study on arrhythmia classification based？on local maximum scalogram using convolutional neural？network." Journal of the Transactions of the Korean Institute？of Electrical Engineers, Vol. 70, No. 5, pp. 791-804.
Lee, H.Y., and Kang, S.S. (2019). "Automatic word spacing of the？Korean sentences by using end-to-end deep neural network."？KIPS Transactions on Software and Data Engineering, Vol. 8,？No. 11, pp. 441-448.

원문보기 상세보기
Lee, T.G., and Shin, K.S. (2019). Performance comparison of natural？language processing model based on deep neural networks."？The Journal of Korean Institute of Communications and Information Sciences, Vol. 44, No. 7, pp. 1344-1350.
Lyu, Y.M., and Lee, E.H. (2022). "Application of neural networks to？predict Daecheong Dam water levels." Journal of the Korean？Society of Hazard Mitigation, Vol. 22, No. 1, pp. 67-78.
Ministry of the Interior and Safety (MOIS) (2021). The 2020 annual？natural disaster report.
Ministry of the Interior and Safety (MOIS) (2022). The 2021 annual？natural disaster report.
Oh, J.L, and Park, H.J. (2014). "Analysis of landslide triggering？rainfall threshold for prediction of landslide occurrence."？Journal of the Korean Society of Hazard Mitigation, Vol. 14,？No. 2, pp. 115-130.
Park, S.S., and Kang, B.S. (2014). "Differentiating scheme for the？storm warning criteria considering the regional disaster prevention capacity." Journal of Korean Society of Hazard Mitigation, Vol. 14, No. 5. pp. 67-76.
Powers, D.M. (2011). "Evaluation: From precision, recall and Fmeasure to ROC, informedness, markedness and correlation."？Journal of Machine Learning Technologies, Vol. 2, No. 1, pp.？37-63.
Seo, J.D. (2016). "Foreign exchange rate forecasting using the GARCH？extended Random forest model." Journal of Industrial Economics and Business, Vol. 29, No.5, pp. 1607-1628.
Song, C.Y. (2019). Development of disaster statistics-based wind？(strong wind) damage prediction technology. Methodology？development for the estimation and prediction of direct and？indirect damages/losses from flood and wind disasters report,？Inha University Industry-University Cooperation Foundation.
Song, Y.H., Song, Y.S., Park, M.J., and Lee, J.H. (2014). "Flood？forecasting estimation methodology of standard rainfall for？urban mid and small rivers considering upper- and downstream water levels." Journal of Korean Society of Hazard？Mitigation, Vol. 14, No. 2, pp. 289-298.
Song, Y.S., Lee, P.S., Yeu, Y., and Kim, G.H. (2012). "Flood risk？mapping using 3D virtual reality based on Geo-spatial information." Journal of Korean Society for Geospatial Information？Science, Vol. 20, No. 4. pp. 97-104.
Song, Y.S., Lim, C.H., and Park, M.J. (2016). "A study on heavy？rain forecast evaluation and improvement method." Journal of？the Korean Society of Hazard Mitigation, Vol. 16, No. 2, pp.？113-121.
Tran, Q.K., and Song, S.K. (2017). "Water level forecasting based？on deep learning: A use case of Trinity River-Texas-The United？States." Journal of Korean Institute of Information Scientists？and Engineers, Vol. 44, No. 6, pp. 607-612.
Um, N.K., Woo, S.H., and Lee, S.H. (2007). "The hybrid model？using SVM and decision tree for intrusion detection." Journal？of The KIPS Transactions: PartC, Vol. 14, No. 1, pp. 1-6.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증