한국수자원학회논문집 (Journal of Korea Water Resources Association)

  • 제56권5호
  • /
  • Pages.311-323
  • /
  • 2023
  • /
  • 2799-8746(pISSN)
  • /
  • 2799-8754(eISSN)
한국수자원학회 (Korea Water Resources Association)
권호 표지
DOI QR코드

DOI QR Code

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

  • 이준학 (인하대학교 스마트시티공학과) ;
  • 이하늘 (인하대학교 스마트시티공학과) ;
  • 강나래 (한국건설기술연구원 수자원하천연구본부) ;
  • 황석환 (한국건설기술연구원 수자원하천연구본부) ;
  • 김형수 (인하대학교 사회인프라공학과) ;
  • 김수전 (인하대학교 사회인프라공학과)
  • Lee, Joonhak (Department of Smart City Engineering, Inha University) ;
  • Lee, Haneul (Department of Smart City Engineering, Inha University) ;
  • Kang, Narae (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Hwang, Seokhwan (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Hung Soo (Department of Civil Engineering, Inha University) ;
  • Kim, Soojun (Department of Civil Engineering, Inha University)
  • 투고 : 2023.01.17
  • 심사 : 2023.04.07
  • 발행 : 2023.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

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.

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.

키워드

과제정보

본 연구는 과학기술정보통신부 한국건설기술연구원 연구운영비지원(주요사업)사업으로 수행되었습니다(과제번호 20230115-001, 디지털뉴딜 기반 통합물관리 기술융합 플랫폼(IWRM-K) 개발).

참고문헌

  1. 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. https://doi.org/10.24957/hsr.2018.26.1.107
  2. 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. https://doi.org/10.3741/JKWRA.2005.38.5.355
  3. 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. https://doi.org/10.1144/1470-9236/08-066
  4. 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. https://doi.org/10.9798/KOSHAM.2018.18.7.435
  5. 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. https://doi.org/10.5351/KJAS.2009.22.5.923
  6. 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.
  7. 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.
  8. 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.
  9. 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. https://doi.org/10.1007/s11069-016-2297-x
  10. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  11. 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. https://doi.org/10.5389/KSAE.2022.64.3.009
  12. 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. https://doi.org/10.9798/KOSHAM.2021.21.3.193
  13. 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. https://doi.org/10.3741/JKWRA.2018.51.12.1207
  14. 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.
  15. 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.
  16. 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. https://doi.org/10.9798/KOSHAM.2022.22.4.145
  17. 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. https://doi.org/10.9798/KOSHAM.2020.20.6.301
  18. 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.
  19. 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.
  20. 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. https://doi.org/10.14383/cri.2018.13.4.297
  21. 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.
  22. 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. https://doi.org/10.9798/KOSHAM.2019.19.6.115
  23. 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.
  24. 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.
  25. 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.
  26. 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.
  27. 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. https://doi.org/10.26748/KSOE.2019.066
  28. Korea Meteorological Administration (KMA) (2007). A policy study on the modification of the weather.
  29. 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. https://doi.org/10.5370/KIEE.2021.70.5.791
  30. 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. https://doi.org/10.3745/KTSDE.2019.8.11.441
  31. 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. https://doi.org/10.7840/kics.2019.44.7.1344
  32. 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. https://doi.org/10.9798/KOSHAM.2022.22.1.67
  33. Ministry of the Interior and Safety (MOIS) (2021). The 2020 annual natural disaster report.
  34. Ministry of the Interior and Safety (MOIS) (2022). The 2021 annual natural disaster report.
  35. 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. https://doi.org/10.9798/KOSHAM.2014.14.2.115
  36. 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. https://doi.org/10.9798/KOSHAM.2014.14.5.67
  37. 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.
  38. 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.
  39. 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.
  40. 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.
  41. 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. https://doi.org/10.7319/kogsis.2012.20.4.097
  42. 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. https://doi.org/10.9798/KOSHAM.2016.16.2.113
  43. 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.
  44. 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.