한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

머신러닝을 이용한 침수 깊이와 위치예측 모델 개발

Development of Machine Learning based Flood Depth and Location Prediction Model

  • 강지욱 (포항공과대학교 IT융합공학과) ;
  • 박종혁 (포항공과대학교 IT융합공학과) ;
  • 한수희 (포항공과대학교 IT융합공학과) ;
  • 김경준 (포항공과대학교 IT융합공학과)
  • 투고 : 2022.12.21
  • 심사 : 2023.02.17
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 국지성 폭우로 인한 침수 피해가 빈번하게 발생함에 따라 침수 피해를 사전 예방하기 위한 침수 예측 연구가 진행되고 있다. 본 논문에서는 머신 러닝 기반으로 강우 데이터를 이용해 침수 깊이와 침수 위치를 예측하는 모델을 개발하는 방법을 연구한다. 실시간 강우량을 입력으로 사용하여 다양한 강우 분포 패턴에 강건하게 구성하고 적은 메모리로 모델을 학습시킬 수 있는 2가지 데이터 셋(set) 구성 방법을 제시하였다. 침수에 유의미한 영향을 미치는 valid total 데이터는 침수 위치는 잘 예측했지만, 특정 강우 패턴에 대해 값이 다르게 나타나는 경향을 띠었다. 부분적이지만 침수에 영향을 미치는 영역을 valid local이라 한다. Valid local은 고정점 방법에 대해서는 잘 학습되었지만, 임의점 방법에 대해서는 침수 위치를 정확하게 나타내지 못했다. 본 연구를 통해 실시간으로 침수 깊이와 위치를 예측할 수 있게 되어 큰 피해를 예방할 수 있을 것으로 예상된다.

With the increasing flood damage by frequently localized heavy rains, flood prediction research are being conducted to prevent flooding damage in advance. In this paper, we present a machine-learning scheme for developing a flooding depth and location prediction model using real-time rainfall data. This scheme proposes a dataset configuration method using the data as input, which can robustly configure various rainfall distribution patterns and train the model with less memory. These data are composed of two: valid total data and valid local. The one data that has a significant effect on flooding predicted the flooding location well but tended to have different values for predicting specific rainfall patterns. The other data that means the flood area partially affects flooding refers to valid local data. The valid local data was well learned for the fixed point method, but the flooding location was not accurately indicated for the arbitrary point method. Through this study, it is expected that a lot of damage can be prevented by predicting the depth and location of flooding in a real-time manner.

키워드

과제정보

본 논문은 2022년도 행정안전부 '기후변화대응 AI기반 풍수해위험도 예측기술개발 사업의 지원으로 수행되었음 (No. 2022MOIS61-002)

참고문헌

  1. C. Lee, "Train Location and Control using Spread Spectrum Radio Communications," United States Patent, no. 5420883, May 30, 1995.
  2. B. Kim, O. Kim, H. Kwon, and S. Yoon, "Climate change effect of rainfall frequency analysis using high resolution RCM data," in Proceeding of the 30th Annual Korea Water Resources Association Conference, Gyeongju, Korea, 2008, pp. 224-228.
  3. J. Lee and B. Kim, "Scenario-based real-time flood prediction with logistic regression," Water, vol. 13, no. 9, Apr. 2021, pp. 1191.
  4. J. Hou, N. Zhou, G. Chen, M. Huang, and B. Bai, "Rapid forcasting of urban flood inundation using multiple machine learning models," Natural Hazards, vol. 108, May. 2021, pp. 2335-2356. https://doi.org/10.1007/s11069-021-04782-x
  5. J. Choi and H. Choi. "Prediction of Wind Power Generation using Deep Learning," The Journal of The Korea Institute of Electronic Communication Sciences, vol. 16, no. 2, 2021, pp. 329-338.
  6. G, Bak and Y. Bae. "Groundwater Level Prediction Using ANFIS Algorithm." The Journal of the Korea Institute of Electronic Communication Sciences, vol. 14, no. 6, Dec. 2019, pp. 1235- 1240 https://doi.org/10.13067/JKIECS.2019.14.6.1235
  7. M. Motta, M. de Castro Neto, and P. Sarmento, "A mixed approach for urban flood prediction using machine learning and GIS," Natural International Journal of Disaster Risk Reduction, vol. 56, Apr. 2021, pp. 102154
  8. B. Leo, "Random forests," Machine Learning, vol. 45, 2001, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  9. T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE Transactions on Information Theory, vol. 13, 1967, pp. 21-27. https://doi.org/10.1109/TIT.1967.1053964
  10. A. B. Ranit and P. V. Durge, "Different Techniques of Flood Forecasting and Their Application," in Proc. of 2018 International Conference on Research in Intelligent and Computing in Engineering (RICE), El Salvador, El Salvador, Aug. 2018.
  11. S. Bande and V. V. Shete, "Smart Flood Disaster Prediction System using IoT & Neural Networks," in Proc. of 2017 International Conference On Smart Technologies For Smart Nation (SmartTechCon), Bengaluru, India, 2017.
  12. S. Kurnaz, S. Salahova, R. B. Rustamov, and M. Zeynalova, "River Inundation Impact Reduction Based on Space Technology Application," in Proc. of 2009 4th International Conference on Recent Advances in Space Technologies, Istanbul, Turkey, June 2009.
  13. S. Park, "Adaptive Sea Level Prediction Method Using Mearured Data," J. of the Korea Institute of Electronic Communication Sciences, vol. 12, no. 5, 2017, pp. 891-898.
  14. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderpals, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchensay, "Scikit-learn: Machine learning in Python," the Journal of Machine Learning Research, vol. 12, 2011, pp.2825-2830.