DOI QR코드

DOI QR Code

The Development of a Rainfall Correction Technique based on Machine Learning for Hydrological Applications

수문학적 활용을 위한 머신러닝 기반의 강우보정기술 개발

  • Received : 2018.12.18
  • Accepted : 2019.01.15
  • Published : 2019.01.31

Abstract

For the purposes of enhancing usability of Numerical Weather Prediction (NWP), the quantitative precipitation prediction scheme by machine learning has been proposed. In this study, heavy rainfall was corrected for by utilizing rainfall predictors from LENS and Radar from 2017 to 2018, as well as machine learning tools LightGBM and XGBoost. The results were analyzed using Mean Absolute Error (MAE), Normalized Peak Error (NPE), and Peak Timing Error (PTE) for rainfall corrected through machine learning. Machine learning results (i.e. using LightGBM and XGBoost) showed improvements in the overall correction of rainfall and maximum rainfall compared to LENS. For example, the MAE of case 5 was found to be 24.252 using LENS, 11.564 using LightGBM, and 11.693 using XGBoost, showing excellent error improvement in machine learning results. This rainfall correction technique can provide hydrologically meaningful rainfall information such as predictions of flooding. Future research on the interpretation of various hydrologic processes using machine learning is necessary.

Keywords

References

  1. Hong, W. C., 2008, Rainfall forecasting by technological machine learning models, AMC, 200, 41-57.
  2. Hwang, D. I., Lee, J. H., Seo, D. I., Nah, H. J., Seo, Y. K., 2015, Short-term and 1-hour rain forecast improvement using extrapolation prediction techniques, Proceedings of the Autumn Meeting of Korean Meteorological Society, 260-261.
  3. Kang, B. S., Lee, B. K., 2011, Application of artificial neural network to improve quantitative precipitation forecasts of meso-scale numerical weather prediction, JKWRA, 44(2), 97-107.
  4. Ke, G., Meng, Q., Finely, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T. Y., 2017, LightGBM: A Highly efficient gradient boosting decision tree, 31st conference on neural information processing systems, 3149-3157.
  5. Kim, B. S., Kim, B. K., Kim, H. S., 2008, Flood simulation using the gauge-adjusted radar rainfall and physics-based distributed hydrologic model, hydrol. Process., 22, 4400-4414. https://doi.org/10.1002/hyp.7043
  6. Kim, S. H., Kim, H. M., Kay, J. K., Lee, S. W., 2015, Development and evaluation of the high resolution limited area ensemble prediction system in the korea meteorological administration, atmosphere, 25, 67-83. https://doi.org/10.14191/Atmos.2015.25.1.067
  7. Korea Meteorological Administration, 2017, Meteorological Technology & policy, 10(1).
  8. K-Water, 2016, https://www.water.or.kr/encyclopedia/encyclopedia/encyclopediaview.do?seq=527&p_group_seq=526&menu_mode=4¤tPageNo=1&search_Hangulindex=&search_Engindex=&TERM_SEQNO=4485&HANGULTERM=&ENGTERM=&COMM_CODE=&ATTFILE_SEQNO=&languege=h&searchText=concentrationrainfall.
  9. Met Office, 2017, Flood Guidance Statement User Guide.
  10. Ministry of Public Safety and Security, 2015, Statistical yearbook of natural disaster.
  11. Moore, R. J., Cole, S. J., Dunn, S., Ghimire, S., Golding, B. W., Pierce, C. E., Roberts, N. M., Speight, L., 2015, Surface water flood forecasting for urban communities, Aberdeen, CREW, 32. (CREW Report CRW2012_03, CEH Project no. C04830).
  12. Parmar, A., Mistree, K., Sompura, M., 2017, Machine learning techniques for rainfall prediction: A Review, Conference: 2017 international conference on innovations in information embedded and communication systems.
  13. Sumi, S. M., Zaman, M. F., Hirose, H., 2012, A Rainfall forecasting method using machine laerning models and its application to the Fukuoka city case, Int. J. Appl. Math. Comput. Sci., 22(4), 841-854. https://doi.org/10.2478/v10006-012-0062-1
  14. WMO (World Meteorological Organization), 2011, Manual on flood forecasting and warning, WMO-No.1072, Geneva, Switzerland.