자원환경지질 (Economic and Environmental Geology)

  • 제56권1호
  • /
  • Pages.65-73
  • /
  • 2023
  • /
  • 1225-7281(pISSN)
  • /
  • 2288-7962(eISSN)
대한자원환경지질학회 (The Korean Society of Economic and Environmental Geology)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning for Flood Prediction in Indonesia: Providing Online Access for Disaster Management Control

  • Reta L. Puspasari (School of Earth Sciences and Environmental Engineering, Gwangju Institute of Science and Technology (GIST)) ;
  • Daeung Yoon (Department of Energy and Resources Engineering Chonnam National University) ;
  • Hyun Kim (Division of Environmental Health Sciences, School of Public Health, University of Minnesota) ;
  • Kyoung-Woong Kim (School of Earth Sciences and Environmental Engineering, Gwangju Institute of Science and Technology (GIST))
  • 투고 : 2023.02.06
  • 심사 : 2023.02.23
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.

키워드

과제정보

We would like to acknowledge BMKG, BPS, BNPB for publicly available climate, catchment characteristics and flood data. Moreover, we would like to acknowledge the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2021R1A2C1094272) and GIST Research Institute (GRI) grant funded by the GIST in 2022.

참고문헌

  1. Arnell, N.W. and Gosling, S.N. (2016) The impacts of climate change on river flood risk at the global scale. Clim. Change, v.134(3), p.387-401. doi: 10.1007/s10584-014-1084-5
  2. Asadieh, B. and Krakauer, N.Y. (2017) Global change in streamflow extremes under climate change over the 21st century. Hydrol. Earth Syst. Sci., v.21(11), p.5863-5874. doi: 10.5194/hess-21-5863-2017
  3. Bonafilia, D., Tellman, B., Anderson, T. and Issenberg, E. (2020) Sen1Floods11: A georeferenced dataset to train and test deep learning flood algorithms for sentinel-1. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2020-June, p.835-845, doi: 10.1109/CVPRW50498.2020.00113
  4. Breiman, L. (1996) Bagging predictors. Mach Learn, v.24, p.123-140. doi: 10.1007/BF00058655
  5. Chapman, A., Davies, W., Downey, C. and Dookie, D. (2021) ADB Climate Risk Country Profile: Micronesia. Think-Asia
  6. Hirabayashi, Y., Mahendran, R., Koirala, S., Konoshima, L., Yamazaki, D., Watanabe, S., ... and Kanae, S. (2013). Global flood risk under climate change. Nat. Clim. Change, v.3(9), p.816-821. doi: 10.1038/nclimate1911
  7. International Strategy for Disaster Reduction (ISDR) (2006) What's early warning. Accessible at: https://www.unisdr.org/2006/ppew/whats-ew/basics-ew.htm.
  8. Lamovec, P., Veljanovski, T., Mikos, M. and Ostir, K. (2013) Detecting flooded areas with machine learning techniques: case study of the Selska Sora River flash flood in September 2007. J. Appl. Remote Sens., v.7(1), p.073564. doi: 10.1117/1.jrs.7.073564
  9. Leibe B., Matas J., Sebe N. and Welling M. (2015) What is Machine Learning?. Lecture Notes in Computer Science. Springer, Cham., v.9905. doi: 10.1007/978-3-319-46448-0_2
  10. Martinez-Taboada, F. and Redondo, J.I. (2020) Variable importance plot (mean decrease accuracy and mean decrease Gini). PLOS ONE. doi: 10.1371/journal.pone.0230799.g002
  11. Pedregosa, F., Varoquaux, G., Gramfort, A, Michel, V., Thirion, B, Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M. and Duchesnay, E. (2011) Scikit-learn: Machine learning in Python. J. Mach Learn Res., v.12, p.2825-2830.
  12. Sasaki, Y. (2007) The truth of the F-measure. Teach Tutor Mater, v.26.
  13. Strobl, C., Boulesteix, A. L., Kneib, T., Augustin, T. and Zeileis, A. (2008) Conditional variable importance for random forests. BMC Bioinform., v.9, p.1-11. doi:10.1186/1471-2105-9-307
  14. Tabari, H. (2020) Climate change impact on flood and extreme precipitation increases with water availability. Sci. Rep., v.10(1), p.1-10. doi: 10.1038/s41598-020-70816-2
  15. Wagenaar, D., Curran, A., Balbi, M., Bhardwaj, A., Soden, R., Hartato, E., Mestav Sarica, G., Ruangpan, L., Molinario, G. and Lallemant, D. (2020) Invited perspectives: How machine learning will change flood risk and impact assessment. Nat. Hazards Earth Syst. Sci., v.20(4), p.1149-1161. doi: 10.5194/nhess-20-1149-2020
  16. Wang, Z., Lai, C., Chen, X., Yang, B., Zhao, S. and Bai, X. (2015) Flood hazard risk assessment model based on random forest. J. Hydrol., v.527, p.1130-1141. doi: 10.1016/j.jhydrol.2015.06.008
  17. Yu, P.-S., Yang, T.-C., Chen, S.-Y., Kuo, C.-M. and Tseng, H.-W. (2017) Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting. J. Hydrol, v.552, p.92-104, doi: 10.1016/j.jhydrol.2017.06.020