Journal of The Korean Society of Agricultural Engineers (한국농공학회논문집)

The Korean Society of Agricultural Engineers (한국농공학회)
권호 표지
DOI QR코드

DOI QR Code

Influence of Rainfall observation Network on Daily Dam Inflow using Artificial Neural Networks

강우자료 형태에 따른 인공신경망의 일유입량 예측 정확도 평가

  • Kim, Seokhyeon (Department of Rural Systems Engineering, Seoul national University) ;
  • Kim, Kyeung (Department of Rural Systems Engineering, Seoul national University) ;
  • Hwang, Soonho (Department of Rural Systems Engineering, Seoul national University) ;
  • Park, Jihoon (Climate Services and Research Department, APEC Climate Center) ;
  • Lee, Jaenam (Water Resources & Environment Research Group, Rural Research Institute, Korea Rural Community Corporation) ;
  • Kang, Moonseong (Department of Rural Systems Engineering, Institute of Agriculture and Life sciences, Institute of Green Bio Science and Technology, Seoul national University)
  • Received : 2018.11.29
  • Accepted : 2019.03.07
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

The objective of this study was to evaluate the influence of rainfall observation network on daily dam inflow using artificial neural networks(ANNs). Chungju Dam and Soyangriver Dam were selected for the study watershed. Rainfall and dam inflow data were collected as input data for construction of ANNs models. Five ANNs models, represented by Model 1 (In watershed, point rainfall), Model 2 (All in the Thiessen network, point rainfall), Model 3 (Out of watershed in the Thiessen network, point rainfall), Model 1-T (In watershed, area mean rainfall), Model 2-T (All in the Thiessen network, area mean rainfall), were adopted to evaluate the influence of rainfall observation network. As a result of the study, the models that used all station in the Thiessen network performed better than the models that used station only in the watershed or out of the watershed. The models that used point rainfall data performed better than the models that used area mean rainfall. Model 2 achieved the highest level of performance. The model performance for the ANNs model 2 in Chungju dam resulted in the $R^2$ value of 0.94, NSE of 0.94 $NSE_{ln}$ of 0.88 and PBIAS of -0.04 respectively. The model-2 predictions of Soyangriver Dam with the $R^2$ and NSE values greater than 0.94 were reasonably well agreed with the observations. The results of this study are expected to be used as a reference for rainfall data utilization in forecasting dam inflow using artificial neural networks.

Keywords

NGHHCI_2019_v61n2_63_f0001.png 이미지

Fig. 1 Study area – Soyangriver dam watershed

NGHHCI_2019_v61n2_63_f0002.png 이미지

Fig. 2 Study area – Chungju dam watershed

NGHHCI_2019_v61n2_63_f0003.png 이미지

Fig. 3 Architecture of artificial neuron

NGHHCI_2019_v61n2_63_f0004.png 이미지

Fig. 4 Structure of artificial neural network

NGHHCI_2019_v61n2_63_f0005.png 이미지

Fig. 5 MSE according to time lags (Chungju dam)

NGHHCI_2019_v61n2_63_f0006.png 이미지

Fig. 6 MSE according to time lags (Soyangriver dam)

NGHHCI_2019_v61n2_63_f0007.png 이미지

Fig. 7 Scatter plots comparing observed and simulated Chungju dam inflow by artificial neural network for testing period

NGHHCI_2019_v61n2_63_f0008.png 이미지

Fig. 8 Scatter plots comparing observed and simulated Soyangriver dam inflow by artificial neural network for testing period

NGHHCI_2019_v61n2_63_f0009.png 이미지

Fig. 9 Time series of observed and simulated of Chungju dam inflow according to the meteorological range

NGHHCI_2019_v61n2_63_f0010.png 이미지

Fig. 10 Time series of observed and simulated of Soyangriver dam inflow according to the meteorological range

NGHHCI_2019_v61n2_63_f0011.png 이미지

Fig. 11 Time series of observed and simulated of Chungju dam inflow according to the use of area mean rainfall

NGHHCI_2019_v61n2_63_f0012.png 이미지

Fig. 12 Time series of observed and simulated of Soyangriver dam inflow according to the use of area mean rainfall

Table 1 Thiessen area of Soyangriver dam watershed

NGHHCI_2019_v61n2_63_t0001.png 이미지

Table 2 Thiessen area of Chungju dam watershed

NGHHCI_2019_v61n2_63_t0002.png 이미지

Table 3 Type of Input rainfall in model

NGHHCI_2019_v61n2_63_t0003.png 이미지

Table 4 Time lags and hidden node of each model

NGHHCI_2019_v61n2_63_t0004.png 이미지

Table 5 Training and testing statics for each models

NGHHCI_2019_v61n2_63_t0005.png 이미지

References

  1. Anctil, F., and A. Rat, 2005. Evaluation of neural network streamflow forecasting on 47 watershed. Journal of Hydrologic Engineering 10(1): 85-88. doi:10.1061/(ASCE)1084-0699(2005)10:1(85).
  2. Choi, S. Y., and K. Y. Han, 2011. Comparison and analysis for performance of flood stage prediction regression model according to type of input rainfall. Journal of Korean Society of Hazard Mitigation 11(5): 313-325 (in Korean). https://doi.org/10.9798/KOSHAM.2011.11.5.313
  3. Gupta, H., V. S. Sorooshian, and P. O. Yapo, 1999. Status of automatic calibration for hydrologic models: comparison with multilevel expert calibration. Journal of Hydrologic Engineering 4(2): 135-143. doi:10.1061/(ASCE)1084-0699(1999)4:2(135).
  4. Hwang, J. S., S. Y. Choi, and H. S. Jeon, 2001. A classification analysis using bayesian neural network. Journal of Korean Data & Information Science Society 12(2): 11-25 (in Korean).
  5. Jang, D. W., D. G. Kim, Y. S. Kim, and W. I. Choi, 2018. Application of SWAT model considering spatial distribution of rainfall. Journal of Wetlands Research 20(1): 94-103 (in Korean). doi:10.17663/JWR.2018.20.1.094.
  6. Kang, M. S., M. G. Kang, S. W. Park, J. J. Lee, and K. H. Yoo, 2006. Application of grey model and artificial neural networks to flood forecasting. Journal of the American Water Resources Association 42(2): 473-486. doi:10.111/j.1752-1688.2006.tb03851.x.
  7. Kang, M. S., and S. W. Park, 2001. Forecasting long_term steamflow from a small waterhed using artificial neural network. Journal of the Korean Society of Agricultural Engineers 43(2): 69-77 (in Korean).
  8. Kang, M. S., and S. W. Park, 2003. Short-term flood forecasting using artificial neural networks. Journal of The Korean Society of Agricultural Engineers 45(2): 45-57 (in Korean).
  9. Kim, H. L., K. S. Jun, and M. H. Choi, 2016. Estimation of river discharge using satellite-derived flow signals and artificial neural network model: application to imjin river. Journal of Korea Water Resources Association 49(7): 589-597 (in Korean). doi:10.3741/JKWRA.2016.49.7.589.
  10. Kim, M. E., J. M. Kim, S. J. Ye, J. B. Park, M. Y. Yun, and H. S. Shin, 2015. A study on water quality prediction model over midterm considering correlation between water quality and hydrologic factors. Journal of Korean Society of Hazard Mitigation 15(6): 459-470 (in Korean). doi: 10.9798/KOSHAM.2015.15.6.459.
  11. Kim, S. E., and I. W. Seo, 2015. Artificial neural network ensemble modeling with exploratory factor analysis for streamflow forecasting. Journal of Hydro informatics 17(4): 614-639 doi:10.2166/hydro.2015.033.
  12. Kim, S. E., and I. W. Seo, 2017. A study on improvement of generalization accuracy of artificial neural network modeling using factor analysis and cluster analysis: application to flow and water quality prediction. Water for Future 50(6): 31-40.
  13. Kim, S. H., J. M. So, S. U. Kang, and D. H. Bae, 2017. Development and evaluation of dam inflow prediction method based on bayesian method. Journal of Korea Water Resources Association 50(7): 489-502 (in Korean). doi: 10.3741/JKWRA.2017.50.7.489.
  14. Lee, G. S., S. C. Park, H. M. Lee, and Y. H. Jin, 2000. The prediction of runoff using artificial neural network in the Young-san River. Journal of Korea Water Resources Association 33(1): 251-256 (in Korean).
  15. Lee, J. H., and S. H. Yoon, 2005. Runoff analysis using spatially distributed rainfall data. Journal of Korea Society of Agricultural Engineers 47(6): 3-14 (in Korean). doi:10.5389/KSAE.2005.47.6.003.
  16. Lee, S. H., M. G. Kim, J. Y. Choi, and J. H. Bang, 2019. Estimating reference crop evapotranspiration using artificial neural network and temperature-based climatic data. Journal of the Korean Society of Agricultural Engineers 61(1): 95-105 (in Korean). doi:10.5389/KSAE.2019.61.1.095.
  17. Mahsa, M., and T. S. Lee, 2018. Comparison of optimization algorithms in deep learning-based neural networks for hydrological forecasting: case study of nam river daily runoff. Journal of Korean Society of Hazard Mitigation 18(6): 377-384 (in Korean). doi:10.9798/KOSHAM.2018.18.6.377.
  18. Minns, A. W., and M. J. Hall, 1996 Artificial neural networks as rainfall-runoff models. Hydrological Sciences Journal 41(3): 399-417. doi:10.1080/02626669609491511.
  19. Nash, J. E., and J. V. Sutcliffe, 1970. River flow forecasting through conceptual models part I - A discussion of principles. Journal of Hydrology 10(3): 282-290. doi: 10.1016/0022-1694(70)90255-6.
  20. Park, H. K., and E. K. Kim, 2013. Study on the modelling of algal dynamics in lake paldang using artificial neural networks. Journal of Korean Society on Water Environment 29(1): 19-28 (in Korean).
  21. Park, J. C., N. Kim, and K. S. Ryoo, 2009. Improvement of inflow estimation data by precise measurement of water level in reservoir. Journal of the Environmental Sciences 18(3): 309-314 (in Korean). https://doi.org/10.5322/JES.2009.18.3.309
  22. Park, M. K., Y. S. Yoon, H. H. Lee, and J. H. Kim, 2018. Application of recurrent neural network for inflow prediction into multi-purpose dam basin. Journal of Korea Water Resources Association 51(12): 1217-1227 (in Korean). doi:10.3741/JKWRA.2018.51.12.1217.
  23. Pushpalatha, R., C. Perrin, N. L. Moine, and V. Andreassian, 2012. A review of efficiency criteria suitable for evaluating low-flow simulations. Journal of Hydrology 420-421: 171-182. doi:10.1016/j.jhydrol.2011.11.055.
  24. Ryu, Y. J., J. Y. Shin, W. S. Nam, and J. H. Heo, 2012. Forecast of the daily inflow with artificial neural network using wavelet transform at Chungju dam. Journal of Korea Water Resources Association 45(12): 1321-1330 (in Korean). doi:10.3741/JKWRA.2012.45.12.1321.
  25. Yoon, Y. N., 2007. Hydrology-basic and application. Paju: cheongmoongak.