Journal of Wetlands Research (한국습지학회지)

Korean Wetlands Society (한국습지학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Water Level Prediction Models Using Deep Neural Network in Mountain Wetlands

딥러닝을 활용한 산지습지 수위 예측 모형 개발

  • Kim, Donghyun (Department of Civil Engineering, Inha University) ;
  • Kim, Jungwook (Water Quality Assessment Research Division, Water Environment Research Department, National Institute of Environment Research) ;
  • Kwak, Jaewon (Nakdong River Flood Control Office) ;
  • Necesito, Imee V. (Department of Civil Engineering, Inha University) ;
  • Kim, Jongsung (Department of Civil Engineering, Inha University) ;
  • Kim, Hung Soo (Department of Civil Engineering, Inha University)
  • 김동현 (인하대학교 토목공학과) ;
  • 김정욱 (국립환경과학원 물환경연구부 물환경평가연구과) ;
  • 곽재원 (낙동강홍수통제소) ;
  • 아이미 (인하대학교 토목공학과) ;
  • 김종성 (인하대학교 토목공학과) ;
  • 김형수 (인하대학교 사회인프라공학과)
  • Received : 2020.05.06
  • Accepted : 2020.05.18
  • Published : 2020.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Wetlands play an important function and role in hydrological, environmental, and ecological, aspects of the watershed. Water level in wetlands is essential for various analysis such as for the determination of wetland function and its effects on the environment. Since several wetlands are ungauged, research on wetland water level prediction are uncommon. Therefore, this study developed a water level prediction model using multiple regression analysis, principal component regression analysis, artificial neural network, and DNN to predict wetland water level. Geumjeong-Mountain Wetland located in Yangsan-city, Gyeongsangnam-do province was selected as the target area, and the water level measurement data from April 2017 to July 2018 was used as the dependent variable. On the other hand, hydrological and meteorological data were used as independent variables in the study. As a result of evaluating the predictive power, the water level prediction model using DNN was selected as the final model as it showed an RMSE value of 6.359 and an NRMSE value of 18.91%. This research study is believed to be useful especially as a basic data for the development of wetland maintenance and management techniques using the water level of the existing unmeasured points.

습지는 수문, 환경, 생태학적으로 중요한 기능 및 역할을 하며, 특히 습지 내의 수위는 습지의 기능과 환경 등 다양한 분석을 위해 필수적인 자료이다. 그러나 습지는 수위자료를 측정하지 않는 미계측 지역이 많기 때문에, 수위 예측에 대한 연구는 매우 미흡한 실정이다. 따라서 본 연구에서는 습지의 수위를 예측하기 위해 다중회귀분석, 주성분회귀분석, 인공신경망, DNN을 활용하여 수위 예측모형을 개발하였다. 대상지역으로 경상남도 양산시에 위치한 금정산 산지습지를 선정하였고, 2017년 4월부터 2018년 7월까지의 수위 측정자료를 종속변수로 사용하였다. 수문자료와 기상자료를 독립변수로 사용하였다. 예측력 평가결과 최종 모형으로 선정된 DNN을 활용한 수위 예측모형의 예측력 평가결과 RMSE는 6.359, NRMSE는 18.91%로 비교적 산지습지의 수위를 잘 예측하는 것으로 나타났다. 본 연구결과를 활용한다면 기존의 미비하였던 미계측 지점의 수위를 활용한 습지유지 및 관리 기법 개발에 기초자료로 사용할 수 있을 것으로 판단된다.

Keywords

References

  1. Bittmann, E. Grundlagen und Methoden des biologischen Wasserbaus. In Der Biologische Wasserbau an den Bundesstrassen; Bundesanstalt f. Gewaesserkunde: Koblenz, Germany, 1965; pp. 1-56.
  2. Byeon, S.J.; Lee, S.H.; Choi, G.W.; Jung, J.G. Use of Gauged Water Level and Precipitation Data to Predict Short Term Water Level Changes. Korean Rev. Crisis Emerg. Manag. 2014, 10, 247-264.
  3. Castillo, J.M.M.; Cspedes, J.M.S.; Cuchango, H.E.E. Water Level Prediction Using Artificial Neural Network Model. Int. J. Appl. Eng. Res. 2018, 13, 14378-14381.
  4. Chau, K.W. Particle swarm optimization training algorithm for ANNs in stage prediction of shing mun river. J. Hydrol. 2006, 329, 363-367. https://doi.org/10.1016/j.jhydrol.2006.02.025
  5. Jun, H.D.; Lee, J.H. A Methodology for Flood Forecasting and Warning Based on the Characteristic of Observed Water Levels Between Upstream and Downstream. J. Korean Soc. Hazard Mitig. 2013, 13, 367-374.[Korea Literature] https://doi.org/10.9798/KOSHAM.2013.13.6.367
  6. Keddy, P.A. Wetland Ecology: Principles and Conservation; Cambridge University: Cambridge, UK, 2000.
  7. Kim, J.W. Prediction and Evaluation of Hydro-Ecology, Functions, and Sustainability of a Wetland under Climate Change. Ph.D. Thesis, Inha University, Incheon, Korea, 2019.
  8. Kim, J.W.; Lee, B.E.; Kim, J.G.; Oh, S.H.; Jung, J.W.; Lee, M.J.; Kim, H.S. Functional Assessment of Gangcheon Replacement Wetland Using Modified HGM. J. Wetl. Res. 2017, 19, 318-326.[Korea Literature] DOI https://doi.org/10.17663/JWR.2017.19.3.318
  9. Kumar, A.P.S.; Sudheer, K.P.; Jain, S.K.; Agarwal, P.K. Rainfall runoff modeling using artificial neural networks: Comparison of network types. Hydrol. Process. 2005, 19, 1277-1291. https://doi.org/10.1002/hyp.5581
  10. Kwak, J.W.; Kim, G.H.; Kim, J.W.; Singh, V.P.; Kim, H.S. Assessment of hydrological regimes for vegetation on riparian wetlands in Han River Basin, Korea. Terr. Atmos. Ocean. Sci. 2017, 28, 1055-1067.[Korea Literature] doi: 10.3319/TAO.2017.03.25.01
  11. Rezaeianzadeh, M.; Kalin, L.; Anderson, C. Wetland Water-Level Prediction Using ANN in Conjunction with Base-Flow Recession Analysis. J. Hydrol. Eng. 2015, 22, 1-11.
  12. Rezaeianzadeh, M.; Kalin, L.; Hantush, M. An Integrated Approach for Modeling Wetland Water Level: Application to a Headwater Wetland in Coastal Alabama, USA. Water 2018, 10, 1-17. https://doi.org/10.3390/w10070879
  13. Tiwari, M.K.; Chatterjee, C. Development of an accurate and reliable hourly flood forecasting model using wavelet-bootstrap-ANN (WBANN) hybrid approach. J. Hydrol. 2010, 394, 458-470. https://doi.org/10.1016/j.jhydrol.2010.10.001
  14. Yu, P.S.; Chen, S.T.; Chang, I.F. Support vector regression for real-time flood stage forecasting. J. Hydrol. 2006, 328, 704-716. https://doi.org/10.1016/j.jhydrol.2006.01.021