The Prediction of Water Temperature at Saemangeum Lake by Neural Network

신경망모형을 이용한 새만금호 수온 예측

  • Oh, Nam Sun (Ocean.Plant Construction Engineering, Mokpo Maritime National University) ;
  • Jeong, Shin Taek (Department of Civil and Environmental Engineering, Wonkwang Univ.)
  • 오남선 (목포해양대학교 해양.플랜트건설공학과) ;
  • 정신택 (원광대학교 토목환경공학과, 원광대학교 부설 공업기술개발연구소)
  • Received : 2015.01.18
  • Accepted : 2015.02.25
  • Published : 2015.02.28


The potential impact of water temperature on sea level and air temperature rise in response to recent global warming has been noticed. To predict the effect of temperature change on river water quality and aquatic environment, it is necessary to understand and predict the change of water temperature. Air-water temperature relationship was analyzed using air temperature data at Buan and water temperature data of Shinsi, Garyeok, Mangyeong and Dongjin. Maximum and minimum water temperature was predicted by neural network and the results show a very high correlation between measured and predicted water temperature.


Supported by : 전북녹색환경지원센터


  1. Agresti, A. and Franklin, C. (2007). Statistics, The Art and Science of Learning from Data, Pearson Education Inc.
  2. An, J.H. and Lee, K.H.(2013), Correlation and Hysteresis Analysis of Air-Water Temperature in Four Rivers: Preliminary study for water temperature prediction, Korea Environmental Policy Bulletin, 12(2), 17-32. (in Korean).
  3. Caissie, D., N. EI-Jabi, and M.G. Satish.(2001). Modelling of maximum daily water temperatures in a small stream using air temperature, Journal of Hydrology, 17, 14-28.
  4. Cho, H.Y., Lee, K.H., Cho, K.J. and Kim, J.S.(2007), Correlation and Hysteresis Analysis between Air and Water Temperatures in the Coastal Zone - Masan Bay, Journal of Korean Society of Coastal and Ocean Engineers, 19(3), 213-221. (in Korean).
  5. Cho, H-Y. and Lee, K-H.(2012), Development of an Air-Water Temperature Relationship Model to Predict Climate-Induced Future Water Temperature in Estuaries, J. of Environmental Engineering, 138(5), 570-577.
  6. Cho, H.Y. and Oh, J., (2012). Outlier detection of the coastal water temperature monitoring data using the approximate and detailed components, J. of the Korean Society for Marine Environmental Engineering, Technical Note, 15(2), 156-162. (in Korean).
  7. Cleveland, W.S., (1979). Robust locally weighted regression and smoothing scatterplots, J. of the American Statistical Association, 74(368), 829-836.
  8. Kim, H.S., Jeon, S.Y., Yoo, C.S. and Yang, I.H. (2012). Principles of statistics for engineers and scientists. Donghwa, 35-40. (in Korean).
  9. Lyons, J., J.S. Stewart and M. Mitro.(2010). Predicted effects of climate warming on the distribution of 50 stream fishes in Wisconsin, U.S.A., Journal of Fish Biologoy, 77, 1867-1898.
  10. Moon, H.Y. (2012), Simulation of Temporal Variation of Surface Water Temperature by Applying Inverse Theory on Mixing Layer, Department of civil & environmental engineering, the graduate school, Seoul national university (in Korean).
  11. Morse, W. L.(1970), Stream Temperature Prediction Model, Water Resour. Res., 6(1), 290-320.
  12. National Fisheries Research and Development Institute(2009), Hypoxia in the coast of Korea (in Korean).
  13. Pedersen, N. L. and K. Sand-Jensen.(2007). 'Temperature in lowland Danish streams: contemporary patterns, empirical models and future scenarios, Hydrological Processes, 21: 348-358.
  14. Rehana, S. and P. P. Mujumdar(2012). Climate change induced risk in water quality control problems, Journal of Hydrology, 444-445, 63-77.
  15. Song, C.C.S., and C. Y. Chien(1977), Stochastic Properties of Daily Temperature in Rivers, J. Env. Eng. Div. ASCE, 103(EE2), 217-231.