Korean Journal of Agricultural Science (농업과학연구)

Institute of Agricultural Science, CNU (충남대학교 농업과학연구소)
권호 표지
DOI QR코드

DOI QR Code

Prediction of the DO concentration using the machine learning algorithm: case study in Oncheoncheon, Republic of Korea

  • Lim, Heesung (Agricultural and Rural Engineering, Chungnam National University) ;
  • An, Hyunuk (Agricultural and Rural Engineering, Chungnam National University) ;
  • Choi, Eunhyuk (Rural research institute, Korea Rural Community Corporation) ;
  • Kim, Yeonsu (Korea Water Resources Corporation)
  • Received : 2020.10.29
  • Accepted : 2020.11.20
  • Published : 2020.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

Keywords

Acknowledgement

본 연구는 농림축산식품부의 재원 농림식품기술기획평가원의 농업기반 및 재해대응기술 개발사업(과제번호:320004-1)의 지원으로 수행되었습니다.

References

  1. Ahn SJ, Yeon IS, Han YS, Lee JK. 2001. Water quality forecasting at Gongju station in Geum River using neural network model. Journal of Korea Water Resources Association 34:701-711. [in Korean]
  2. Box GEP, Jenkins GM. 1970. Time series analysis, forecasting and control. pp. 109-118. WILEY, San Francisco, USA.
  3. Cho DH, Um HS. 2005. A study on the forecasting of water quality of Nakdong River - focusing on the Gorung measurement point using the monthly tme series data . Korea Environmental Policy and Administration Society 13:5-30. [in Korean]
  4. Han YS, Lee WH, Lee JK, Cho YJ. 2004. Time series analysis using black box model in dissolved. Proceedings of Korean Geo-Environmental Society 1:355-362. [in Korean]
  5. Hochreiter S, Schmidhuber J. 1997. Long short-term memory. Neural Computation 9:1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  6. Huck PM, Farquhar GJ. 1974. Water quality models using the Box-Jenkins method. Journal of the Environmetal Engineering. Division 100:733-751. https://doi.org/10.1061/JEEGAV.0000192
  7. Jeong HJ, Lee SJ, Lee HK. 2002. Water quality forecasting of Chungju Lake using aritificial neural network algorithm. Journal of the Environmental Sciences 11:201-207. [in Korean] https://doi.org/10.5322/JES.2002.11.3.201
  8. Jung SH, Cho HS, Kim JY, Lee GH. 2018. Prediction of water level in a tidal River using a deep-learning based LSTM model. Journal Korea Water Resour 51:1207-2016. [in Korean]
  9. Kim DH, Kim JW, Kwak JW, Kim JS. 2020. Development of water level prediction models using deep neural network in mountain wetlands. Journal of Wetlands Researh 22:106-112. [in Korean]
  10. Kim JO, Yoo HH, Kim OS, Park JS. 1999. Forecasting of water quality in Chinyang Reservoir using ARIMA model. Journal of Wetlands Researh 1:17-28. [in Korean]
  11. K-water. 1996. A study on the prediction of pollutant advection and dispersion and on the reduction countermeasures in a large river: Focusing on the main stream of Nakdong River. K-water, Daejeon, Korea.
  12. Lim HS, An HU, Kim HD, Lee JJ. 2019. Prediction of pollution loads in the Geum River upstream using the recurrent neural network algorithm. Korean Journal of Agricultural Science 46:67-78. [in Korean] https://doi.org/10.7744/KJOAS.20180085
  13. Oh CR, Park SC, Lee HM, Pyo YP. 2002. A forecasting of water quality in the Youngsan River using neural network. Journal of the Korean Society of Civil Engineers B 22:371-382. [in Korean]
  14. Olah C. 2015. Understanding lstm networks. GITHUB blog. Accessed in http://colah.github.io/posts/2015-08-Understanding-LSTMs on 27 August 2015.
  15. Ryu BR, Jun KW. 2004. Forecasting of water quality using neural network at Gabcheon. Journal of Korean Society of Environmental Technology 5:231-240. [in Korean]
  16. Seo YM, Choi EH, Yeo WK. 2017. Reservoir water level forecasting using machine learning models. Journal of the Korean Society of Agricultural Engineers 59:97-110. [in Korean]
  17. Streeter HW, Phelps EB. 1925. A study of the pollution and natural purification of the Ohio River. pp. 1-75. Public Health Service, Washington, D.C., USA.
  18. Tran QK, Song S. 2017. Water level forecasting based on deep learning: A use case of Trinity River-Texas-The United States. Journal of Korean Institute of Information Scientists Engineers 44:607612. [in Korean]
  19. Wetzel. 1984. Liminology 2nd edition. Harcourt Brace Jovanovich Colleage Publishers, San Diego, USA.