Korean Journal of Agricultural Science (농업과학연구)

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

DOI QR Code

Prediction of pollution loads in agricultural reservoirs using LSTM algorithm: case study of reservoirs in Nonsan City

  • Heesung, Lim (Department of Agricultural and Rural Engineering, Chungnam National University) ;
  • Hyunuk, An (Department of Agricultural and Rural Engineering, Chungnam National University) ;
  • Gyeongsuk, Choi (Department of Agricultural Civil Engineering, Institute of Agricultural Science & Technology, Kyungpook National University) ;
  • Jaenam, Lee (Department of Rural Research Institute, Korea Rural Community Corporation) ;
  • Jongwon, Do (Department of Rural Research Institute, Korea Rural Community Corporation)
  • Received : 2021.11.02
  • Accepted : 2022.03.24
  • Published : 2022.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

The recurrent neural network (RNN) algorithm has been widely used in water-related research areas, such as water level predictions and water quality predictions, due to its excellent time series learning capabilities. However, studies on water quality predictions using RNN algorithms are limited because of the scarcity of water quality data. Therefore, most previous studies related to water quality predictions were based on monthly predictions. In this study, the quality of the water in a reservoir in Nonsan, Chungcheongnam-do Republic of Korea was predicted using the RNN-LSTM algorithm. The study was conducted after constructing data that could then be, linearly interpolated as daily data. In this study, we attempt to predict the water quality on the 7th, 15th, 30th, 45th and 60th days instead of making daily predictions of water quality factors. For daily predictions, linear interpolated daily water quality data and daily weather data (rainfall, average temperature, and average wind speed) were used. The results of predicting water quality concentrations (chemical oxygen demand [COD], dissolved oxygen [DO], suspended solid [SS], total nitrogen [T-N], total phosphorus [TP]) through the LSTM algorithm indicated that the predictive value was high on the 7th and 15th days. In the 30th day predictions, the COD and DO items showed R2 that exceeded 0.6 at all points, whereas the SS, T-N, and T-P items showed differences depending on the factor being assessed. In the 45th day predictions, it was found that the accuracy of all water quality predictions except for the DO item was sharply lowered.

Keywords

Acknowledgement

본 연구는 농림축산식품부의 재원 농림식품기술기획평가원의 농업기반 및 재해대응기술 개발사업(과제번호:321071-3)의 지원으로 수행되었습니다.

References

  1. Chen WB, Liu WC. 2014. Artificial neural network modeling of dissolved oxygen in reservoir. Environmental Monitoring and Assessment 186:1203-1217. https://doi.org/10.1007/s10661-013-3450-6
  2. Chung PJ, Goh HS, Hyun MH, Lee EJ. 2004. Water quality management using WASP5 & WASP builder for a basin of an agricultural reservoir. Journal of Korean Society on Water Environment 20:422-431. [in
  3. Haam JH, Kim DH, Kim HJ, Kim MO. 2012. Development and application of agricultural reservoir water quality simulation model (ARSIM-Rev). Journal of The Korean Society of Agricultural Engineers 54:65-76. [in https://doi.org/10.5389/KSAE.2012.54.6.065
  4. Hochretier S, Schmidhuber J. 1997. LSTM can solve hard long time lag problems. Advances in Neural Information Processing Systems 9:473-479.
  5. Jeong HJ, Lee SJ, Lee HK. 2002. Water quality forecasting of Chungju lake using artificial neural network algorithm. Journal of Environmental Science International 11:201-207. [in https://doi.org/10.5322/JES.2002.11.3.201
  6. Kim JH, Chea SK, Kim BS. 2011. Evaluation of water quality prediction models at intake station by data mining techniques. Korean Society of Environmental Impact Assessment 20:705-716. [in
  7. 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
  8. Kim ME, Shin HS. 2013. Study on establishing algal bloom forecasting models using the artificial neural network. Journal of Korea Water Resources Association 46:697-706. [in https://doi.org/10.3741/JKWRA.2013.46.7.697
  9. Lim HS, An HU, Choi EH, Kim YS. 2020. Prediction of the DO concentration using the machine learning algorithm: Case study in Oncheoncheon, Republic of Korea. Korean Journal of Agricultural Science 47:1029-1037. [in https://doi.org/10.7744/KJOAS.20200086
  10. 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 https://doi.org/10.7744/KJOAS.20180085
  11. Lim MH, Lee YT, Son YG. 2015. Water quality monitoring in small/medium sized reservoirs. Journal of Korean Socienty of Environmental Engineers 37:631-635. [in https://doi.org/10.4491/KSEE.2015.37.11.631
  12. Moriasi DN, Gitau MW, Pai N, Daggupati P. 2015. Hydrologic and water quality models: Performance measures and evaluation criteria. Transactions of the ASABE 58:1763-1785. https://doi.org/10.13031/trans.58.10715
  13. Najah A, Elshafie A, Karin OA, Jaffar O. 2009. Prediction of Johor river water quality parameters using artificial neural networks. European Journal of Scientific Research 28:422-435.
  14. Oh SR, Jin SH, Kim DR, Park SC. 2008. Study on development of artificial neural network forecasting model using runoff, water quality data. Journal of Korea Water Resources Association 41:1035-1044. [in https://doi.org/10.3741/JKWRA.2008.41.10.1035
  15. Oh YP, Park CR, Lee SC, Pyo HM. 2002. A forecasting of water quality in the Youngsan river using neural network. Journal of The Korean Society of Civil Engineers 22B:371-382. [in
  16. Pyo JC, Lee SH, Kim MJ, Cho KH, Cho HJ. 2015. Application of CE-QUAL-W2 model and scenario analysis for predicting water quality constituents in Sayeun reservoir. Journal of Korean Society of Hazard Mitigation 15:275-282. [in Korean]
  17. Yeon IS, Ahn SJ. 2005. A development of real time artificial intelligence warning system linked discharge and water quality (1) application of discharge - water quality forecasting model. Journal of Korea Water Resources Assocition 38:565-574. [in Korean]  https://doi.org/10.3741/JKWRA.2005.38.7.565