Water Level Forecasting at Bang Sai Arts and Crafts Center (C.29A) Gauge Station, Chao Phraya River Basin, Amphoe Bang Sai, PhraNakhon Si Ayuttaya Province Using NARX Network

Authors

  • Phimphaka Taninpong
  • Thamonwan Manori
  • Watha Minsan

Keywords:

water level prediction, artificial neural network, NARX model, smoothing technique, time series

Abstract

This study aims to predict the water level at the Bang Sai Arts and Crafts Center (C.29A) gauge station located in the Chao Phraya River Basin, Amphoe Bang Sai, PhraNakhon Si Ayuttaya Province using NARX Network. The daily water level data at the C.13, C.3, C.7A, C.35, S.5, S.26, and C.29A gauge stations from Apr 2012 - Dec 2016 were used to develop the water level forecasting model. Data was separated in to three sets: training set, validation set, and testing set. The one-step ahead forecasting model was evaluated using mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results showed that the NARX Network using only the upstream water level gauge stations and gauge station to be predicted obtained the lowest forecasting error. Moreover, the NARX model outperformed Holt-Winters forecasting method.

Author Biographies

Phimphaka Taninpong

Department of Statistics, Faculty of Science, Chiang Mai University

Thamonwan Manori

Department of Statistics, Faculty of Science,Chiang Mai University

Watha Minsan

Department of Statistics, Faculty of Science, Chiang Mai University

References

[1] Thailand Country Report. (document on the Internet) [cited 2017, Apr 1]Available from: http://www.adrc.asia/countryreport/THA/THAeng98/.

[2] Manager Newspaper. (document on the Internet). [updated 20[, Nov 17; cited 2017, Apr 1]. Available from: http://www.manager.co.th/.

[3] 2011 Thailand Flood Execute Summary. (document on Internet) [cited 2017, Apr 1]. Available from: http://www.thaiwater.net/web/index.php/ourworks2554/379-2011flood-summary.html.

[4] Vangpaisal T and Threenat J. Factors Affecting the Accuracy of Water Level Forecasting at M.7 Gauge Station Using Artificial Neural Network Model. Ubon Ratchathani University; 2012.

[5] Chaipimoplin T and Vangpaisal T. Comparison of the Efficiency of Input Determination Techniques with LM and BR Algorithms in ANN for Flood Forecasting, Mun Basin, Thailand. International Journal of Computer and Electrical Engineering. 2014; 6 (2): 90-94.

[6] Main rivers of north eastern part of Thailand. (document on Internet) [cited 2017, Apr 1]. Available from: https://mayures15.files.wordpress.com/2015/06/35.png.

[7] Hydrology Irrigation Center for Central Region – RID. (document on Internet).
[cited 2017, Apr 1]. Available from: http://hydro-5.com/report/wl_week.php.

[8] Júnior JP and Barreto GA. Long-Term Time Series Prediction with the NARX Network: An Empirical Evaluation. Neurocomputing. 2008;71, 3335-3343.

[9] Levenberg K. A Method for the Solution of Certain Non-Linear Problems in Least Squares. Quart Appl Math. 1944; 2: 164–168.

[10] Marquardt D. An Algorithm for Least-Squares Estimation of Nonlinear Parameters. SIAM J Appl Math. 1963; 11 (2): 431–441.

[11] Holt CC. Forecasting trends and seasonals by exponentially weighted averages. O.N.R. Memorandum 52/1957, Carnegie Institute of Technology, 1957. [12] Makridakis S, Wheelwright SC, Hyndma RJ. Forecasting methods and applications. 3rd ed. John Wiley & Sons; 1998.

Downloads

Published

2018-06-30

How to Cite

Taninpong, P., Manori, T., & Minsan, W. (2018). Water Level Forecasting at Bang Sai Arts and Crafts Center (C.29A) Gauge Station, Chao Phraya River Basin, Amphoe Bang Sai, PhraNakhon Si Ayuttaya Province Using NARX Network. Journal of Applied Statistics and Information Technology, 3(1), 32–41. Retrieved from https://ph02.tci-thaijo.org/index.php/asit-journal/article/view/166888