Forecasting of Water Volume in the Agricultural Area of Phra Nakhon Si Ayutthaya Province by Artificial Neural Network Model
Article Sidebar
Main Article Content
Abstract
The purpose of this study was to develop an artificial neural network system model for flood forecasting in agricultural areas of the water intake zone community in Phra Nakhon Si Ayutthaya. The Thap Nam-Ban Ma community was set as a study site. The collected data were based on the water level and rainfall from the lower Chao Phraya Basin water level measurement station and the Khlong Thap Nam. The data were used to create neural networks for a time series forecasting model to predict water levels at daily, weekly, and monthly intervals. The findings revealed that the efficiency of daily multi-layer artificial neural network forecasting from the lower Chao Phraya Basin water level measurement station was good. The correlation coefficient between the actual measured values and forecast results was within the acceptable range (r = 0.9975 and 0.6843 for training and testing procedures, respectively) and the data could be learned accurately. The root mean square error (RMSE) was the lowest (0.2783 and 0.1394 for the respective training and testing procedures) compared to weekly and monthly forecast results. For Khlong Thap Nam, the daily forecast was effective at a good level. The correlation coefficient between the actual measured values and forecast results was within the acceptable range (r = 0.9975 and 0.6754 for training and testing procedures, respectively) and the data could be learned accurately with the lowest RMSE (0.1841 and 0.1041 for the respective training and testing procedures). Weekly and monthly water level forecast sections produced less accurate forecasts over a longer period with the correlation coefficient of 0.6531–0.9508 and RMSE of 0.4570–0.8639. These results revealed that the artificial neural network model can provide reliable forecast results and can be applied in forecasting to support the actual operation effectively.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Alon, A.S., J.N. Mindoro, C.D. Casuat, M.A.F. Malbog and J.A.B. Susa. 2020. An inference approach of flood level detection and alert system: flood-induced simulated environment. IJATCSE. 9(2): 2259–2264.
Blöschl, G., J. Hall, J. Parajka, R.A.P. Perdigão, B. Merz, B. Arheimer, G.T. Aronica, A. Bilibashi, O. Bonacci, M. Borga, I. Canjevac, A. Castellarin, G.B. Chirico, P. Claps, K. Fiala, N. Frolova, L. Gorbachova, A. Gül, J. Hannaford, S. Harrigan, M. Kireeva, A. Kiss, T.R. Kjeldsen, S. Kohnová, J.J. Koskela, O. Ledvinka, N. Macdonald, M. Mavrova-Guirguinova, L. Mediero, R. Merz, P. Molnar, A. Montanari, C. Murphy, M. Osuch, V. Ovcharuk, I. Radevski, M. Rogger, J.L. Salinas, E. Sauquet, M. Sraj, J. Szolgay, A. Viglione, E. Volpi, D. Wilson, K. Zaimi and N. Zivkovic. 2017. Changing climate shifts timing of European floods. Science. 357(6351): 588–590.
Bomers, A., B. van der Meulen, R.M.J. Schielen and S.J.M.H. Hulscher. 2019. Historic flood reconstruction with the use of an artificial neural network. Water Resour. Res. 55: 9673–9688.
Boontawee, N., N. Saepaisarn, N. Wattanavong, P. Piyakuldumrong, P. Wongrattanakumphon and S. Opasanon. 2021. Improving the performance of windstorm disaster warning dissemination: a case study of Thailand tropical storm Pabuk. Chulalongkorn Business Review. 43(167): 1–21. (in Thai)
Chaipimonplin, T. 2018. Artificial neural network model for water level forecasting at lower Yom catchment with rainfall grid data from climate model. Journal of Social Sciences Srinakharinwirot University. 21: 80–93. (in Thai)
Chaisompran, Y. and T. Chaipimonplin. 2017. Water level forecasting by artificial neural network model with rainfall data from WRF–ECHAM5 model. Srinakharinwirot University (Journal of Science and Technology). 9(17): 83–90. (in Thai)
Daengkanit, A., A. Mankong, O. Prasert and S. Rattanapong. 2017. Mechanisms of rubber situation analysis and urgent information distribution. Journal of Economics Ramkhamhaeng University. 3(2): 1–41. (in Thai)
Department of Disaster Prevention and Mitigation. 2021. Situation report disaster. Available Source: http://portal.disaster.go.th/portal/ext/nirapai/2021093007.pdf, April 12, 2022. (in Thai)
Hollingsworth, A., K. Arpe, M. Tiedtke, M. Capaldo and H. Savijärvi. 1980. The performance of a medium-range forecast model in winter–impact of physical parameterizations. Mon. Weather Rev. 108: 1736–1773.
Hydro Informatics Institute. 2012. Data collection and analysis operations data warehouse system development project for 25 watersheds and flood and drought model. Available Source: https://tiwrm.hii.or.th/web/attachments/25basins/10–chaopraya.pdf, April 12, 2022. (in Thai)
Jetpipattanapong, D. and R. Tanapattanadol. 2010. A comparative impact study of the changing number of outputs in artificial neuron network on Yom River tide forecasting, Phrae province. Journal of Environmental Management. 6(2): 35–53. (in Thai)
Khamkaew, N., N. Kaewthong and P. Ditthakit. 2020. Inflow forecasting of Pa Phayom reservoir using genetic programming. J. Sci. Tech. UBU 22(1): 136–147. (in Thai)
Kongwichianwat, C. 2018. Flood Relief Project in the Lower Chao Phraya River Basin. Available Source: http://www.dsdw2016.dsdw.go.th/doc_pr/ndc_2560-2561/PDF/8365sc/8365.pdf, June 8, 2020. (in Thai)
Kontochimplee, T., K. Pongput and N. Majang. 2018. Forecasting of reservoir inflow using artificial neural networks. In Proc. the 11th THAICID National Symposium, 20 June 2018. (in Thai)
Leknoi, U. 2019. Situation and trend of disasters. Available Source: http://www.cusri.chula.ac.th/wp-content/uploads/2019/09.pdf, April 12, 2022. (in Thai)
Malarvizhi, R. and A.S. Thanamani. 2012. K–nearest neighbor in missing data imputation. IJERD. J. 5(1): 5–7.
Meteorological Department. 2017. Annual Report 2017. Available Source: https://www.tmd.go.th/aboutus/annual_report2560S.pdf, July 24, 2020.
Mongkolngam, K. and K. Choensirichaimongkol. 2015. Application to geographic information system for forecast of flood risk area case study: upper Ping watershed. In Proc. the 8thThai Students Symposium on Geography and Geo-informatics, 25–26 December 2015. (in Thai)
National Strategy Board. 2017. The National Strategy. Available Source: https://www.ldd.go.th/www/files/81731.pdf, June 8, 2020.
Phuphong, S. 2013. Development and Validation of Runoff Forecasting Model for U-Tapao River Basin, Songkhla Province, Thailand. MS Thesis, Prince of Songkla University, Songkla. (in Thai)
Rahim, N.F., M. Othman and R. Sokkalingam. 2018. A comparative review on various method of forecasting crude palm oil prices. J. Phys.: Conf. Ser. 1123: 012043.
Searcy, J.K. and C.H. Hardison. 1960. Double-Mass Curves. United States Government Printing Office, Washington, D.C., USA.
Sola, J. and J. Sevilla. 1997. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans. Nucl. Sci. 44(3): 1464–1468.
Thumbnum Sub District Administration Organization. 2017. Local Development Plan (2018–2022). Available Source: http://tubnum.go.th/public/plan_upload/backend/plan_99_1.pdf, April 13, 2022. (in Thai)
Tsakiri, K., A. Marsellos and S. Kapetanakis. 2018. Artificial neural network and multiple linear regression for flood prediction in Mohawk River, New York. Water. 10(9): 1158.
