Improving the Estimation of Simulated River Discharge Values Using State Space Structural Models

Document Type : Research Paper

Authors

1 PhD student in Water Resources, Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

2 Associate Professor Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

3 Department of Hydrology and Water Resources, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

4 Department of Statistics, Faculty of Mathematics and Computer Science, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

Abstract

System simulation is done with different structures and by using different approaches and algorithms. Algorithms are intelligent methods of data processing in machine learning that can identify unknown factors in a time-dependent phenomenon. In the analysis of random phenomena, among the methods that can make decision-making easier is the ensemble algorithms. With the help of this method, more accurate data management and more knowledge of the studied system is obtained. Since, investigation of the trend component can be effective in simulating hydrological phenomena and help in interpreting the relationship between hydrological processes and environmental changes in the study areas; State space models have the advantage of analyzing the system flexibly and dynamically. Therefore, this article aims to improve the efficiency of Kalman Filter, ETS, BATS, and TBATS state space time series models with the help of an ensemble method and by comparing with the Box-Jenkins model, to show which of these models has a better capability in simulating the monthly discharge of the river. This comparison has been done in three water measuring stations of Sepiddasht Cesar, TangPanj Bakhtiari and Telezang in Dez catchments located in Khuzestan province since 1386 to 1399. The results of this study, based on the model evaluation criteria (RMSE, MAE and R2), showed that the state space performed better than the Box-Jenkins model (classical), and among the state space models, the local level model (Kalman filter) performed better. So that in the validation stage, RMSE = 39.21and R2 = 0.79 in Sepiddasht Cesar water measuring station, RMSE = 57.89 and R2 = 0.76 in TangPanj Bakhtiari station and RMSE = 113.41 and R2= 0.73 in Telezang station were obtained.

Keywords

References

Wu S.J., Lien H.C., Chang C.H., Shen J.C. (2012). Real-time correction of water stage forecast during rainstorm events using combination of forecast errors. Stochastic Environmental Research and Risk Assessment. 26(4),519 531.
Nayak P.C., Sudheer K.P., Rangan D.M., Ramasastri K.S. (2004). A neurofuzzy computing technique for modeling hydrological time series. Journal of Hydrology, 291,52–66.
El-Shafie, A., Taha, M. R., & Noureldin, A. (2007). A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. Water resources management, 21(3), 533-556. ‏
Ngan, P. (1987). Kalman filter and its application to flow forecasting. ‏
Sun, Y., Bao, W., Valk, K., Brauer, C. C., Sumihar, J., & Weerts, A. H. (2020). Improving forecast skill of lowland hydrological models using ensemble Kalman filter and unscented Kalman filter. Water Resources Research, 56(8), e2020WR027468.
Zeng, Q., Li, D., Huang, G., Xia, J., Wang, X., Zhang, Y., ... & Zhou, H. (2016). Time series analysis of temporal trends in the pertussis incidence in Mainland China from 2005 to 2016. Scientific reports, 6(1), 1-8.‏
De Livera, A. M., Hyndman, R. J., & Snyder, R. D. (2011). Forecasting time series with complex seasonal patterns using exponential smoothing. Journal of the American statistical association, 106(496), 1513-1527. ‏
Lu, M., Lu, S., Liao, W., Lei, X., Yin, Z., & Wang, H. (2022). Research and application of parameter estimation method in hydrological model based on dual ensemble Kalman filter. Hydrology Research, 53(1), 65-84. ‏
Shen, Y., Wang, S., Zhang, B., & Zhu, J. (2022). Development of a stochastic hydrological modeling system for improving ensemble streamflow prediction. Journal of Hydrology, 608, 127683. ‏
Stefenon, S. F., Ribeiro, M. H. D. M., Nied, A., Yow, K. C., Mariani, V. C., dos Santos Coelho, L., & Seman, L. O. (2022). Time series forecasting using ensemble learning methods for emergency prevention in hydroelectric power plants with dam. Electric Power Systems Research, 202, 107584.
Dong, X., Yu, Z., Cao, W., Shi, Y., & Ma, Q. (2020). A survey on ensemble learning. Frontiers of Computer Science, 14(2), 241-258. ‏
Fletcher, R. (2013). Practical methods of optimization. John Wiley & Sons. ‏
Pintelas, P., & Livieris, I. E. (2020). Special issue on ensemble learning and applications. Algorithms, 13(6), 140. ‏‏
Liu, B. (2009). Some research problems in uncertainty theory. Journal of Uncertain systems, 3(1), 3-10. ‏
Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140. ‏
Huang, F., Xie, G., & Xiao, R. (2009, November). Research on ensemble learning. In 2009 International Conference on Artificial Intelligence and Computational Intelligence (Vol. 3, pp. 249-252). IEEE. ‏
Dantas, T. M., & Oliveira, F. L. C. (2018). Improving time series forecasting: An approach combining bootstrap  
aggregation, clusters and exponential smoothing. International Journal of Forecasting, 34(4), 748-761.
Bühlmann, P., & Yu, B. (2002). Analyzing bagging. The annals of Statistics, 30(4), 927-961.
Bühlmann, P. (2012). Bagging, boosting and ensemble methods. In Handbook of computational statistics (pp. 985-1022). Springer, Berlin, Heidelberg.‏  ‏
Box, G. E. P., & Jenkins, G. M. (1970). 1970: Time series analysis, forecasting and control. San Francisco:          Holden-Day.
Makridakis, S., & Hibon, M. (1997). ARMA models and the Box–Jenkins methodology. Journal of forecasting, 16(3), 147-163.‏‏
Shumway, R. H., & Stoffer, D. S. (1982). An approach to time series smoothing and forecasting using the EM 
algorithm. Journal of time series analysis, 3(4), 253-264. ‏
Shumway, R. H. (1988). Applied statistical time series analysis. Prentice Hall Series in Statistics.
Kalman R.E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering Transactions, 82(1), 35-45.
Chan, N. H., & Palma, W. (1998). State space modeling of long-memory processes. The Annals of   Statistics, 26(2), 719-740. ‏
Sharifi, M., Mohammadzadeh Shobegar, A., Radmanesh, F., & Mansouri, B. (2022). Evaluation of structural approaches to state space compared to classical in predicting precipitation time series (Dez catchment). Water and Irrigation Management, 12(1), 1-13. ‏
Durbin, J., & Koopman, S. J. (2012). Time series analysis by state space methods (Vol. 38). OUP Oxford. ‏
Harvey, A. C. (1990). Forecasting, structural time series models and the Kalman filter. ‏
Shamshad, B., Khan, M. Z., & Omar, Z. (2019). Modeling and forecasting weather parameters using ANN-MLP, ARIMA and ETS model: a case study for Lahore, Pakistan. Journal of Applied Statistics, 5, 388.
Jain, G., & Mallick, B. (2017). A study of time series models ARIMA and ETS. Available at SSRN 2898968.
Alakkari, K. M., Mishra, P., Rawat, D., Abotaleb, M., & Ghazi, A. M. (2022). Using ETS State Space Model for forecasting on third wave on COVID19 in India.
Abd Rahman, N., Yusop, Z., Åžen, Z., Taher, S., & Kane, I. L. (2017). Mitigation of time series approach on climate change adaptation on rainfall of Wadi Al-Aqiq, Madinah, Saudi Arabia. Jurnal Teknologi, 79(5).
Hyndman, R., Koehler, A. B., Ord, J. K., & Snyder, R. D. (2008). Forecasting with exponential smoothing: the state space approach. Springer Science & Business Media.
Gos, M., Krzyszczak, J., Baranowski, P., Murat, M., & Malinowska, I. (2020). Combined TBATS and SVM model of minimum and maximum air temperatures applied to wheat yield prediction at different locations in Europe. Agricultural and Forest Meteorology, 281, 107827.
De Livera, A. M. (2010). Automatic forecasting with a modified exponential smoothing state space framework. Monash Econometrics and Business Statistics Working Papers, 10(10), 6.
‏Badr, A., Makarovskikh, T., Mishra, P., Abotaleb, M., Al Khatib, A. M. G., Karakaya, K., ... & Attal, E. (2021). Modelling and forecasting of web traffic using Holt's linear, bats and TBATS models. J. Math. Comput. Sci., 11(4), 3887-3915.
Naim, I., Mahara, T., & Idrisi, A. R. (2018). Effective short-term forecasting for daily time series with complex seasonal patterns. Procedia computer science, 132, 1832-1841.
Zachary, H., Asghar, Z., & Oroza, C. A. (2020). Multi-step Weekly Average Forecasting of Reservoir Storage Volume Using Deep Learning. Earth and Space Science Open Archive ESSOAr.
Huang, K., Zhang, J., & Song, Y. (2022, May). Application of machine learning models based on ANN and GA coupling algorithms in hydrological runoff simulation. In International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022) (Vol. 12256, pp. 373-380). 
Yeh, W.W.-G.; Yoon, Y.S. (1981). Aquifer parameter identification with optimum dimension   
in parameterization. Water Resources Research. 17, 664–672.
Kotsiantis, S. B., Zaharakis, I. D., & Pintelas, P. E. (2006). Machine learning: a review of classification and combining techniques. Artificial Intelligence Review, 26(3), 159-190.
Ribeiro, M. H. D. M., & dos Santos Coelho, L. (2020). Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series. Applied Soft Computing, 86, 105837.
Gastinger, J., Nicolas, S., Stepić, D., Schmidt, M., & Schülke, A. (2021, July). A study on ensemble learning for time series forecasting and the need for meta-learning. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. ‏
Murray, S. A. (2018). The importance of ensemble techniques for operational space weather forecasting. Space Weather, 16(7), 777-783. ‏
Seising, R., & Allende-Cid, H. (Eds.). (2017). Claudio Moraga: A Passion for Multi-Valued Logic and Soft Computing. Springer International Publishing. ‏
Wideroos, K. (2021). Improving time series forecasting accuracy by ensemble methods and time series             features (Master's thesis). ‏
Li, Y., Liang, Z., Hu, Y., Li, B., Xu, B., & Wang, D. (2020). A multi-model integration method for monthly streamflow prediction: modified stacking ensemble strategy. Journal of Hydroinformatics, 22(2), 310-326. ‏
Rajesh, M., & Rehana, S. (2021). Prediction of river water temperature using machine learning algorithms: a tropical river system of India. Journal of Hydroinformatics, 23(3), 605-626. ‏
Wang, W. C., Chau, K. W., Xu, D. M., & Chen, X. Y. (2015). Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition. Water Resources Management, 29(8), 2655-2675. ‏
Ardabili, S., Mosavi, A., & Várkonyi-Kóczy, A. R. (2019, September). Advances in machine learning modeling reviewing hybrid and ensemble methods. In International Conference on Global Research and Education (pp. 215-227). Springer, Cham. ‏
Boukharouba, K., & Kettab, A. (2016). Comparison of prediction performances between Box–Jenkins and Kalman filter models––Case of annual and monthly sreamflows in Algeria. Desalination and Water Treatment, 57(36), 17095-17103.
Ahsan, M., & O'Connor, K. M. (1994). A reappraisal of the Kalman filtering technique, as applied in river flow forecasting. Journal of Hydrology, 161(1-4), 197-226.
Li, Z., Xu, X., Liu, M., Li, X., Zhang, R., Wang, K., & Xu, C. (2017). State-space prediction of spring discharge in a karst catchment in southwest China. Journal of Hydrology, 549, 264-276.
Li, Z., Xu, X., Xu, C., Liu, M., Wang, K., & Yi, R. (2017). Monthly sediment discharge changes and estimates in a typical karst catchment of southwest China. Journal of Hydrology, 555, 95-107.
Adubisi, O. D., David, I. J., Eka, O., & Uduma, A. E. (2019). State space and Box-Jenkins approaches: a comparison of models prediction performance in finance. International Journal of Data Science, 4(3), 181-195.
Husin, W. Z. W., Afdzal, A. S., Azmi, N. L. H., & Hamadi, S. A. T. S. (2021, November). Box-Jenkins and State Space Model in Forecasting Malaysia Road Accident Cases. In Journal of Physics: Conference Series (Vol. 2084, No. 1, p. 012005). IOP Publishing
Iranian Journal of Soil and Water Research
Volume 53, Issue 8
October 2023
Pages 1921-1936

Files

Share

How to cite

Statistics