Evaluation of random forest and hybrid time series models in bivariate simulation of electrical conductivity

Document Type : Research Paper

Author

Department of Water and Environmantal Engineering, Faculty of Civil Engineering, Shahrood Univerisity of Technology, Shahrood, Iran.

Abstract

The quality parameters of the river, including electrical conductivity, are highly dependent on changes in flow rate. Adding the flow rate parameter to the simulation of this parameter can increase the certainty of the simulation results. For this reason, in this study, random forest, CARMA and CARMA-GARCH models were used to model the electrical conductivity values in Gerdyaghoub, Kutar and Bitas stations in Mahabadchai basin, taking into account the flow rates. In this regard, the monthly values of electrical conductivity and flow discharge in the statistical period 1986-2018 were used. The results were analyzed using Nash-Sutcliffe statistics, root mean square error and violin plot. The results of evaluation the root mean square error and Nash-Sutcliffe statistics showed that the simulation results of CARMA-GARCH model compared to CARMA model in Bitas and Kuter stations as well as the training step in Gerdyaghoub station were improved. The results showed that the combination of nonlinear and linear models could improve the modeling error in three stations, Gerdyaghoub, Kotar and Bitas in the training step of 9.56, 9.70 and 21.68 percent. By examining the violin plots, the results showed acceptable accuracy and performance of CARMA and CARMA-GARCH models compared to the random forest model. In general, the results showed that time series models have higher accuracy in bivariate simulating of electrical conductivity values in the study area.

Keywords

Main Subjects

References

  1. Abbaszadeh Afshar, M., Behmanesh, J., Khalili, K., & Nazeri Tahroudi, M. (2017). Evaluation of the Combined AR-ARCH and GAR-ARCH Models in Modeling Rivers Flow Rate (Case Study: Zarineh River in West Azerbaijan). Journal of Water and Soil Conservation, 23(6), 181-197. (In Persian).
  2. Ahmadianfar, I., Jamei, M., & Chu, X. (2020). A novel hybrid wavelet-locally weighted linear regression (W-LWLR) model for electrical conductivity (EC) prediction in surface water. Journal of Contaminant Hydrology, 232, 103641.
  3. Ahmadianfar, I., Shirvani-Hosseini, S., He, J., Samadi-Koucheksaraee, A., & Yaseen, Z. M. (2022). An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction. Scientific Reports, 12(1), 1-34.
  4. Bollerslev,, Chou, R. Y., & Kroner, K. F. (1992). ARCH modeling in finance. A selective review of the theory and empirical evidence. Journal of Econometrics, 52, 5-59.
  5. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32.
  6. Duan, J. C. (1996). A unified theory of option pricing under stochastic volatility-from GARCH to diffusion. Hong Kong University of Science and Technology.
  7. Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the Econometric Society, 987-1007.
  8. Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning. New York: Springer series in statistics.
  9. Hintze, J. L., & Nelson, R. D. (1998). Violin plots: a box plot-density trace synergism. The American Statistician, 52(2), 181-184.
  10. Jafarzadeh, A., Pourreza-Bilondi, M., Khashei Siuki, A., & Ramezani Moghadam, J. (2021). Examination of various feature selection approaches for daily precipitation downscaling in different climates. Water Resources Management, 35(2), 407-427.
  11. Khashei-Siuki, A., Shahidi, A., Ramezani, Y., Nazeri Tahrudi, M. (2020). Forecasting the groundwater monitoring network using hybrid time series models (Case study:Nalochay). Journal of Water and Soil Conservation, 27(3), 85-103. (In Persian).
  12. Laux, P., Vogl, S., Qiu, W., Knoche, H. R., & Kunstmann, H. (2011). Copula-based statistical refinement of precipitation in RCM simulations over complex terrain. Journal of Hydrology and Earth System Sciences, 15(4), 2401-2419.
  13. Moffat, I. U., Akpan, E. A., & Abasiekwere, U. A. (2017). A time series evaluation of the asymmetric nature of heteroscedasticity: an EGARCH approach. International Journal of Statistics and Applied Mathematics, 2(6), 111-117.
  14. Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I-A discussion of principles. Journal of Hydrology, 10(3), 282-290.
  15. Nazeri Tahroudi, M., & Khalili, K. (2015). Comparing Combined Arma-Parch and Arma-Arch Models for Modeling Peak Flow Discharge (Case Study: Siminehrood River in The West Azarbaijan Province). Water and Soil Science (Agricultural Science), 25(4/1), 113-127. (In Persian).
  16. Nazeri Tahroudi, M., Ramezani, Y., De Michele, C., & Mirabbasi, R. (2021). Flood routing via a copula-based approach. Hydrology Research, 52(6), 1294-1308.
  17. Nelson, D. B. (1991). Conditional heteroskedasticity in asset returns: A new approach. Econometrica: Journal of the Econometric Society, 347-370.
  18. Ramezani, Y., Nazeri Tahroudi, M., & Ahmadi, F. (2019). Analyzing the droughts in Iran and its eastern neighboring countries using copula functions. Journal of the Hungarian Meteorological Service, 123(4), 435-453.
  19. Ravansalar, M., & Rajaee, T. (2015). Evaluation of wavelet performance via an ANN-based electrical conductivity prediction model. Environmental Monitoring and Assessment,187(6),1-16.
  20. Salami, E. S., & Ehteshami, M. (2015). Simulation, evaluation and prediction modeling of river water quality properties (case study: Ireland Rivers). International Journal of Environmental Science and Technology, 12(10), 3235-3242.
  21. Salas, J. D., Delleur, J. W., Yevjevich, V., & Lane, W. L. (1980). Applied Modeling of Hydrologic Time Series. Water Resource Publications, P.O.Box 2841. Littleton, Colorado.80161, U.S.A. 484 P.
  22. Sayadi Shahraki, A., & Sayadi Shahraki, F. (2019). Simulation of Electrical Conductivity of Behbahan Plain Using ANN and ANN-PSO Models. Journal of Water and Wastewater Science and Engineering, 4(1), 34-41. (In Persian).
  23. Shahidi, A., Ramezani, Y., Nazeri-Tahroudi, M., & Mohammadi, S. (2020). Application of vector autoregressive models to estimate pan evaporation values at the Salt Lake Basin, Iran. Journal of the Hungarian Meteorological Service, 124(4), 463-482.
  24. Thakur, A. K., Singh, V. P., & Ojha, C. S. P. (2012). Evaluation of a probabilistic approach to simulation of alkalinity and electrical conductivity at a river bank filtration site. Hydrological Processes, 26(22), 3362-3368.
  25. Tse, Y. K., & Tsui, A. K. C. (2002). A multivariate generalized autoregressive conditional heteroscedasticity model with time-varying correlations. Journal of Business & Economic Statistics, 20(3), 351-362.
  26. Wang, W., Van Gelder, P. H. A. J. M., Vrijling, J. K., & Ma, J. (2005). Testing and modeling autoregressive conditional heteroskedasticity of streamflow processes. Nonlinear processes in Geophysics, 12(1), 55-66.
  27. Yusof, F., & Kane, I. L. (2013). Volatility modeling of rainfall time series. Theoretical and Applied Climatology, 113(1-2), 247-258.
Water and Irrigation Management
Volume 12, Issue 4
January 2023
Pages 729-745

Files

Share

How to cite

Statistics