Assessment of prediction performances of stochastic models: Monthly groundwater level prediction in Southern Italy

Boulariah O; Mikhailov PA; Longobardi A; Elizariev AN; Aksenov SG

doi:10.19637/j.cnki.2305-7068.2021.02.008

2021 Vol. 9, No. 2

Article Contents

Article navigation > Journal of Groundwater Science and Engineering > 2021 > 9(2): 161-170

Next Article Previous Article

Boulariah O, Mikhailov PA, Longobardi A, Elizariev AN, Aksenov SG. 2021. Assessment of prediction performances of stochastic models: Monthly groundwater level prediction in Southern Italy. Journal of Groundwater Science and Engineering, 9(2): 161-170. doi: 10.19637/j.cnki.2305-7068.2021.02.008

Citation:

Boulariah O, Mikhailov PA, Longobardi A, Elizariev AN, Aksenov SG. 2021. Assessment of prediction performances of stochastic models: Monthly groundwater level prediction in Southern Italy. Journal of Groundwater Science and Engineering, 9(2): 161-170. doi: 10.19637/j.cnki.2305-7068.2021.02.008

Assessment of prediction performances of stochastic models: Monthly groundwater level prediction in Southern Italy

1.
Department of Civil Engineering, University of Salerno, Via Giovanni Paolo II, 123, 84084, Italy
2.
Ufa State Aviation Technical University, 450000, Russian Federation

More Information

Corresponding author: oboulariah@unisa.it

Received Date: 02 November 2020

Accepted Date: 20 April 2021

Publish Date: 15 June 2021

Abstract

Abstract

Stochastic modelling of hydrological time series with insufficient length and data gaps is a serious challenge since these problems significantly affect the reliability of statistical models predicting and forecasting skills. In this paper, we proposed a method for searching the seasonal autoregressive integrated moving average (SARIMA) model parameters to predict the behavior of groundwater time series affected by the issues mentioned. Based on the analysis of statistical indices, 8 stations among 44 available within the Campania region (Italy) have been selected as the highest quality measurements. Different SARIMA models, with different autoregressive, moving average and differentiation orders had been used. By reviewing the criteria used to determine the consistency and goodness-of-fit of the model, it is revealed that the model with specific combination of parameters, SARIMA (0,1,3) (0,1,2) ₁₂, has a high R² value, larger than 92%, for each of the 8 selected stations. The same model has also good performances for what concern the forecasting skills, with an average NSE of about 96%. Therefore, this study has the potential to provide a new horizon for the simulation and reconstruction of groundwater time series within the investigated area.
- Groundwater level forecast /
- Stochastic modelling /
- Southern Italy /
- Seasonality /
- Homogeneity

FullText(HTML)

References

[1]	Adamowski J. 2008. Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis. Journal of Hydrology, 353: 247-266. doi: 10.1016/j.jhydrol.2008.02.013. CrossRef Google Scholar
[2]	Ahn H, Salas J. 1997. Groundwater head sampling based on stochastic analysis. Water Resources Research, 33: 2769-2780. doi: 10.1029/97WR02187. CrossRef Google Scholar
[3]	Balasmeh A, Babbar O, Karmaker T. 2019. Trend analysis and ARIMA modeling for forecasting precipitation pattern in Wadi Shueib catchment area in Jordan. Arabian Journal of Geosciences, 12: 27-27. doi: 10.1007/s12517-018-4205-z. CrossRef Google Scholar
[4]	Boulariah O, Meddi M, Longobardi A. 2019. Assessment of prediction performances of stochastic and conceptual hydrological models: Monthly stream flow prediction in northwestern Algeria. Arabian Journal of Geosciences, 12: 792-792. doi: 10.1007/s12517-019-4847-5. CrossRef Google Scholar
[5]	Chatfield C, Prothero DL. 1973. Box‐Jenkins seasonal forecasting: Problems in a case‐study. Journal of the Royal Statistical Society: Series A (General), 136(3): 295-315. doi: 10.2307/2344994. CrossRef Google Scholar
[6]	Cleophas T, Zwinderman A. 2016. One-Sample Continuous Data (One-Sample T-Test, One-Sample Wilcoxon Signed Rank Test, 10 Patients). SPSS for Starters and 2nd Levelers: 3-6. Google Scholar
[7]	Faruk DÖ. 2010. A hybrid neural network and ARIMA model for water quality time series prediction. Engineering applications of artificial intelligence, 23(4), 586-594. Google Scholar
[8]	Hamilton J. 1994. Time series analysis. Princeton University Press. 1-820. Google Scholar
[9]	Jaiswal R, Lohani A, Tiwari H. 2015. Statistical Analysis for Change Detection and Trend Assessment and Climatological Parameters. Environmental Processes: 729-749. Google Scholar
[10]	Kumar KS, Rathnam EV. 2019. Analysis and prediction of groundwater level trends using four variations of Mann Kendall tests and ARIMA modelling. Journal of the Geological Society of India, 94: 281-289. doi: 10.1007/s12594-019-1308-4. CrossRef Google Scholar
[11]	Longobardi A, Villani P. 2006. Seasonal response function for daily stream flow investigation. Physics and Chemistry of the Earth, 31: 1107-1117. doi: 10.1016/j.pce.2006.02.063. CrossRef Google Scholar
[12]	Longobardi A, Van Loon A. 2018. Base flow index vulnerability to variation in dry spell length for a range of catchment and climate properties. Hydrological Processes, 32: 2496-2509. doi: 10.1002/hyp.13147. CrossRef Google Scholar
[13]	Montgomery DC, Jennings CL, Kulahci M. 2015. Introduction to time series analysis and forecasting. John Wiley & Sons. Google Scholar
[14]	Mirzavand M, Ghazavi R. 2014. A stochastic modelling technique for groundwater level forecasting in an arid environment using time series methods. Water resources management, 29(4): 1315-1328. doi: 10.1007/s11269-014-0875-9. CrossRef Google Scholar
[15]	Mirzavand M, Ghazavi R. 2015. A stochastic modelling technique for groundwater level forecasting in an arid environment using time series methods. Water resources management, 29(4): 1315-1328. Google Scholar
[16]	Mohammadi K, Eslami H, Dayani DS. 2005. Comparison of regression, ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). Journal of Agricultural Science and Technology, 7: 17-30. Google Scholar
[17]	Mombeni H, Rezaei S, Nadarajah S, et al. 2013. Estimation of water demand in Iran based on SARIMA models. Environmental Modeling & Assessment, 18: 559-565. Google Scholar
[18]	Moriasi D, ARnoid G, Kuijk M, et al. 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50: 885-900. doi: 10.13031/2013.23153. CrossRef Google Scholar
[19]	Nash J, Sutcliffe J. 1970. River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10: 282-290. doi: 10.1016/0022-1694(70)90255-6. CrossRef Google Scholar
[20]	Nunno FD, Granata F. 2020. Groundwater level prediction in Apulia region (Southern Italy) using NARX neural network. Environmental Research, 190: 110062. doi: 10.1016/j.envres.2020.110062. CrossRef Google Scholar
[21]	Oikonomou PD, Alzraiee AH, Karavitis CA, et al. 2018. A novel framework for filling data gaps in groundwater level observations. Advances in Water Resources, 119: 111-124. doi: 10.1016/j.advwatres.2018.06.008. CrossRef Google Scholar
[22]	Semiromi M, Koch M. 2019. Reconstruction of groundwater levels to impute missing values using singular and multichannel spectrum analysis: application to the Ardabil Plain, Iran. Hydrological sciences journal, 64: 1711-1726. doi: 10.1080/02626667.2019.1669793. CrossRef Google Scholar
[23]	Singh J, Knapp H, Arnold J, et al. 2005. Hydrologic modeling of the Iroquois River watershed using HSPF and SWAT. J. American Water Resources Assoc, 41(2): 361-375. doi: 10.1111/j.1752-1688.2005.tb03741.x. CrossRef Google Scholar
[24]	Suryanarayana C, Sudheer C, Mahammood V, et al. 2014. An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam, India. Neurocomputing, 145: 324-335. doi: 10.1016/j.neucom.2014.05.026. CrossRef Google Scholar
[25]	Takafuji E, Rocha M, Manzione R. 2019. Groundwater level prediction forecasting and assessment of uncertainty using SGS and ARIMA Models: A case study in the Bauru Aquifer System (Brazil). Natural Resources Research, 28: 487-503. doi: 10.1007/s11053-018-9403-6. CrossRef Google Scholar
[26]	Valipour M, Banihabib M, Behbahani S. 2013. Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. Journal of Hydrology, 476: 433-441. doi: 10.1016/j.jhydrol.2012.11.017. CrossRef Google Scholar
[27]	Valipour M. 2013a. Increasing irrigation efficiency by management strategies: cutback and surge irrigation. ARPN Journal of Agricultural and Biological Science. 8(1):35-43. Google Scholar
[28]	Valipour M. 2013b. Necessity of irrigated and rainfed agriculture in the world. Irrigation & Drainage Systems Engineering. S9, e001. Google Scholar
[29]	Valipour M. 2012. Ability of Box-Jenkins models to estimate of reference potential evapotranspiration (A case study: Mehrabad Synoptic Station, Tehran, Iran). IOSR Journal of Agriculture and Veterinary Science, 1.5: 1-11. Google Scholar
[30]	Willmott C. 1981. On the validation of models. Physical Geography, 2: 184-194. doi: 10.1080/02723646.1981.10642213. CrossRef Google Scholar
[31]	Willmott CJ, Matsuura K. 2005. Advantages of the mean absolute error (MAE) overthe root mean square error (RMSE) in assessingaverage model performance, 30, 79-82. Google Scholar
[32]	Young P. 1999. Nonstationary time series analysis and forecasting. Progress in Environmental Science, 1: 3-48. Google Scholar
[33]	Yang Q, Wang Y, Zhang J, et al. 2017. A comparative study of shallow groundwater level simulation with three time series models in a coastal aquifer of South China. Applied Sciences, 7: 689-698. doi: 10.3390/app7070689. CrossRef Google Scholar