Evaluation of preprocessing techniques for improving the accuracy of stochastic rainfall forecast models

Accurate rainfall forecasting is one of the most important and challenging hydrological modeling tasks with significant benefits for many sectors of the economy. This study presents novel insight into how to improve the accuracy of a new generation of stochastic monthly rainfall forecast models by examining four different preprocessing techniques: (1) time series modeling without preprocessing which is the common method in stochastic modeling as the base case, (2) preprocess using differencing, spectral analysis seasonal and non-seasonal standardization techniques, (3) two-step preprocessing including stationarization and normalization of data using 8 different transformations, and (4) two-step preprocessing, unlike scenario 3, so that the main time series was normalized and transformed to be stationary. Using the autocorrelation function and partial autocorrelation function diagrams, the parameters of the stochastic model are determined. The results indicate that the proposed data preprocessing normalization and transformation techniques can lead to major improvements in the prediction accuracy of the new monthly rainfall forecast model.

[1]  Bahram Gharabaghi,et al.  Novel hybrid linear stochastic with non-linear extreme learning machine methods for forecasting monthly rainfall a tropical climate. , 2018, Journal of environmental management.

[2]  Liu Hongying,et al.  Adjustments based on wavelet transform ARIMA model for network traffic prediction , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[3]  Bahram Gharabaghi,et al.  Reservoir water level forecasting using group method of data handling , 2018, Acta Geophysica.

[4]  Huang Qian,et al.  ARIMA model for traffic flow prediction based on wavelet analysis , 2010, The 2nd International Conference on Information Science and Engineering.

[5]  Hossein Bonakdari,et al.  Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design , 2017, Appl. Math. Comput..

[6]  J. Stedinger,et al.  Multisite ARMA(1,1) and Disaggregation Models for Annual Streamflow Generation , 1985 .

[7]  E. H. Lloyd,et al.  Long-Term Storage: An Experimental Study. , 1966 .

[8]  M. Valipour.  Long‐term runoff study using SARIMA and ARIMA models in the United States , 2015 .

[9]  S. Shapiro,et al.  An Analysis of Variance Test for Normality (Complete Samples) , 1965 .

[10]  Bahram Gharabaghi,et al.  New insights into soil temperature time series modeling: linear or nonlinear? , 2019, Theoretical and Applied Climatology.

[11]  Ruey S. Tsay,et al.  Analysis of Financial Time Series , 2005 .

[12]  Bahram Gharabaghi,et al.  Changes in Rainfall Extremes in Ontario , 2015 .

[13]  Ratnadip Adhikari,et al.  Time Series Forecasting Using Hybrid ARIMA and ANN Models Based on DWT Decomposition , 2015 .

[14]  P. Van Remoortere,et al.  Dynamic stochastic models from empirical data , 1979 .

[15]  Hossein Bonakdari,et al.  Monthly reservoir inflow forecasting using a new hybrid SARIMA genetic programming approach , 2017, Journal of Earth System Science.

[16]  Bryan F. J. Manly,et al.  Exponential Data Transformations , 1976 .

[17]  A. Jalalkamali,et al.  Application of several artificial intelligence models and ARIMAX model for forecasting drought using the Standardized Precipitation Index , 2015, International Journal of Environmental Science and Technology.

[18]  D. Dickey,et al.  Testing for unit roots in autoregressive-moving average models of unknown order , 1984 .

[19]  Richard A. Johnson,et al.  A new family of power transformations to improve normality or symmetry , 2000 .

[20]  S. Kullback,et al.  Information Theory and Statistics , 1959 .

[21]  George P. Petropoulos,et al.  Forecasting Arabian Sea level rise using exponential smoothing state space models and ARIMA from TOPEX and Jason satellite radar altimeter data , 2016 .

[22]  Bahram Gharabaghi,et al.  A reliable linear method for modeling lake level fluctuations , 2019, Journal of Hydrology.

[23]  R. Tsay.  Analysis of Financial Time Series: Tsay/Financial Time Series 3E , 2010 .

[24]  M. Valipour,et al.  Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir , 2013 .

[25]  Ali Osman Pektas,et al.  ANN hybrid model versus ARIMA and ARIMAX models of runoff coefficient , 2013 .

[26]  J. Salas,et al.  Forecasting of short-term rainfall using ARMA models , 1993 .

[27]  Zaher Mundher Yaseen,et al.  Rainfall Pattern Forecasting Using Novel Hybrid Intelligent Model Based ANFIS-FFA , 2017, Water Resources Management.

[28]  Anil K. Bera,et al.  Efficient tests for normality, homoscedasticity and serial independence of regression residuals , 1980 .

[29]  Bahram Gharabaghi,et al.  Remote Sensing Satellite Data Preparation for Simulating and Forecasting River Discharge , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[30]  James Nga-Kwok Liu,et al.  iJADE WeatherMAN: a weather forecasting system using intelligent multiagent-based fuzzy neuro network , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[31]  Muhammad Khusairi Osman,et al.  Weather Forecasting Using Photovoltaic System and Neural Network , 2010, 2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks.

[32]  P. Phillips,et al.  Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? , 1992 .

[33]  Amir Hossein Zaji,et al.  Assessment of Stochastic Models and a Hybrid Artificial Neural Network-Genetic Algorithm Method in Forecasting Monthly Reservoir Inflow , 2017 .

[34]  R. Hirsch,et al.  A Nonparametric Trend Test for Seasonal Data With Serial Dependence , 1984 .

[35]  Jha,et al.  Time-series analysis of monthly rainfall data for the Mahanadi River Basin, India , 2013 .

[36]  Ani Shabri,et al.  Hybrid Empirical Mode Decomposition-ARIMA for Forecasting Price of Rice , 2014 .

[37]  Bahram Gharabaghi,et al.  Trends in rainfall intensity for stormwater designs in Ontario , 2011 .

[38]  P. K. Mishra,et al.  Performance of optimum neural network in rainfall–runoff modeling over a river basin , 2018, International Journal of Environmental Science and Technology.

[39]  Idika E. Okorie,et al.  SARIMA Modelling of the Frequency of Monthly Rainfall in Umuahia, Abia State of Nigeria , 2015 .

[40]  Haiyan Lu,et al.  A new hybrid model optimized by an intelligent optimization algorithm for wind speed forecasting , 2014 .

[41]  Zhou Shi,et al.  Identifying scale-specific controls of soil organic matter distribution in mountain areas using anisotropy analysis and discrete wavelet transform , 2018 .

[42]  Ernest Bladé i Castellet,et al.  Modelación numérica de flujo mixto en conductos cerrados con esquemas en volúmenes finitos , 2017 .

[43]  Graham W. Taylor,et al.  Forecasting air quality time series using deep learning , 2018, Journal of the Air & Waste Management Association.

[44]  M. F. Fuller,et al.  Practical Nonparametric Statistics; Nonparametric Statistical Inference , 1973 .

[45]  M. Valipour,et al.  Parameters Estimate of Autoregressive Moving Average and Autoregressive Integrated Moving Average Models and Compare Their Ability for Inflow Forecasting , 2012 .

[46]  W. L. Lane,et al.  Applied Modeling of Hydrologic Time Series , 1997 .

[47]  G. Box,et al.  On a measure of lack of fit in time series models , 1978 .

[48]  H. Lilliefors.  On the Kolmogorov-Smirnov Test for Normality with Mean and Variance Unknown , 1967 .

[49]  J. ...,et al.  Applied modeling of hydrologic time series , 1980 .

[50]  T. W. Anderson,et al.  Asymptotic Theory of Certain "Goodness of Fit" Criteria Based on Stochastic Processes , 1952 .

[51]  I.I.A. Rahman,et al.  Rainfall forecasting using an artificial neural network model to prevent flash floods , 2011, 8th International Conference on High-capacity Optical Networks and Emerging Technologies.

[52]  H. B. Mann,et al.  On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other , 1947 .

[53]  Kung-Sik Chan,et al.  Time series analysi , 2013 .

[54]  N. Draper,et al.  An Alternative Family of Transformations , 1980 .

[55]  Liu Xiuqin,et al.  Energy Consumption Forecasting Using Seasonal ARIMA with Artificial Neural Networks Models , 2016 .

[56]  M. R. Mansouri Daneshvar,et al.  Spatial contribution of one-day precipitations variability to rainy days and rainfall amounts in Iran , 2014, International Journal of Environmental Science and Technology.

[57]  N. L. Johnson,et al.  Systems of frequency curves generated by methods of translation. , 1949, Biometrika.

[58]  Andrés Torres,et al.  Arima as a forecasting tool for water quality time series measured with UV-Vis spectrometers in a constructed wetland , 2017 .

[59]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[60]  Seyed Reza Hejazi,et al.  A new hybrid for improvement of auto-regressive integrated moving average models applying particle swarm optimization , 2012, Expert Syst. Appl..

[61]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[62]  Ahmad Asnaashari,et al.  Reservoir management under predictable climate variability and change , 2015 .

[63]  V. Yevjevich,et al.  Stochastic hydrology and its use in water resources systems simulation and optimization , 1993 .

[64]  Hossein Bonakdari,et al.  Stochastic model stationarization by eliminating the periodic term and its effect on time series prediction , 2017 .

[65]  W. J. Conover,et al.  Practical Nonparametric Statistics , 1972 .

[66]  Hossein Bonakdari,et al.  Design criteria for sediment transport in sewers based on self-cleansing concept , 2014 .

[67]  Keith W. Hipel,et al.  Advances in Box‐Jenkins modeling: 2. Applications , 1977 .

[68]  Hossein Bonakdari,et al.  Forecasting monthly inflow with extreme seasonal variation using the hybrid SARIMA-ANN model , 2017, Stochastic Environmental Research and Risk Assessment.

[69]  Terence C. Mills.  Time series modelling of temperatures: an example from Kefalonia , 2014 .