A hybrid wavelet de‐noising and Rank‐Set Pair Analysis approach for forecasting hydro‐meteorological time series

Abstract Accurate, fast forecasting of hydro‐meteorological time series is presently a major challenge in drought and flood mitigation. This paper proposes a hybrid approach, wavelet de‐noising (WD) and Rank‐Set Pair Analysis (RSPA), that takes full advantage of a combination of the two approaches to improve forecasts of hydro‐meteorological time series. WD allows decomposition and reconstruction of a time series by the wavelet transform, and hence separation of the noise from the original series. RSPA, a more reliable and efficient version of Set Pair Analysis, is integrated with WD to form the hybrid WD‐RSPA approach. Two types of hydro‐meteorological data sets with different characteristics and different levels of human influences at some representative stations are used to illustrate the WD‐RSPA approach. The approach is also compared to three other generic methods: the conventional Auto Regressive Integrated Moving Average (ARIMA) method, Artificial Neural Networks (ANNs) (BP‐error Back Propagation, MLP‐Multilayer Perceptron and RBF‐Radial Basis Function), and RSPA alone. Nine error metrics are used to evaluate the model performance. Compared to three other generic methods, the results generated by WD‐REPA model presented invariably smaller error measures which means the forecasting capability of the WD‐REPA model is better than other models. The results show that WD‐RSPA is accurate, feasible, and effective. In particular, WD‐RSPA is found to be the best among the various generic methods compared in this paper, even when the extreme events are included within a time series. HighlightsA new hybrid approach is proposed to improve forecasts of hydro‐meteorological time series.Rank‐Set Pair Analysis combined with wavelet de‐noising markedly improves forecasting accuracy.The performance of the proposed approach proves best among its present competitors even when the extreme value occurs.

[1]  Juliang Jin,et al.  A new approach to water resources system assessment — set pair analysis method , 2009 .

[2]  Nicholas A Alexander,et al.  Correcting data from an unknown accelerometer using recursive least squares and wavelet de-noising , 2007 .

[3]  Jan Adamowski,et al.  Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models , 2014 .

[4]  David Labat,et al.  Recent advances in wavelet analyses: Part 1. A review of concepts , 2005 .

[5]  Subimal Ghosh,et al.  Statistical downscaling of GCM simulations to streamflow using relevance vector machine , 2008 .

[6]  Asaad Y. Shamseldin,et al.  Runoff forecasting using hybrid Wavelet Gene Expression Programming (WGEP) approach , 2015 .

[7]  Chien-Ming Chou.  Application of Set Pair Analysis-Based Similarity Forecast Model and Wavelet Denoising for Runoff Forecasting , 2014 .

[8]  Vahid Nourani,et al.  Using self-organizing maps and wavelet transforms for space–time pre-processing of satellite precipitation and runoff data in neural network based rainfall–runoff modeling , 2013 .

[9]  Jan Adamowski,et al.  Drought forecasting using new machine learning methods / Prognozowanie suszy z wykorzystaniem automatycznych samouczących się metod , 2013 .

[10]  Juliang Jin,et al.  Risk Assessment of Regional Water Resources and Forewarning Model at Different Time Scales , 2013 .

[11]  Juan Fu,et al.  Integrated risk assessment method of waterlog disaster in Huaihe River Basin of China , 2014, Natural Hazards.

[12]  Xiaohua Yang,et al.  VULNERABILITY OF ASSESSING WATER RESOURCES BY THE IMPROVED SET PAIR ANALYSIS , 2014 .

[13]  Bin Chen,et al.  Urban ecosystem health assessment based on emergy and set pair analysis—A comparative study of typical Chinese cities , 2009 .

[14]  Lihua Feng,et al.  Statistical Prediction of Changes in Water Resources Trends Based on Set Pair Analysis , 2014, Water Resources Management.

[15]  Jan Adamowski,et al.  Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. , 2010 .

[16]  Dong Wang,et al.  A hybrid wavelet analysis–cloud model data‐extending approach for meteorologic and hydrologic time series , 2015 .

[17]  Yue Liang,et al.  Debris flow hazard assessment using set pair analysis models: Take Beichuan county as an example , 2014, Journal of Mountain Science.

[18]  Zhihong Ding,et al.  Research on the drought index of irrigation district with multi-time scales , 2013, Environmental Monitoring and Assessment.

[19]  Ximing Cai,et al.  Assessing the regional variability of GCM simulations , 2009 .

[20]  Huaizhi Su,et al.  A Method for Evaluating Sea Dike Safety , 2013, Water Resources Management.

[21]  Lachun Wang,et al.  Assessment of water resource security in Chongqing City of China: What has been done and what remains to be done? , 2015, Natural Hazards.

[22]  Inmaculada Pulido-Calvo,et al.  Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds , 2007 .

[23]  Xiaohua Yang,et al.  Set Pair Analysis Based on Phase Space Reconstruction Model and Its Application in Forecasting Extreme Temperature , 2013 .

[24]  Juliang Jin,et al.  Forewarning of sustainable utilization of regional water resources: a model based on BP neural network and set pair analysis , 2012, Natural Hazards.

[25]  D. Baldwin,et al.  Drought, floods and water quality : Drivers of a severe hypoxic blackwater event in a major river system (the southern Murray–Darling Basin, Australia) , 2012 .

[26]  Song Yi,et al.  Application of set pair analysis method on occupational hazard of coal mining , 2017 .

[27]  Dong Wang,et al.  WD-RBF Model and its Application of Hydrologic Time Series Prediction , 2013 .

[28]  Zhi Li,et al.  Progress and prospects of climate change impacts on hydrology in the arid region of northwest China. , 2015, Environmental Research.

[29]  Wang Wensheng,et al.  Hazard degree assessment of landslide using set pair analysis method , 2011, Natural Hazards.

[30]  Soroosh Sorooshian,et al.  A stochastic precipitation disaggregation scheme for GCM applications , 1994 .

[31]  Simon Li,et al.  Uncertainties in real‐time flood forecasting with neural networks , 2007 .

[32]  W. Landman,et al.  Statistical downscaling of GCM simulations to Streamflow , 2001 .

[33]  Shuyou Cao,et al.  How to Select a Reference Basin in the Ungauged Regions , 2013 .

[34]  Chao Zhou,et al.  Comprehensive flood risk assessment based on set pair analysis-variable fuzzy sets model and fuzzy AHP , 2013, Stochastic Environmental Research and Risk Assessment.

[35]  Li aiyun.  Annual Runoff Forecasting Model based on Wavelet De-noising RSPA Method , 2012 .

[36]  Juliang Jin,et al.  Set pair analysis method for coordination evaluation in water resources utilizing conflict , 2017 .

[37]  Ting Wang,et al.  Entropy weight-set pair analysis based on tracer techniques for dam leakage investigation , 2015, Natural Hazards.

[38]  Yuan Zhang,et al.  Multi-scale evaluation of river health in Liao River Basin, China , 2011 .

[39]  Yanpeng Cai,et al.  Risk assessment of water pollution sources based on an integrated k-means clustering and set pair analysis method in the region of Shiyan, China. , 2016, The Science of the total environment.

[40]  Jan Adamowski,et al.  Short-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet transforms and machine learning methods , 2016, Sustainable Water Resources Management.

[41]  Amir AghaKouchak,et al.  A hybrid framework for assessing socioeconomic drought: Linking climate variability, local resilience, and demand , 2015 .

[42]  C. L. Wu,et al.  Rainfall–runoff modeling using artificial neural network coupled with singular spectrum analysis , 2011 .

[43]  Jin Lin,et al.  A comparative research of different ensemble surrogate models based on set pair analysis for the DNAPL-contaminated aquifer remediation strategy optimization. , 2017, Journal of contaminant hydrology.

[44]  Jan Adamowski,et al.  Using discrete wavelet transforms to analyze trends in streamflow and precipitation in Quebec and Ontario (1954–2008) , 2012 .

[45]  A. Bárdossy,et al.  Geostatistical interpolation using copulas , 2008 .

[46]  Shie-Yui Liong,et al.  A systematic approach to noise reduction in chaotic hydrological time series , 1999 .

[47]  V. Singh,et al.  Mid- and long-term runoff predictions by an improved phase-space reconstruction model. , 2016, Environmental research.

[48]  Ruonan Li,et al.  River basin water resource compensation characteristics by set pair analysis: the Dongjiang example , 2014, Frontiers of Earth Science.

[49]  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 .

[50]  Dawei Han,et al.  Automated Thiessen polygon generation , 2006 .

[51]  Alexander Y. Sun,et al.  Monthly streamflow forecasting using Gaussian Process Regression , 2014 .

[52]  L. Ruby Leung,et al.  A long‐term regional simulation and observations of the hydroclimate in China , 2007 .

[53]  Bettina Schaefli,et al.  What drives high flow events in the Swiss Alps? Recent developments in wavelet spectral analysis and their application to hydrology , 2007 .

[54]  J. Adamowski,et al.  Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada , 2012 .

[55]  A. Bárdossy,et al.  SPACE-TIME MODEL FOR DAILY RAINFALL USING ATMOSPHERIC CIRCULATION PATTERNS , 1992 .

[56]  Xianfang Sun,et al.  Despeckling SRTM and other topographic data with a denoising algorithm , 2010 .

[57]  X. Wen,et al.  A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region , 2014 .

[58]  Xi Chen,et al.  Sample entropy‐based adaptive wavelet de‐noising approach for meteorologic and hydrologic time series , 2014 .

[59]  Slobodan P. Simonovic,et al.  Noise reduction in chaotic hydrologic time series: facts and doubts , 2002 .

[60]  K. Andolsek,et al.  Risk assessment , 2003, Nature.

[61]  P. Lipman.  Natural hazards , 1993, Nature.

[62]  Qiang Zhang,et al.  Singular Spectrum Analysis and ARIMA Hybrid Model for Annual Runoff Forecasting , 2011 .

[63]  Song Ning-ning.  Set pair analysis based on stability of the system model under , 2010 .

[64]  Dandan Wang,et al.  Operating mechanism and set pair analysis model of a sustainable water resources system , 2015, Frontiers of Environmental Science & Engineering.

[65]  Todd D. Ringler,et al.  A Hierarchical Evaluation of Regional Climate Simulations , 2013 .

[66]  Xuehui Ren,et al.  Integrated risk assessment of flood disaster based on improved set pair analysis and the variable fuzzy set theory in central Liaoning Province, China , 2014, Natural Hazards.

[67]  Xiaohua Yang,et al.  New Optimal Weight Combination Model for Forecasting Precipitation , 2012 .

[68]  Zhang Yujie.  Annual Runoff Forecasting Model Based on Weighted Rank Set Pair Analysis Method , 2012 .

[69]  M. L. Kavvas,et al.  WEHY-HCM for Modeling Interactive Atmospheric-Hydrologic Processes at Watershed Scale. I: Model Description , 2013 .

[70]  R. Leconte,et al.  Uncertainty of the impact of climate change on the hydrology of a nordic watershed , 2008 .

[71]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[72]  Yuyu Liu,et al.  River ecosystem assessment and application in ecological restorations: A mathematical approach based on evaluating its structure and function , 2015 .