Streamflow Data Infilling Techniques Based on Concepts of Groups and Neural Networks

For planning, management, and effective control of water resource systems, a considerable amount of data on numerous hydrologic variables such as rainfall, streamflow, evapotranspiration, temperature, etc. is required. Data sets of various hydrologic variables are at times not only short, but also often have gaps because of missing observations. Such deficiencies in hydrologic time series are attributable, among others, to the malfunctioning of monitoring equipment, the effects of natural phenomena, such as earthquakes, hurricanes, or landslides, and problems with data transmission, storage and retrieval processes. Deficiencies in hydrologic data series vary from 5 to 10 percent in the case of runoff data [Correll et al. (1998)] and up to 25 percent in the case of oceanic storm surges [Zhang et al. (1997)] . Time series methods, among others, do not tolerate missing observations, and thus numerous data infilling techniques have evolved in various scientific disciplines to deal with incomplete data sets.

[1]  U. Panu,et al.  Infilling Missing Monthly Streamflow Data Using a Multivariate Approach , 1994 .

[2]  Kishan G. Mehrotra,et al.  Forecasting the behavior of multivariate time series using neural networks , 1992, Neural Networks.

[3]  Rammohan K. Ragade,et al.  A feature prediction model in synthetic hydrology based on concepts of pattern recognition , 1978 .

[4]  Dennis P. Lettenmaier,et al.  Operational assessment of hydrologic models of long-term persistence , 1977 .

[5]  Jery R. Stedinger,et al.  A generalized maintenance of variance extension procedure for extending correlated series , 1989 .

[6]  Daniel A. Griffith,et al.  Estimating missing values in space-time data series. , 1985 .

[7]  Vladimir U. Smakhtin,et al.  Daily flow time series patching or extension: a spatial interpolation approach based on flow duration curves , 1996 .

[8]  Eduardo Parente Ribeiro,et al.  Neural Networks with Missing Values Attributes , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  S. F. Railsback,et al.  Comparison of regression and time-series methods for synthesizing missing streamflow records , 1989 .

[10]  Leo R Beard,et al.  Statistical Methods in Hydrology , 1962 .

[11]  Geoffrey G. S. Pegram.  Patching rainfall data using regression methods. 3. Grouping, patching and outlier detection , 1997 .

[12]  A. Elshorbagy,et al.  Performance Evaluation of Artificial Neural Networks for Runoff Prediction , 2000 .

[13]  N. Matalas.  Mathematical assessment of synthetic hydrology , 1967 .

[14]  A. Wong,et al.  Pattern Analysis and Synthesis of Time-Dependent Hydrologic Data , 1981 .

[15]  William P. Jones,et al.  Back Propagation , 1987, Principles of Artificial Neural Networks.

[16]  Amit Gupta,et al.  Estimating Missing Values Using Neural Networks , 1996 .

[17]  P. Gyau-Boakye,et al.  Filling gaps in runoff time series in West Africa , 1994 .

[18]  Completing missing groundwater observations by interpolation , 1985 .

[19]  T. E. Unny,et al.  Stochastic synthesis of hydrologic data based on concepts of pattern recognition: II. Application of natural watersheds , 1980 .

[20]  On Estimators Obtained From a Sample Augmented by Multiple Regression , 1974 .

[21]  T. E. Unny,et al.  Stochastic synthesis of hydrologic data based on concepts of pattern recognition: III. Performance evaluation of the methodology , 1980 .

[22]  R. Hirsch,et al.  METHODS OF FITTING A STRAIGHT LINE TO DATA: EXAMPLES IN WATER RESOURCES , 1984 .

[23]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[24]  W. Y. Tang,et al.  Comparative studies of various missing data treatment methods - Malaysian experience , 1996 .

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

[26]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[27]  T. E. Unny,et al.  Stochastic synthesis of hydrologic data based on concepts of pattern recognition: I. General methodology of the approach , 1980 .

[28]  U. S. Panu,et al.  Application of Some Entropic Measures in Hydrologic Data Infilling Procedures , 1992 .

[29]  C. T. Haan,et al.  Statistical Methods In Hydrology , 1977 .

[30]  Robert M. Hirsch,et al.  An evaluation of some record reconstruction techniques , 1979 .

[31]  J. Salas,et al.  Conceptual Basis of Seasonal Streamflow Time Series Models , 1992 .

[32]  Bruce C. Douglas,et al.  East Coast storm surges provide unique climate record , 1997 .

[33]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[34]  T. W. Sammis,et al.  Climate Data Estimation Using Climate Information From Surrounding Climate Stations , 1994 .

[35]  Ross Sparks,et al.  Patching rainfall data using regression methods. 2. Comparisons of accuracy, bias and efficiency , 1997 .

[36]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[37]  E. J. Gilroy.  Reliability of a Variance Estimate Obtained from a Sample Augmented by Multivariate Regression , 1970 .

[38]  G. C. Tiao,et al.  Model Specification in Multivariate Time Series , 1989 .

[39]  K. Cheng,et al.  Generation of Synthetic and Missing Climatic Data for Puerto Rico , 1989 .

[40]  R. Hirsch.  A Comparison of Four Streamflow Record Extension Techniques , 1982 .

[41]  W. C. Lennox,et al.  Groups and neural networks based streamflow data infilling procedures , 2001 .

[42]  George Kuczera,et al.  On maximum likelihood estimators for the multisite lag-one streamflow model: Complete and incomplete data cases , 1987 .

[43]  W. R. Terry,et al.  Time series analysis in acid rain modeling: Evaluation of filling missing values by linear interpolation , 1986 .

[44]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[45]  Hideo Tanaka,et al.  Learning from incomplete training data with missing values and medical application , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[46]  H. Raman,et al.  Multivariate modelling of water resources time series using artificial neural networks , 1995 .

[47]  C. Granger,et al.  Forecasting Economic Time Series. , 1988 .

[48]  Keith D. C. Stoodley,et al.  Time Series Analysis: Theory and Practice I , 1982 .

[49]  J. Stedinger,et al.  Minimum variance streamflow record augmentation procedures , 1985 .

[50]  E. Beale,et al.  Missing Values in Multivariate Analysis , 1975 .

[51]  Roy L. Streit,et al.  Maximum likelihood training of probabilistic neural networks , 1994, IEEE Trans. Neural Networks.

[52]  William M. Alley,et al.  Mixed-station extension of monthly streamflow records. , 1983 .

[53]  Myron B. Fiering,et al.  ON THE USE OF CORRELATION TO AUGMENT DATA , 1962 .

[54]  T. Unny,et al.  Extension and application of feature prediction model for synthesis of hydrologic records , 1980 .

[55]  Nachimuthu Karunanithi,et al.  Neural Networks for River Flow Prediction , 1994 .

[56]  David R. Maidment,et al.  Handbook of Hydrology , 1993 .

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

[58]  J. David Fuller,et al.  Backpropagation in Hydrological Time Series Forecasting , 1994 .

[59]  Ramanathan Gnanadesikan,et al.  Methods for statistical data analysis of multivariate observations , 1977, A Wiley publication in applied statistics.

[60]  Ross Sparks,et al.  Patching rainfall data using regression methods. , 1997 .

[61]  N. Matalas,et al.  A correlation procedure for augmenting hydrologic data , 1964 .

[62]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .