Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River

The most important motivation for streamflow forecasts is flood prediction and longtime continuous prediction in hydrological research. As for many traditional statistical models, forecasting flood peak discharge is nearly impossible. They can only get acceptable results in normal year. On the other hand, the numerical methods including physics mechanisms and rainfall-atmospherics could provide a better performance when floods coming, but the minima prediction period of them is about one month ahead, which is too short to be used in hydrological application. In this study, a deep neural network was employed to predict the streamflow of the Hankou Hydrological Station on the Yangtze River. This method combined the Empirical Mode Decomposition (EMD) algorithm and Encoder Decoder Long Short-Term Memory (En-De-LSTM) architecture. Owing to the hydrological series prediction problem usually contains several different frequency components, which will affect the precision of the longtime prediction. The EMD technique could read and decomposes the original data into several different frequency components. It will help the model to make longtime predictions more efficiently. The LSTM based En-De-LSTM neural network could make the forecasting closer to the observed in peak flow value through reading, training, remembering the valuable information and forgetting the useless data. Monthly streamflow data (from January 1952 to December 2008) from Hankou Hydrological Station on the Yangtze River was selected to train the model, and predictions were made in two years with catastrophic flood events and ten years rolling forecast. Furthermore, the Root Mean Square Error (RMSE), Coefficient of Determination (R2), Willmott’s Index of agreement (WI) and the Legates-McCabe’s Index (LMI) were used to evaluate the goodness-of-fit and performance of this model. The results showed the reliability of this method in catastrophic flood years and longtime continuous rolling forecasting.

[1]  Nadhir Al-Ansari,et al.  Implementation of Univariate Paradigm for Streamflow Simulation Using Hybrid Data-Driven Model: Case Study in Tropical Region , 2019, IEEE Access.

[2]  Long Chen,et al.  Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation , 2017 .

[3]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Mohd Yawar Ali Khan,et al.  Neural network model for discharge and water-level prediction for Ramganga River catchment of Ganga Basin, India , 2016 .

[6]  Navdeep Jaitly,et al.  Towards Better Decoding and Language Model Integration in Sequence to Sequence Models , 2016, INTERSPEECH.

[7]  Md. Jalil Piran,et al.  Survey of computational intelligence as basis to big flood management: challenges, research directions and future work , 2018 .

[8]  Yangyang Li,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using RBFN Based on EEMD Decomposition , 2017 .

[9]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[10]  K. Chau,et al.  Predicting Standardized Streamflow index for hydrological drought using machine learning models , 2020 .

[11]  Zhonggen Wang,et al.  Bayesian-combined wavelet regressive modeling for hydrologic time series forecasting , 2013 .

[12]  M. Ye,et al.  Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas , 2018, Journal of Hydrology.

[13]  Kwok-wing Chau,et al.  Flood Prediction Using Machine Learning Models: Literature Review , 2018, Water.

[14]  Mohammad Ali Ghorbani,et al.  Hourly River Flow Forecasting: Application of Emotional Neural Network Versus Multiple Machine Learning Paradigms , 2020, Water Resources Management.

[15]  Davide Chicco,et al.  Ten quick tips for machine learning in computational biology , 2017, BioData Mining.

[16]  Mohammad Ali Ghorbani,et al.  Evaluation of daily solar radiation flux using soft computing approaches based on different meteorological information: peninsula vs continent , 2018, Theoretical and Applied Climatology.

[17]  Mohammad Zaker Moshfegh.  Analysis and Prediction of River Flow Based on Evolutionary Programming and Artificial Intelligence , 2018 .

[18]  Mohammad Rezaie-Balf,et al.  Daily river flow forecasting using ensemble empirical mode decomposition based heuristic regression models: Application on the perennial rivers in Iran and South Korea , 2019, Journal of Hydrology.

[19]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[20]  Jianzhong Zhou,et al.  Streamflow estimation by support vector machine coupled with different methods of time series decomposition in the upper reaches of Yangtze River, China , 2016, Environmental Earth Sciences.

[21]  Shengzhi Huang,et al.  Monthly streamflow prediction using modified EMD-based support vector machine , 2014 .

[22]  Junzo Watada,et al.  Short-Term Load Forecasting Using Optimized LSTM Networks Based on EMD , 2018, 2018 10th International Conference on Communications, Circuits and Systems (ICCCAS).

[23]  J. Torrie,et al.  Principles and Procedures of Statistics with Special Reference to the Biological Sciences , 1962 .

[24]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[25]  Kwok-Wing Chau,et al.  ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS , 2015, Eng. Appl. Artif. Intell..

[26]  Ahmad Sharafati,et al.  Development of multivariate adaptive regression spline integrated with differential evolution model for streamflow simulation , 2019, Journal of Hydrology.

[27]  Aman Mohammad Kalteh,et al.  Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform , 2013, Comput. Geosci..

[28]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[29]  L. Kalin,et al.  Coupling SWAT and ANN models for enhanced daily streamflow prediction , 2016 .

[30]  C. Willmott,et al.  A refined index of model performance , 2012 .

[31]  Quoc V. Le,et al.  Listen, attend and spell: A neural network for large vocabulary conversational speech recognition , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Deshan Tang,et al.  A combined rotated general regression neural network method for river flow forecasting , 2016 .

[33]  F. Huang,et al.  Flow-Complexity Analysis of the Upper Reaches of the Yangtze River, China , 2011 .

[34]  Lin Qiu,et al.  The Annual Maximum Flood Peak Discharge Forecasting Using Hermite Projection Pursuit Regression with SSO and LS Method , 2016, Water Resources Management.

[35]  Babak Omidvar,et al.  Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic , 2010, Expert Syst. Appl..

[36]  Cort J. Willmott,et al.  On the Evaluation of Model Performance in Physical Geography , 1984 .

[37]  Nadhir Al-Ansari,et al.  Non-Linear Input Variable Selection Approach Integrated With Non-Tuned Data Intelligence Model for Streamflow Pattern Simulation , 2019, IEEE Access.

[38]  W. Collischonn,et al.  Forecasting River Uruguay flow using rainfall forecasts from a regional weather-prediction model , 2005 .

[39]  Ercan Kahya,et al.  Flow forecast by SWAT model and ANN in Pracana basin, Portugal , 2009, Adv. Eng. Softw..

[40]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[41]  N. Huang,et al.  A new view of nonlinear water waves: the Hilbert spectrum , 1999 .

[42]  Lukás Burget,et al.  Extensions of recurrent neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[43]  Jun Guo,et al.  Monthly streamflow forecasting based on improved support vector machine model , 2011, Expert Syst. Appl..

[44]  Shou-yu Chen,et al.  Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD , 2013 .

[45]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[46]  Nadhir Al-Ansari,et al.  Deep Learning Data-Intelligence Model Based on Adjusted Forecasting Window Scale: Application in Daily Streamflow Simulation , 2020, IEEE Access.

[47]  Shengzhi Huang,et al.  A robust method for non-stationary streamflow prediction based on improved EMD-SVM model , 2019, Journal of Hydrology.

[48]  Zaher Mundher Yaseen,et al.  An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction , 2019, Journal of Hydrology.

[49]  P. Gelder,et al.  Linking Three Gorges Dam and downstream hydrological regimes along the Yangtze River, China , 2015 .

[50]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[51]  S. Thomas Ng,et al.  A Modified Neural Network for Improving River Flow Prediction/Un Réseau de Neurones Modifié pour Améliorer la Prévision de L'Écoulement Fluvial , 2005 .

[52]  Richard Socher,et al.  Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).