Simulating and predicting of hydrological time series based on TensorFlow deep learning

• Autorzy: Qin J. , Liang J. , Chen T. , Lei X. , Kang A.
• Języki publikacji: EN

Abstrakty

EN

Hydrological time series refers to the observation time point and the observed time value. The simulation and prediction of hydrological time series will greatly improve the predictability of hydrological time series, which is of great significance for hydrological forecasting. TensorFlow, the second generation of artificial intelligence learning system in Google, has been favored by a large number of researchers by virtue of its high flexibility, portability, multi-language support, and performance optimization. However, the application of deep learning in hydrology is less. Based on the TensorFlow framework, the AR model and the LSTM model are constructed in Python language. The hydrological time series is used as the input object, and the model is deeply studied and trained to simulate and predict the hydrological time series. The effect of the model was tested by fitting degrees and other indexes. The fitting degree of the AR model is 0.9551, and the fitting degree of the LSTM model is 0.8012, which shows the feasibility of the model for predicting the hydrological time series, and puts forward the solution for the limitation of the existing analysis results.

• Wydawca: -
• Czasopismo: Polish Journal of Environmental Studies
• Rocznik: 2019
• Tom: 28
• Numer: 2
• Opis fizyczny: p.795-802,fig.,ref.

Twórcy

autor

Qin J.

• Huazhong University of Science and Technology, Wuhan, China

autor

Liang J.

• Huazhong University of Science and Technology, Wuhan, China

autor

Chen T.

• Electric Power Research Institute, Jilin Electric Power Co., Changcun, China

autor

Lei X.

• State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin and China Institute of Water Resources and Hydropower Research, Beijing, China

autor

Kang A.

• State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin and China Institute of Water Resources and Hydropower Research, Beijing, China

Bibliografia

• 1. TERASVIRTA T. Estimation and evaluation of smooth transition autoregressive models. Journal of the American Statistical Association, 89 (425), 208, 1994.
• 2. HAN X., HSIEH C.S., LEE L.F. Estimation and model selection of higher-order spatial autoregressive model: an efficient bayesian approach. Regional Science & Urban Economics, 63, 97, 2017.
• 3. TSIONAS M.G., CHEN Z., WANKE P.A. Structural vector autoregressive model of technical efficiency and delays with an application to chinese airlines. Transportation Research Part A Policy & Practice, 101, 1, 2017.
• 4. HWANG E., DONG W.S. Stationary bootstrapping for structural break tests for a heterogeneous autoregressive model. Communications for Statistical Applications and Methods, 24 (4), 367, 2017.
• 5. RIVEST F., KALASKA J.F., BENGIO Y. Conditioning and time representation in long short-term memory networks. Biological Cybernetics, 108 (1), 23, 2014.
• 6. CAI M., LIU J., CAI M., LIU J., CAI M., LIU J. Maxout neurons for deep convolutional and lstm neural networks in speech recognition. Speech Communication, 77, 53, 2016.
• 7. HANSSON M. On stock return prediction with lstm networks. Asaio Journal, 40 (4), 928, 2017.
• 8. HANSON J., YANG Y., PALIWAL K., ZHOU Y. Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks. Bioinformatics, 33 (5), 685, 2017.
• 9. JIA G., LU Y., LU W., SHI Y., YANG J. Verification method for chinese aviation radiotelephony readbacks based on lstm-rnn. Electronics Letters, 53 (6), 401, 2017.
• 10. SENF C., PFLUGMACHER D., HEURICH M., KRUEGER T. A bayesian hierarchical model for estimating spatial and temporal variation in vegetation phenology from landsat time series. Remote Sensing of Environment, 194, 155, 2017.
• 11. XU M., HAN M. Adaptive elastic echo state network for multivariate time series prediction. IEEE Transactions on Cybernetics, 46 (10), 2173, 2017.
• 12. CHAYAMA M., HIRATA Y. When univariate model-free time series prediction is better than multivariate. Physics Letters A, 380 (31-32), 2359, 2016.
• 13. REICH N.G., LESSLER J., SAKREJDA K., LAUER S.A., IAMSIRITHAWORN S., CUMMINGS D.A.T. Case study in evaluating time series prediction models using the relative mean absolute error. American Statistician, 70 (3), 285, 2016.
• 14. WU X., ZHAN F.B., ZHANG K., DENG Q. Application of a two-step cluster analysis and the apriori algorithm to classify the deformation states of two typical colluvial landslides in the three gorges, china. Environmental Earth Sciences, 75 (2), 146, 2016.
• 15. GHORBANI M.A., ZADEH H.A., ISAZADEH M., TERZI O.A. Comparative study of artificial neural network (mlp, rbf) and support vector machine models for river flow prediction. Environmental Earth Sciences, 75 (6), 1, 2016.
• 16. ZHANG M., XU H., WANG X., ZHOU M., HONG S. Application of Google TensorFlow machine learning framework . Microcomputer and Application, 36 (10), 58, 2017 [In Chinese].
• 17. ABADI M. Tensorflow: learning functions at scale. Acm Sigplan Notices, 1, 1, 2016.
• 18. BAEK Y.T., LEE S.H., KIM J.S. Intelligent missing persons index system implementation based on the opencv image processing and tensorflow deep-running image processing. Journal of the Korea Society of Computer and Information, 22 (1), 15, 2017.
• 19. QUAN D., SON T.C., CHAUDRI J. Classification of asthma severity and medication using tensorflow and multilevel databases. Procedia Computer Science, 113, 344, 2017.
• 20. XIA X.L., XU C., NAN B. Facial expression recognition based on tensorflow platform. ITM Web of Conferences, 12, 01005, 2017.
• 21. BAGNALL A., LINES J., BOSTROM A., LARGE J., KEOGH E. The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining & Knowledge Discovery, 31 (3), 606, 2017.
• 22. XIAO W., HU Y., ZHAO X., CHEN Y., LI R. Time series based urban air quality predication. Big Data & Information Analytics, 1 (2/3), 171, 2017.
• 23. LINDEN A., YARNOLD P.R. Using machine learning to identify structural breaks in single-group interrupted time series designs. Journal of Evaluation in Clinical Practice, 22 (6), 851, 2016.
• 24. HAN H., LINTON O., OKA T., WHANG Y.J. The cross-quantilogram: measuring quantile dependence and testing directional predictability between time series. Journal of Econometrics, 193 (1), 251, 2016.
• 25. GAO Z.K., SMALL M., KURTHS J. Complex network analysis of time series. Epl, 116 (5), 50001, 2016.
• 26. TSAI L.C., MACALALAD E.P., LIU C.H. Taiwan ionospheric model (twim) prediction based on time series autoregressive analysis. Radio Science, 49 (10), 977, 2016.
• 27. LIU X., XIAO H., CHEN R. Convolutional autoregressive models for functional time series. Journal of Econometrics, 194 (2), 263, 2016.
• 28. CHEN C.W.S., LEE S. Generalized poisson autoregressive models for time series of counts. Computational Statistics & Data Analysis, 99, 51, 2016.
• 29. ZHAO Z., CHEN W., WU X., CHEN P.C.Y., LIU J. Lstm network: a deep learning approach for short-term traffic forecast. Iet Intelligent Transport Systems, 11 (2), 68, 2017.
• 30. GAO L., GUO Z., ZHANG H., XU X., SHEN H.T. Video captioning with attention-based lstm and semantic consistency. IEEE Transactions on Multimedia, 19 (9), 2045, 2017.
• 31. CHEN H., CHEN J., HU R., CHEN C., WANG Z. Action recognition with temporal scale-invariant deep learning framework. China communications (English Edition), 14 (2), 163, 2017.
• 32. CAO D., XU S.A Fast&Accurate Image Classifier Based on the Pre-training Models of TensorFlow. Journal of Hanjiang Normal University, 37 (03), 27, 2017 [In Chinese].

Identyfikatory

DOI

10.15244/pjoes/81557