Hybrid Multivariate Machine Learning Models for Streamflow Forecasting: A Two-Stage Decomposition–Reconstruction Framework
Publication: Journal of Hydrologic Engineering
Volume 29, Issue 5
Abstract
Robust and accurate streamflow forecasting holds significant importance for flood mitigation, drought warning and water resource management. On account of the intricate nonlinear and nonstationary nature of streamflow time series, numerous decomposition-based approaches have been proposed and integrated with other architectures. However, directly decomposing the entire streamflow data set introduces future information into the decomposition and reconstruction processes, while decomposing calibration and validation sets independently can result in undesired boundary effects. Besides, the signal decomposition techniques tend to generate a large number of decomposed modes. Using all these modes directly as input variables results in intricate forecasting models and is prone to overfitting. To address these challenges, we developed a novel two-stage decomposition reconstruction forecasting (TSDRF) framework by coupling sequentially decomposition technique, sample entropy and multivariate machine learning methods in this study. This newly proposed TSDRF framework is assessed at three hydrologic stations from Yellow River, China. Furthermore, the TSDRF framework is also compared with the two-stage decomposition reconstruction hindcasting (TSDRH) framework under different lead times. The findings suggest that TSDRF framework based on variation mode decomposition (VMD) algorithm outperform other models in terms of mitigating boundary effects, minimizing computational costs, and enhancing generalization capabilities across various lead times.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The streamflow records are collected from the Yellow River Water Conservancy Commission, Ministry of Water Resources of China (http://www.yrcc.gov.cn/). The EEMD, VMD, and DWT methods were performed based on the MATLAB R2022b software. The SVR, DNN, LSTM, and Bayesian optimization algorithms were built using Python 3.11 software. The remaining data are available from the corresponding author upon request.
Acknowledgments
This research was partially supported by Programs of National Natural Science Foundation of China (No. 41972250 and No. 42222704); the Natural Science Foundation of Hubei Province (No. 2021CFA089). We thank the associate editor and three anonymous reviewers for their critical and constructive comments, which help us improve the quality of the manuscript.
Author contributions: Aohan Jin: Methodology, Software, Visualization, Writing–original draft. Quanrong Wang: Conceptualization, Writing–review and editing, Funding acquisition, Project administration. Renjie Zhou: Conceptualization, Validation, Writing–review and editing. Wenguang Shi: Writing–review and editing. Xiangyu Qiao: Writing–review and editing.
References
Adnan, R. M., Z. Liang, S. Trajkovic, M. Zounemat-Kermani, B. Li, and O. Kisi. 2019. “Daily streamflow prediction using optimally pruned extreme learning machine.” J. Hydrol. 577 (Mar): 123981. https://doi.org/10.1016/j.jhydrol.2019.123981.
Ahani, A., M. Shourian, and P. Rahimi Rad. 2018. “Performance assessment of the linear, nonlinear and nonparametric data driven models in river flow forecasting.” Water Resour. Manage. 32 (2): 383–399. https://doi.org/10.1007/s11269-017-1792-5.
Alizadeh, B., A. Ghaderi Bafti, H. Kamangir, Y. Zhang, D. B. Wright, and K. J. Franz. 2021. “A novel attention-based LSTM cell post-processor coupled with Bayesian optimization for streamflow prediction.” J. Hydrol. 601 (Dec): 126526. https://doi.org/10.1016/j.jhydrol.2021.126526.
Apaydin, H., M. T. Sattari, K. Falsafian, and R. Prasad. 2021. “Artificial intelligence modelling integrated with singular spectral analysis and seasonal-trend decomposition using loess approaches for streamflow predictions.” J. Hydrol. 600 (Mar): 126506. https://doi.org/10.1016/j.jhydrol.2021.126506.
Apaydin, H., and M. Sibtain. 2021. “A multivariate streamflow forecasting model by integrating improved complete ensemble empirical mode decomposition with additive noise, sample entropy, Gini index and sequence-to-sequence approaches.” J. Hydrol. 603 (Jun): 126831. https://doi.org/10.1016/j.jhydrol.2021.126831.
Badrzadeh, H., R. Sarukkalige, and A. W. Jayawardena. 2015. “Hourly runoff forecasting for flood risk management: Application of various computational intelligence models.” J. Hydrol. 529 (Oct): 1633–1643. https://doi.org/10.1016/j.jhydrol.2015.07.057.
Cai, X., and M. W. Rosegrant. 2004. “Optional water development strategies for the Yellow River Basin: Balancing agricultural and ecological water demands.” Water Resour. Res. 40 (8). https://doi.org/10.1029/2003WR002488.
Castellano-Méndez, M., W. González-Manteiga, M. Febrero-Bande, J. M. Prada-Sánchez, and R. Lozano-Calderón. 2004. “Modelling of the monthly and daily behaviour of the runoff of the Xallas river using Box–Jenkins and neural networks methods.” J. Hydrol. 296 (1–4): 38–58. https://doi.org/10.1016/j.jhydrol.2004.03.011.
Chang, T. J., J. Delleur, and M. Kavvas. 1987. “Application of discrete autoregressive moving average models for estimation of daily runoff.” J. Hydrol. 91 (1–2): 119–135. https://doi.org/10.1016/0022-1694(87)90132-6.
Cong, Z., D. Yang, B. Gao, H. Yang, and H. Hu. 2009. “Hydrological trend analysis in the Yellow River basin using a distributed hydrological model.” Water Resour. Res. 45 (7). https://doi.org/10.1029/2008WR006852.
Dragomiretskiy, K., and D. Zosso. 2014. “Variational Mode Decomposition.” IEEE Trans. Signal Process. 62 (3): 531–544. https://doi.org/10.1109/TSP.2013.2288675.
Fang, W., S. Huang, K. Ren, Q. Huang, G. Huang, G. Cheng, and K. Li. 2019. “Examining the applicability of different sampling techniques in the development of decomposition-based streamflow forecasting models.” J. Hydrol. 568 (Jun): 534–550. https://doi.org/10.1016/j.jhydrol.2018.11.020.
He, X., J. Luo, G. Zuo, and J. Xie. 2019. “Daily runoff forecasting using a hybrid model based on variational mode decomposition and deep neural networks.” Water Resour. Manage. 33 (Mar): 1571–1590. https://doi.org/10.1007/s11269-019-2183-x.
Huang, S., J. Chang, Q. Huang, and Y. Chen. 2014. “Monthly streamflow prediction using modified EMD-based support vector machine.” J. Hydrol. 511 (May): 764–775. https://doi.org/10.1016/j.jhydrol.2014.01.062.
Huang, Y., L. Yang, S. Liu, and G. Wang. 2019. “Multi-step wind speed forecasting based on ensemble empirical mode decomposition, long short term memory network and error correction strategy.” Energies 12 (10): 1822. https://doi.org/10.3390/en12101822.
Jiang, C., and Y. Shen. 2023. “Watershed models: Review of Approaches, challenges, and opportunities.” ACS ES&T Water 3 (10): 3189–3199. https://doi.org/10.1021/acsestwater.3c00259.
Jiang, S., Y. Zheng, C. Wang, and V. Babovic. 2021. “Uncovering flooding mechanisms across the contiguous United States through interpretive deep learning on representative catchments.” Water Resour. Res. 58 (1): e2021WR030185. https://doi.org/10.1029/2021WR030185.
Jin, A., Q. Wang, H. Zhan, and R. Zhou. 2024. “Comparative performance assessment of physical-based and data-driven machine-learning models for simulating streamflow: A case study in three catchments across the US.” J. Hydrol. Eng. 29 (2): 05024004. https://doi.org/10.1061/JHYEFF.HEENG-6118.
Kim, K.-J., Y.-O. Kim, and T.-H. Kang. 2017. “Application of time-lagged ensemble approach with auto-regressive processors to reduce uncertainties in peak discharge and timing.” J. Hydrol.: Reg. Stud. 9 (Feb): 140–148. https://doi.org/10.1016/j.ejrh.2016.12.081.
Kim, T., T. Yang, S. Gao, L. Zhang, Z. Ding, X. Wen, J. J. Gourley, and Y. Hong. 2021. “Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation? A case study of four watersheds with different hydro-climatic regions across the CONUS.” J. Hydrol. 598 (Mar): 126423. https://doi.org/10.1016/j.jhydrol.2021.126423.
Krishnaswamy, J., N. Kelkar, and C. Birkel. 2018. “Positive and neutral effects of forest cover on dry-season stream flow in Costa Rica identified from Bayesian regression models with informative prior distributions.” Hydrol. Process. 32 (24): 3604–3614. https://doi.org/10.1002/hyp.13288.
Li, W., Q. Shi, M. Sibtain, D. Li, and D. E. Mbanze. 2020. “A hybrid forecasting model for short-term power load based on sample entropy, two-phase decomposition and whale algorithm optimized support vector regression.” IEEE Access 8 (Jun): 166907–166921. https://doi.org/10.1109/ACCESS.2020.3023143.
Liu, Z., P. Zhou, G. Chen, and L. Guo. 2014. “Evaluating a coupled discrete wavelet transform and support vector regression for daily and monthly streamflow forecasting.” J. Hydrol. 519 (Jun): 2822–2831. https://doi.org/10.1016/j.jhydrol.2014.06.050.
Lu, D., M. Ye, M. C. Hill, E. P. Poeter, and G. P. Curtis. 2014. “A computer program for uncertainty analysis integrating regression and Bayesian methods.” Environ. Modell. Software 60 (Jun): 45–56. https://doi.org/10.1016/j.envsoft.2014.06.002.
Maheswaran, R., and R. Khosa. 2012. “Wavelet–Volterra coupled model for monthly stream flow forecasting.” J. Hydrol. 450 (Mar): 320–335. https://doi.org/10.1016/j.jhydrol.2012.04.017.
Mehr, A. D., and E. Kahya. 2017. “A Pareto-optimal moving average multigene genetic programming model for daily streamflow prediction.” J. Hydrol. 549 (May): 603–615. https://doi.org/10.1016/j.jhydrol.2017.04.045.
Mishra, A., S. Mukherjee, B. Merz, V. P. Singh, D. B. Wright, G. Villarini, S. Paul, D. N. Kumar, C. P. Khedun, and D. Niyogi. 2022. “An overview of flood concepts, challenges, and future directions.” J. Hydrol. Eng. 27 (6): 03122001. https://doi.org/10.1061/(ASCE)HE.1943-5584.0002164.
Mohammadi, K., H. Eslami, and R. Kahawita. 2006. “Parameter estimation of an ARMA model for river flow forecasting using goal programming.” J. Hydrol. 331 (1–2): 293–299. https://doi.org/10.1016/j.jhydrol.2006.05.017.
Mouatadid, S., J. F. Adamowski, M. K. Tiwari, and J. M. Quilty. 2019. “Coupling the maximum overlap discrete wavelet transform and long short-term memory networks for irrigation flow forecasting.” Agric. Water Manage. 219: 72–85.
Murdoch, W. J., C. Singh, K. Kumbier, R. Abbasi-Asl, and B. Yu. 2019. “Definitions, methods, and applications in interpretable machine learning.” Proc. Natl. Acad. Sci. 116 (44): 22071–22080. https://doi.org/10.1073/pnas.1900654116.
Myronidis, D., K. Ioannou, D. Fotakis, and G. Dörflinger. 2018. “Streamflow and hydrological drought trend analysis and forecasting in Cyprus.” Water Resour. Manage. 32 (Jun): 1759–1776. https://doi.org/10.1007/s11269-018-1902-z.
Nguyen, P. K.-T., L. H.-C. Chua, A. Talei, and Q. H. Chai. 2018. “Water level forecasting using neuro-fuzzy models with local learning.” Neural Comput. Appl. 30 (6): 1877–1887. https://doi.org/10.1007/s00521-016-2803-9.
Nourani, V., M. T. Alami, and M. H. Aminfar. 2009. “A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation.” Eng. Appl. Artif. Intell. 22 (3): 466–472. https://doi.org/10.1016/j.engappai.2008.09.003.
Nowak, K. C., B. Rajagopalan, and E. Zagona. 2011. “Wavelet Auto-Regressive Method (WARM) for multi-site streamflow simulation of data with non-stationary spectra.” J. Hydrol. 410 (1–2): 1–12. https://doi.org/10.1016/j.jhydrol.2011.08.051.
Rahman, A. T. M. S., T. Hosono, J. M. Quilty, J. Das, and A. Basak. 2020. “Multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms.” Adv. Water Resour. 141 (Mar): 103595. https://doi.org/10.1016/j.advwatres.2020.103595.
Rezaie-balf, M., S. R. Naganna, A. Ghaemi, and P. C. Deka. 2017. “Wavelet coupled MARS and M5 Model Tree approaches for groundwater level forecasting.” J. Hydrol. 553 (Oct): 356–373. https://doi.org/10.1016/j.jhydrol.2017.08.006.
Sahay, R. R., and A. Srivastava. 2014. “Predicting monsoon floods in rivers embedding wavelet transform, genetic algorithm and neural network.” Water Resour. Manage. 28 (2): 301–317. https://doi.org/10.1007/s11269-013-0446-5.
Seo, Y., S. Kim, O. Kisi, and V. P. Singh. 2015. “Daily water level forecasting using wavelet decomposition and artificial intelligence techniques.” J. Hydrol. 520 (Jan): 224–243. https://doi.org/10.1016/j.jhydrol.2014.11.050.
Shahriari, B., K. Swersky, Z. Wang, R. P. Adams, and N. De Freitas. 2016. “Taking the human out of the loop: A review of Bayesian optimization.” Proc. IEEE 104 (1): 148–175. https://doi.org/10.1109/JPROC.2015.2494218.
Stedinger, J. R., D. P. Lettenmaier, and R. M. Vogel. 1985. “Multisite ARMA (1, 1) and disaggregation models for annual streamflow generation.” Water Resour. Res. 21 (4): 497–509. https://doi.org/10.1029/WR021i004p00497.
Teegavarapu, R. S. V., P. J. Sharma, and P. Lal Patel. 2022. “Frequency-based performance measure for hydrologic model evaluation.” J. Hydrol. 608 (Jun): 127583. https://doi.org/10.1016/j.jhydrol.2022.127583.
Wang, N., D. Zhang, H. Chang, and H. Li. 2020. “Deep learning of subsurface flow via theory-guided neural network.” J. Hydrol. 584 (May): 124700. https://doi.org/10.1016/j.jhydrol.2020.124700.
Wang, T., M. Zhang, Q. Yu, and H. Zhang. 2012. “Comparing the applications of EMD and EEMD on time–frequency analysis of seismic signal.” J. Appl. Geophys. 83 (Aug): 29–34. https://doi.org/10.1016/j.jappgeo.2012.05.002.
Xu, Z., L. Mo, J. Zhou, W. Fang, and H. Qin. 2022. “Stepwise decomposition-integration-prediction framework for runoff forecasting considering boundary correction.” Sci. Total Environ. 851 (Dec): 158342. https://doi.org/10.1016/j.scitotenv.2022.158342.
Yin, Y., Q. Tang, X. Liu, and X. Zhang. 2017. “Water scarcity under various socio-economic pathways and its potential effects on food production in the Yellow River basin.” Hydrol. Earth Syst. Sci. 21 (2): 791–804. https://doi.org/10.5194/hess-21-791-2017.
Zhang, J., X. Liang, L. Zeng, X. Chen, E. Ma, Y. Zhou, and Y.-K. Zhang. 2023. “Deep transfer learning for groundwater flow in heterogeneous aquifers using a simple analytical model.” J. Hydrol. 626 (Jun): 130293. https://doi.org/10.1016/j.jhydrol.2023.130293.
Zhang, X., Y. Peng, C. Zhang, and B. Wang. 2015. “Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences.” J. Hydrol. 530 (Nov): 137–152. https://doi.org/10.1016/j.jhydrol.2015.09.047.
Zhou, R., and Y. Zhang. 2022. “Reconstruction of missing spring discharge by using deep learning models with ensemble empirical mode decomposition of precipitation.” Environ. Sci. Pollut. Res. 29 (54): 82451–82466. https://doi.org/10.1007/s11356-022-21597-w.
Zhou, R., and Y. Zhang. 2023. “Linear and nonlinear ensemble deep learning models for karst spring discharge forecasting.” J. Hydrol. 627 (Dec): 130394. https://doi.org/10.1016/j.jhydrol.2023.130394.
Zhu, S., J. Zhou, L. Ye, and C. Meng. 2016. “Streamflow estimation by support vector machine coupled with different methods of time series decomposition in the upper reaches of Yangtze River, China.” Environ. Earth Sci. 75 (Mar): 1–12. https://doi.org/10.1007/s12665-016-5337-7.
Zuo, G., J. Luo, N. Wang, Y. Lian, and X. He. 2020. “Two-stage variational mode decomposition and support vector regression for streamflow forecasting.” Hydrol. Earth Syst. Sci. 24 (11): 5491–5518. https://doi.org/10.5194/hess-24-5491-2020.
Information & Authors
Information
Published In
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jan 21, 2024
Accepted: Apr 8, 2024
Published online: Jul 1, 2024
Published in print: Oct 1, 2024
Discussion open until: Dec 1, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Biological processes
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction management
- Decomposition
- Domain boundary
- Engineering fundamentals
- Engineering mechanics
- Entropy methods
- Environmental engineering
- Flow (fluid dynamics)
- Fluid dynamics
- Fluid mechanics
- Forecasting
- Hydrologic engineering
- Mathematics
- Statistics
- Streamflow
- Thermodynamics
- Waste management
- Water and water resources
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.