Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area and Data Sources
2.2. Methods
2.2.1. Fuzzy Information Granulation
2.2.2. BP Neural Network Improved by Genetic Algorithm
2.3. Modeling and Evaluation
2.3.1. FIG-GA-BP Prediction Model Construction
2.3.2. Interval Prediction Evaluation Index
- (1)
- FICP
- (2)
- FIAW
2.4. Data Pre-Processing
3. Results
3.1. Feature Selection
3.2. Results Analysis
4. Discussion
5. Conclusions
- (1)
- The interval prediction method based on fuzzy information granulation can be applied to runoff prediction. In the three hydrological stations, the FICP values are greater than 0.9 for both the FIG-GA-BP model and the FIG-BP model, reflecting good prediction effect. Compared with the traditional probability model, it does not need to use the probability density function, requires fewer parameters, and reduces the prediction workload.
- (2)
- The prediction effect of the FIG-GA-BP model in Weijiabu, Linjiacuan, and Zhangjiashan hydrologic stations is better than that of FIG-BP model, and the FICP is 0.98, which is greater than 0.95. The overall prediction performance is good. The results show that the interval prediction model based on fuzzy information granulation is an effective tool for predicting nonstationary time series data and is a new method for solving the uncertainty in runoff prediction. The prediction interval of runoff enables decision makers to better recognize the uncertainty of runoff and thus make more reasonable decisions for water resource management.
- (3)
- The FIG-GA-BP model proposed in this paper is more suitable for the interval prediction of runoff series and can provide information support for decision makers of water resource management. Furthermore, the center of the prediction interval can be used as the result of point value prediction.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Zhang, J.W.; Chen, X.H.; Khan, A.; Zhang, Y.K.; Kuang, X.X.; Liang, X.Y.; Taccari, M.L.; Nuttall, J. Daily runoff forecasting by deep recursive neural network. J. Hydrol. 2021, 596, 126067. [Google Scholar] [CrossRef]
- Kalteh, A.M. Improving forecasting accuracy of streamflow time series using least squares support vector machine Coupled with data-preprocessing techniques. Water Resour. Manag. 2016, 30, 747–766. [Google Scholar] [CrossRef]
- Ji, C.M.; Li, R.B.; Zhang, Y.K.; Liu, D.; Zhang, P.; Du, L. Projection purchasing autoregressive combination model based on wavelet decomposition and its application to annual runoff prediction. J. Hydroelectr. Eng. 2015, 34, 27–35. [Google Scholar]
- Yao, Y.M.; Liu, M.Y.; Chen, Y.; Li, Z.J. Uncertainty analysis and application of daily runoff simulation in Haihe River Basin. Water Conserv. Plan. Des. 2019, 12, 14–17+22. [Google Scholar]
- Cheng, C.T.; Chau, K.; Sun, Y.G.; Lin, J.Y. Long-term prediction of discharges in Manwan Reservoir using artificial neural network models. Lect. Notes Comput. 2005, 3498, 1040–1045. [Google Scholar]
- Zhang, X.W.; Shen, B.; Huang, L.M. Grey self-memory runoff prediction model based on BP neural network. J. Hydroelectr. Eng. 2009, 28, 68–71. [Google Scholar]
- Guo, J.; Zhou, J.Z.; Qin, H.; Zou, Q.; Li, Q.Q. Monthly streamflow forecasting based on improved support vector machine model. Expert Syst. Appl. 2011, 38, 13073–13081. [Google Scholar] [CrossRef]
- Kisi, O.; Cimen, M. A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J. Hydrol. 2011, 399, 132–140. [Google Scholar] [CrossRef]
- Badrzadeh, H.; Sarukkalige, R.; Jayawardena, A.W. Hourly runoff forecasting for flood risk management: Application of various computational intelligence models. J. Hydrol. 2015, 529, 1633–1643. [Google Scholar] [CrossRef]
- Zhao, T.T.G.; Yang, D.W.; Li, M.L. Transcendental probability Bayesian discriminant analysis and its application in medium-long-term runoff forecast. J. Hydraul. Eng. 2011, 42, 692–699. [Google Scholar]
- Ma, Z.K.; Li, Z.J.; Zhang, M.; Fan, Z.W. Bayesian Statistic Forecasting Model for Middle-Term and Long-Term Runoff of a Hydropower Station. J. Hydrol. Eng. 2013, 18, 1458–1463. [Google Scholar] [CrossRef]
- Yuan, X.H.; Chen, C.; Yuan, Y.B.; Zhang, B.Q. Runoff Prediction Based on Hybrid Clustering with WOA Intervals Mapping Model. J. Hydrol. Eng. 2021, 26, 04021019. [Google Scholar] [CrossRef]
- Zadel, L.A. Towards a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst. 1997, 90, 111–127. [Google Scholar] [CrossRef]
- Chen, Y.L.; Yin, H.; Huang, Q.; Zhou, Y.W. Fuzzy interval forecasting of photovoltaic output. Ningxia Electr. Power 2017, 5, 39–44. [Google Scholar]
- He, Y.Y.; Yan, Y.D.; Wang, X.; Wang, C. Uncertainty Forecasting for Streamflow based on Support Vector Regression Method with Fuzzy Information Granulation. Energy Procedia 2019, 158, 6189–6194. [Google Scholar] [CrossRef]
- Zhang, N.; Wang, S.X.; Ge, L.J.; Wang, Z.H. A prediction method for short term output interval of photovoltaic. Acta Energ. Sol. Sin. 2020, 41, 173–179. [Google Scholar]
- Luo, C.; Wang, H.Y. Fuzzy forecasting for long-term time series based on time-variant fuzzy information granules. Appl. Soft Comput. 2020, 88, 106046. [Google Scholar] [CrossRef]
- Yang, L. Machine Learning Classification and Regression Prediction Analysis Based on Information Granulation; Beijing Normal University: Beijing, China, 2009. [Google Scholar]
- Pedrycz, W. Granular Computing: An Introduction; Physica: Heidelberg, Germany, 2000; pp. 309–328. [Google Scholar]
- Zhu, H. VRP problem with fuzzy time and demand based on improved particle swarm optimization. Logist. Technol. 2017, 36, 84–89. [Google Scholar]
- Han, X.; Wei, Z.; Zhang, B.Z.; Li, Y.N.; Du, T.S.; Chen, H. Crop evapotranspiration prediction by considering dynamic change of crop coefficient and the precipitation effect in back-propagation neural coefficient and the precipitation effect in back-propagation neural network model. J. Hydrol. 2021, 596, 126104. [Google Scholar] [CrossRef]
- Li, J.Q.; Wang, S. Medium- and long-term runoff forecast based on ESMD-BP neural network combination model. J. Appl. Basic Eng. Sci. 2020, 28, 817–832. [Google Scholar] [CrossRef]
- Li, Y.P.; Jia, M.; Han, X.; Bai, X.S. Towards a comprehensive optimization of engine efficiency and emissions by coupling artificial neural network (ANN) with genetic algorithm (GA). Energy 2021, 225, 120331. [Google Scholar] [CrossRef]
- Khosravi, A.; Nahavandi, S.; Creighton, D. Construction of optimal prediction intervals for load forecasting problems. IEEE Trans. Power Syst. 2010, 25, 1496–1503. [Google Scholar] [CrossRef] [Green Version]
- Vahid, N.; Nardin, J.P.; Elnaz, S.; Abbas, K. Estimation of prediction interval in ANN-based multi-GCMs downscaling of hydro-climatologic parameters. J. Hydrol. 2019, 579, 124226. [Google Scholar] [CrossRef]
- Zhang, G.; LI, Z.X.; Zhang, K.S.; Zhang, L.; Hua, X.; Wang, Y.Q. Multi-objective interval prediction of wind power based on conditional copula function. Clean Energy 2019, 7, 802–812. [Google Scholar] [CrossRef]
Hydrological Station | Min | Mean | Max | SD |
---|---|---|---|---|
Weijiabu | 1.61 | 87.71 | 728.42 | 113.752 |
Linjiacun | 0.40 | 60.33 | 434.00 | 63.77 |
Zhangjiashan | 0 | 37.10 | 340.07 | 51.38 |
Hydrological Station | Model | FICP | FINAW | QR (%) | ARE (%) | RMSE |
---|---|---|---|---|---|---|
Weijiabu | FIG-GA-BP | 0.98 | 0.46 | 81 | 12 | 18.51 |
FIG-BP | 0.95 | 0.69 | 72 | 18 | 74.40 | |
FIG-WNN | 0.94 | 0.72 | 76 | 17 | 33.95 | |
BP | \ | \ | 77 | 15 | 38.47 | |
Linjiacun | FIG-GA-BP | 0.98 | 0.63 | 84 | 14 | 18.63 |
FIG-BP | 0.94 | 0.87 | 80 | 13 | 18.42 | |
FIG-WNN | 0.93 | 0.76 | 64 | 25 | 23.12 | |
BP | \ | \ | 78 | 18 | 20.32 | |
Zhangjiashan | FIG-GA-BP | 0.98 | 0.23 | 89 | 11 | 7.64 |
FIG-BP | 0.97 | 0.57 | 82 | 18 | 14.23 | |
FIG-WNN | 0.94 | 0.66 | 67 | 30 | 24.56 | |
BP | \ | \ | 81 | 14 | 7.68 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, X.; Zhang, X.; Xie, J.; Zhang, X.; Liu, S. Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network. Water 2022, 14, 3683. https://doi.org/10.3390/w14223683
Yang X, Zhang X, Xie J, Zhang X, Liu S. Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network. Water. 2022; 14(22):3683. https://doi.org/10.3390/w14223683
Chicago/Turabian StyleYang, Xinyu, Xiao Zhang, Jiancang Xie, Xu Zhang, and Shihui Liu. 2022. "Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network" Water 14, no. 22: 3683. https://doi.org/10.3390/w14223683
APA StyleYang, X., Zhang, X., Xie, J., Zhang, X., & Liu, S. (2022). Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network. Water, 14(22), 3683. https://doi.org/10.3390/w14223683