journal article·2023-05-05Open access

Investigation of the EWT–PSO–SVM Model for Runoff Forecasting in the Karst Area

Chongxun Mo, Zhiwei Yan, Rongyong Ma, Xingbi Lei, Yun Deng, Shufeng Lai, Keke Huang, Xixi Mo

Applied Sciences· Volume 13· Issue 9

Abstract

As the runoff series exhibit nonlinear and nonstationary characteristics, capturing the embedded periodicity and regularity in the runoff series using a single model is challenging. To account for these runoff characteristics and enhance the forecasting precision, this research proposed a new empirical wavelet transform–particle swarm optimization–support vector machine (EWT–PSO–SVM) hybrid model based on “decomposition-forecasting-reconstruction” for runoff forecasting and investigated its effectiveness in the karst area. First, empirical wavelet transform (EWT) was employed to decompose the original runoff series into multiple subseries. Second, the support vector machine (SVM) optimized by particle swarm optimization (PSO) was applied to forecast every signal subseries. Finally, this study summarized the predictions of the subseries to reconstruct the ultimate runoff forecasting. The developed forecasting model was assessed by applying the monthly runoff series of the Chengbi River Karst Basin, and the composite rating index combined with five metrics was adopted as the performance evaluation tool. From the results of this research, it is clear that the EWT–PSO–SVM model outperforms both the PSO–SVM model and the SVM model in terms of the composite rating index, reaching 0.68. Furthermore, verifying the performance stability, the developed model was also compared with PSO–SVM and SVM models under different input data structures. The comparison demonstrated that the hybrid EWT–PSO–SVM model had a robust performance superiority and was an effective model that can be applied to karst area runoff forecasting.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Hydrological Forecasting Using AI · Hydrology and Watershed Management Studies · Hydrology and Sediment Transport Processes

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Key Laboratory of Disaster Prevention and Structural Safety, Ministry of Education, College of Civil Engineering and Architecture, Guangxi University, Nanning 530004, China

College of Architecture and Civil Engineering, Guangxi University, Nanning 530004, China

Guangxi Provincial Engineering Research Center of Water Security and Intelligent Control for Karst Region, Guangxi University, Nanning 530004, China

Guangxi Key Laboratory of Disaster Prevention and Engineering Safety, Guangxi University, Nanning 530004, China

Nanning Survey and Design Institute of Guangxi Pearl River Commission, Nanning 530004, China

Funding

National Natural Science Foundation of China · Guangxi University · Interdisciplinary Scientific Research Foundation of Guangxi University · Guangxi Water Resource Technology Promotion Foundation

References (42)

Show source-provided references
1. Short-range reservoir inflow forecasting using hydrological and large-scale atmospheric circulation information10.1016/j.jhydrol.2022.128153 ↗
2. Improving the precision of monthly runoff prediction using the combined non-stationary methods in an oasis irrigation area10.1016/j.agwat.2023.108161 ↗
3. Daily runoff forecasting by deep recursive neural network10.1016/j.jhydrol.2021.126067 ↗
4. High temporal resolution rainfall–runoff modeling using long-short-term-memory (LSTM) networks10.1007/s00521-020-05010-6 ↗
5. Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States10.5194/hess-26-5449-2022 ↗
6. Hydrological time series forecasting via signal decomposition and twin support vector machine using cooperation search algorithm for parameter identification10.1016/j.jhydrol.2022.128213 ↗
7. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds10.1016/j.jhydrol.2010.06.033 ↗
8. The utilization of a GR4J model and wavelet-based artificial neural network for rainfall–runoff modelling10.2166/ws.2018.189 ↗
9. Hydrological time series prediction by extreme learning machine and sparrow search algorithm10.2166/ws.2021.419 ↗
10. On a class of perceptrons
11. A data-driven SVR model for long-term runoff prediction and uncertainty analysis based on the Bayesian framework10.1007/s00704-017-2186-6 ↗
12. Stochastic simulation of daily runoff in the middle reaches of the Yangtze river based on SVM-Copula model10.1080/21642583.2019.1694598 ↗
13. Combining two-stage decomposition based machine learning methods for annual runoff forecasting10.1016/j.jhydrol.2021.126945 ↗
14. Short-Term Power Generation Forecasting of a Photovoltaic Plant Based on PSO-BP and GA-BP Neural Networks10.3389/fenrg.2021.824691 ↗
15. Yang, X., Maihemuti, B., Simayi, Z., Saydi, M., and Na, L. (2022). Prediction of Glacially Derived Runoff in the Muzati River Watershed Based on the PSO-LSTM Model. Water, 14.10.3390/w14132018 ↗
16. A hybrid SVM-PSO model for forecasting monthly streamflow10.1007/s00521-013-1341-y ↗
17. Monthly streamflow prediction using modified EMD-based support vector machine10.1016/j.jhydrol.2014.01.062 ↗
18. Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models10.1016/j.jhydrol.2015.11.011 ↗
19. Ensemble empirical mode decomposition: A noise-assisted data analysis method10.1142/S1793536909000047 ↗
20. Empirical Wavelet Transform10.1109/TSP.2013.2265222 ↗
21. Recent Advancements in Empirical Wavelet Transform and Its Applications10.1109/ACCESS.2019.2930529 ↗
22. Li, B., Liu, M., Guo, Z., and Ji, Y. (2020, January 14–16). Application of EWT and PSO-SVM in Fault Diagnosis of HV Circuit Breakers. Proceedings of the 7th International Conference on Communications, Signal Processing, and Systems (CSPS), Dalian, China.
23. Application of a new EWT-based denoising technique in bearing fault diagnosis10.1016/j.measurement.2019.05.049 ↗
24. A hybrid technique for short-term wind speed prediction10.1016/j.energy.2014.12.074 ↗
25. A Hybrid Model for Financial Time Series Forecasting—Integration of EWT, ARIMA with The Improved ABC Optimized ELM10.1109/ACCESS.2020.2987547 ↗
26. Status, mechanism, suitable distribution areas and protection countermeasure of invasive species in the karst areas of Southwest China10.3389/fenvs.2022.957216 ↗
27. A threshold artificial neural network model for improving runoff prediction in a karst watershed10.1007/s12665-015-4562-9 ↗
28. Adaptive determination method of wavelet filter decomposition layers
29. Evaluating the performances of several artificial intelligence methods in forecasting daily streamflow time series for sustainable water resources management10.1016/j.scs.2020.102562 ↗
30. Kennedy, J., and Eberhart, R. (December, January 27). Particle swarm optimization. Proceedings of the ICNN’95-International Conference on Neural Networks 1995, Perth, WA, Australia.
31. Monthly runoff time series prediction by variational mode decomposition and support vector machine based on quantum-behaved particle swarm optimization10.1016/j.jhydrol.2020.124627 ↗
32. Mo, C., Liu, G., Lei, X., Zhang, M., Ruan, Y., Lai, S., and Xing, Z. (2022). Study on the Optimization and Stability of Machine Learning Runoff Prediction Models in the Karst Area. Appl. Sci., 12.10.3390/app12104979 ↗
33. Zhao, X., Lv, H., Wei, Y., Lv, S., and Zhu, X. (2021). Streamflow Forecasting via Two Types of Predictive Structure-Based Gated Recurrent Unit Models. Water, 13.10.3390/w13010091 ↗
34. Impact of climate change and human activities on the baseflow in a typical karst basin, Southwest China10.1016/j.ecolind.2021.107628 ↗
35. Comparative study of innovative trend analysis technique with Mann-Kendall tests for extreme rainfall10.1007/s12517-021-06906-w ↗
36. Zhang, X., Zhao, C., and Yang, J. (2020, January 5–7). Quantitative Analysis of Impact of Climate Variability and Human Activities on Water Resources Change in Suzhou City. Proceedings of the 4th International Conference on Environmental Engineering and Sustainable Development (CEESD), Xiamen, China.
37. Wavelet regression model for short-term streamflow forecasting10.1016/j.jhydrol.2010.06.013 ↗
38. An interval parameter conditional value-at-risk two-stage stochastic programming model for sustainable regional water allocation under different representative concentration pathways scenarios10.1016/j.jhydrol.2018.07.008 ↗
39. A model involving meteorological factors for short- to medium-term, water-level predictions of small- and medium-sized urban rivers10.1007/s11069-021-05076-y ↗
40. Rainfall-runoff simulation in karst dominated areas based on a coupled conceptual hydrological model10.1016/j.jhydrol.2019.03.099 ↗
41. Daily Runoff Forecasting Using Ensemble Empirical Mode Decomposition and Long Short-Term Memory10.3389/feart.2021.621780 ↗
42. Sagir, C., Kurtulus, B., and Razack, M. (2020). Hydrodynamic Characterization of Mugla Karst Aquifer Using Correlation and Spectral Analyses on the Rainfall and Springs Water-Level Time Series. Water, 12.10.3390/w12010085 ↗