1. MMC
  2. All Volumes and Issues
  3. Volume 12, Number 2, 2025
  4. Hybrid least squares support vector machine for water level forecasting

Hybrid least squares support vector machine for water level forecasting

MMC.
2025;
Volume 12, Number 2
: pp. 384–400
https://doi.org/10.23939/mmc2025.02.384
Received: December 16, 2024
Revised: April 17, 2025
Accepted: April 18, 2025

Someetheram V., Marsani M. F., Kasihmuddin M. S. M., Zamri N. E.  Hybrid least squares support vector machine for water level forecasting.  Mathematical Modeling and Computing. Vol. 12, No. 2, pp. 384–400 (2025)     

Authors:
  1. V. Someetheram
  2. M. F. Marsani
  3. M. S. M. Kasihmuddin
  4. N. E. Zamri
1
School of Mathematical Sciences, Universiti Sains Malaysia
2
School of Mathematical Sciences, Universiti Sains Malaysia
3
School of Mathematical Sciences, University Sains Malaysia
4
Department of Mathematics and Statistics, Faculty od Science, Universiti Putra Malaysia

Previous studies have highlighted the significant role of historical water level data in flood forecasting.  In this study, we compare two standalone models, Support Vector Machine (SVM) and Least Squares Support Vector Machine (LSSVM), with hybrid models that integrate Ensemble Empirical Mode Decomposition (EEMD) with SVM and LSSVM, aiming to develop a more effective forecasting approach for hydrological data.  Particle Swarm Optimization (PSO) is incorporated into these hybrid models to optimize the parameters of SVM and LSSVM, resulting in four models: SVM-PSO, LSSVM-PSO, EEMD-SVM-PSO, and EEMD-LSSVM-PSO.  This study focuses on forecasting water levels in Sungai Gombak, Malaysia.  The performance of the proposed models is evaluated and compared using several metrics, including RMSE, MSE, MAPE, and the squared correlation coefficient.  Results indicate that the EEMD-LSSVM-PSO model outperforms the other models, demonstrating the highest forecasting accuracy for Sungai Gombak, Malaysia, with the lowest RMSE, MSE, and MAPE values and the squared correlation coefficient value close to 1 for the testing data.

machine learning
predictive model
statistical method
water level prediction
flood forecasting
  1. Sumi S. M., Zaman M. F., Hirose H.  A rainfall forecasting method using machine learning models and its application to the Fukuoka city case.  International Journal of Applied Mathematics and Computer Sciencel.  22, 841–854 (2012).
  2. Le X.-H, Ho H. V., Lee G.  River streamflow prediction using a deep neural network: a case study on the Red River, Vietnam.  Korean Journal of Agricultural Science.  46 (4), 843–856 (2019).
  3. Sahoo A., Samantaray S., Ghose D. K.  Prediction of flood in Barak River using hybrid machine learning approaches: A case study.  Journal of Geological Society of India.  97 (2), 186–198 (2021).
  4. Shabri A., Suhartono.  Streamflow forecasting using least-squares support vector machines.  Hydrological Sciences Journal.  57 (7), 1275–1293 (2012).
  5. He S., Sang X., Yin J., Zheng Y., Chen H.  Short-term Runoff Prediction Optimization Method Based on BGRU-BP and BLSTM-BP Neural Networks.  Water Resources Management.  37, 747–-768 (2022).
  6. Belyakova P. A., Moreido V. M., Tsyplenkov A. S., Amerbaev A. N., Grechishnikova D. A., Kurochkina L. S., Filippov V. A., Makeev M. S.  Forecasting Water Levels in Krasnodar Krai Rivers with the Use of Machine Learning.  Water Resources.  49, 10–22 (2022).
  7. Faruq A., Marto A., Abdullah S. S.  Flood forecasting of Malaysia Kelantan river using support vector regression technique.  Computer Systems Science and Engineering.  39 (3), 297–306 (2021).
  8. Ab Razak N. H., Aris A. Z., Ramli A. F., Looi L. J., Juahir H.  Temporal flood incidence forecasting for Segamat River (Malaysia) using auto-regressive integrated moving average modelling.  Journal of Flood Risk Management.  11, S794–S804 (2016).
  9. Darabi H., Torabi Haghighi A., Rahmati O., Jalali Shahrood A., Rouzbeh S., Pradhan B., Tien Bui D.  A hybridized model based on neural network and swarm intelligence-grey wolf algorithm for spatial prediction of urban flood-inundation.  Journal of Hydrology.  603, 126854 (2021).
  10. Shaaban N. N, Hassan N., Mustapha A., Mostafa S. A.  Comparative Performance of Supervised Learning Algorithms for Flood Prediction in Kemaman, Terengganu.  Journal of Computer Science.  17 (5), 451–458 (2021).
  11. Sukanya K., Vijayakumar P.  Frequency Control Approach and Load Forecasting Assessment for Wind Systems.  Intelligent Automation and Soft Computing.  35 (1), 971–982 (2023).
  12. Cortes C., Vapnik V.  Support-vector networks.  Machine Learning.  297, 273–297 (1995).
  13. Achite M., Jehanzaib M., Elshaboury N., Kim T. W.  Evaluation of Machine Learning Techniques for Hydrological Drought Modeling: A Case Study of the Wadi Ouahrane Basin in Algeria.  Water (Switzerland).  14, (2022).
  14. Wang H. F., Hu D.  Comparison of SVM and LS-SVM for regression.  2005 International Conference on Neural Networks and Brain.  279–283 (2005).
  15. Guo S., Wen Y., Zhang X., Chen H.  Runoff prediction of lower Yellow River based on CEEMDAN-LSSVM-GM(1,1) model.  Scientific Reports.  13, 1511 (2023).
  16. Lin S.-W., Ying K.-C., Chen S.-C., Lee Z.-J.  Particle swarm optimization for parameter determination and feature selection of support vector machines.  Expert Systems with Applications.  35 (4), 1817–1824 (2008).
  17. Someetheram V., Marsani M. F., Kasihmuddin M. S. M., Jamaludin S. Z. M., Mansor M. A.  Double Decomposition with Enhanced Least-Squares Support Vector Machine to Predict Water Level.  Journal of Water & Climate Change.  15 (6), 2582–2594 (2024).
  18. Zeng J., Tan Z.-H., Matsunaga T., Shirai T.  Generalization of Parameter Selection of SVM and LS-SVM for Regression.  Machine Learning and Knowledge Extraction.  1 (2), 745–755 (2019).
  19. Zhou C., Yin K., Cao Y., Intrieri E., Ahmed B., Catani F.  Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method.  Landslides.  15, 2211–2225 (2018).
  20. Deng W., Yao R., Zhao H., Yang X., Li G.  A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm.  Soft Computing.  23, 2445–2462 (2019).
  21. Li X., Yang S.-d., Qi J.-x.  A new support vector machine optimized by improved particle swarm optimization and its application.  Journal of Central South University of Technology.  13, 568–572 (2006).
  22. Brits R., Engelbrecht A. P., van den Bergh F.  Locating multiple optima using particle swarm optimization.  Applied Mathematics and Computation.  189 (2), 1859–1883 (2007).
  23. Sarath K. N. V. D., Ravi V.  Association rule mining using binary particle swarm optimization.  Engineering Applications of Artificial Intelligence.  26 (8), 1832–1840 (2013).
  24. Ostadrahimi L, Mariño M. A., Afshar A.  Multi-reservoir operation rules: multi-swarm PSO-based optimization approach.  Water Resources Management.  26, 407–427 (2012).
  25. Huang N. E., Shen Z., Long S. R., Wu M. C., Shih H. H., Zheng Q., Yen N.-C., Tung C. C., Liu H. H.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis.  Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.  454 (1971), 903–995 (1998).
  26. Stajuda M., García Cava D., Liśkiewicz G.  Aerodynamic instabilities detection via empirical mode decomposition in centrifugal compressors.  Measurement.  199, 111496 (2022).
  27. Wu Z., Huang N. E.  Ensemble empirical mode decomposition: A noise-assisted data analysis method.  Advances in Adaptive Data Analysis.  1 (1), 1–41 (2009).
  28. Wang W.-c., Chau K.-w., Xu D.-m., Chen X.-Y.  Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition.  Water Resources Management.  29, 2655–2675 (2015).
  29. Wang W.-c., Chau K.-w., Qiu L., Chen Y.-b.  Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition.  Environmental Research.  139, 46–54 (2015).
  30. Wang W.-c., Xu D.-m., Chau K.-w., Chen S.  Improved annual rainfall-runoff forecasting using PSO-SVM.  Journal of Hydroinformatics.  15 (4), 1377–1390 (2013).
  31. Liu H., Tian H.-q., Li Y.-f.  Comparison of new hybrid FEEMD-MLP, FEEMD-ANFIS, wavelet packet-MLP and wavelet packet ANFIS for wind speed predictions.  Energy Conversion and Management.  89, 1–11 (2015).
  32. Duan W. Y., Han Y., Huang L. M., Zhao B. B., Wang M. H.  A hybrid EMD-SVR model for the short-term prediction of significant wave height.  Ocean Engineering.  124, 54–73 (2016).
  33. Napolitano G., Serinaldi F., See L.  Impact of EMD decomposition and random initialization of weights in ANN hindcasting of daily streamflow series: An empirical examination.  Journal of Hydrology.  406 (3–4), 199–214 (2011).
  34. Karthikeyan L., Nagesh Kumar D.  Predictability of nonstationary time series using wavelet and EMD based ARMA models.  Journal of Hydrology.  502, 103–119 (2013).
  35. Hawinkel P., Swinnen E., Lhermitte S., Verbist B., Van Orshoven J., Muys B.  A time series processing tool to extract climate-driven interannual vegetation dynamics using Ensemble Empirical Mode Decomposition (EEMD).  Remote Sensing of Environment.  169, 375–389 (2015).
  36. Faruq A., Marto A., Abdullah S. S.  Flood forecasting of Malaysia Kelantan River using support vector regression technique.  Computer Systems Science and Engineering.  39 (3), 297–306 (2021).
  37. Qin Y., Lei Y., Gong X., Ju W.  A model involving meteorological factors for short-to medium-term water-level predictions of small- and medium-sized urban rivers.  Natural Hazards.  1–15 (2021).
  38. Samantaray S., Sahoo A.  Prediction of flow discharge in Mahanadi River Basin, India, based on novel hybrid SVM approaches.  Environment, Development and Sustainability.  26 (7), 18699–18723 (2024).
  39. Heddam S., Vishwakarma D. K., Abed S. A., Sharma P., Al-Ansari N., Alataway A., Dewidar A. Z., Mattar M. A.  Hybrid river stage forecasting based on machine learning with empirical mode decomposition.  Applied Water Science.  14 (3), 46 (2024).
  40. Huang S., Chang J., Huang Q., Chen Y.  Monthly streamflow prediction using modified EMD-based support vector machine.  Journal of Hydrology.  511, 764–775 (2014).
  41. Dehghan Y., Amini Zenooz S. M., Pour Z. F.  Analysis of sea level fluctuations around the Australian coast with anomaly time series analysis approach.  Marine Environmental Research.  181, 105742 (2022).
  42. Guhathakurta K., Mukherjee I., Chowdhury A. R.  Empirical mode decomposition analysis of two different financial time series and their comparison.  Chaos, Solitons & Fractals.  37 (4), 1214–1227 (2008).
  43. Flandrin P., Rilling G., Goncalves P.  Empirical mode decomposition as a filter bank.  IEEE Signal Processing Letters.  11 (2), 112–114 (2003).
  44. Colominas M. A., Schlotthauer G., Torres M. E.  An unconstrained optimization approach to empirical mode decomposition.  Digital Signal Processing.  40, 164–175 (2015).
  45. Anuwar F. H., Omar A. M.  Future solar irradiance prediction using least square support vector machine.  International Journal on Advanced Science, Engineering and Information Technology.  6 (4), 520–523 (2016).
  46. Kennedy J., Eberhart R.  Particle swarm optimization.  Proceedings of ICNN'95 – International Conference on Neural Networks. 1942–1948 (1995).
  47. Chau K. W.  Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River.  Journal of Hydrology.  329 (3–4), 363–367 (2006).
  48. Wong W. M., Lee M. Y., Azman A. S., Rose L. A. F.  Development of short-term flood forecast using ARIMA. International Journal of Mathematical Models and Methods in Applied Sciences.  15, 68–75 (2021).
  49. Dickey D. A., Fuller W. A.  Distribution of the estimators for autoregressive time series with a unit root.  Journal of the American Statistical Association.  74 (366a), 427–431 (1979).
  50. Kwiatkowski D., Phillips P. C. B., Schmidt P., Shin Y.  Testing the null hypothesis of stationarity against the alternative of a unit root.  Journal of Econometrics.  54 (1–3), 159–178 (1992).
  51. Wang W.-C., Chau K.-W., Cheng C.-T., Qiu L.  A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series.  Journal of Hydrology.  374 (3–4), 294–306 (2009).
  52. Wang D., Cui X., Niu D.  Wind power forecasting based on LSTM improved by EMD-PCA-RF.  Sustainability.  14 (12), 7307 (2022).
  53. Marsani M. F., Shabri A.  Non-stationary in extreme share return: World indices application.  ASM Science Journal.  13, 1–9 (2020).