1. MMC
  2. All Volumes and Issues
  3. Volume 12, Number 2, 2025
  4. Enhancing flood forecasting accuracy through improved SVM and ANFIS techniques

Enhancing flood forecasting accuracy through improved SVM and ANFIS techniques

MMC.
2025;
Volume 12, Number 2
: pp. 447–460
https://doi.org/10.23939/mmc2025.02.447
Received: December 18, 2024
Revised: May 11, 2025
Accepted: May 15, 2025

Abdualkarim S., Kasihmuddin M., Marsani M.  Enhancing flood forecasting accuracy through improved SVM and ANFIS techniques.  Mathematical Modeling and Computing. Vol. 12, No. 2, pp. 447–460 (2025)   

Authors:
  1. S. Abdualkarim
  2. M. Kasihmuddin
  3. M. Marsani
1
School of Mathematical Sciences, Universiti Sains Malaysia
2
School of Mathematical Sciences, Universiti Sains Malaysia
3
School of Mathematical Sciences, Universiti Sains Malaysia

Extreme rainfall in upstream watersheds often results in the rise of river water levels, leading to severe flood disasters in the downstream catchment.  Therefore, monitoring river water levels and flow is crucial for flood forecasting in early warning systems and disaster risk reduction. However, forecasting river water levels remains a challenging task that cannot be easily captured with classical time-series approaches.  This paper explores the potential of improving flood forecasting accuracy by combining two forecasting techniques: Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) by simple averaging and weighted averaging methods and optimizing their contributions.  To tune different individuals' weights the genetic algorithm and K-nearest neighbors' algorithm (K-NN) were used to find the optimal weight combination.  The committee machine model was employed to forecast the river water level in different lead times from 1 hour to 6 hours applied to the Selangor River.  Model performance was evaluated and analyzed using various performance metrics, including mean percentage error (MPE), root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R).  The results show that the proposed Intelligent Committee Machine Learning (ICML) outperformed SVM and ANFIS for most performance indicators.  This method aims to develop a robust and accurate time series forecasting model by combining multiple forecasting techniques and optimizing their contributions, ultimately leading to improved prediction performance.

flood
genetic algorithm
forecasting
Selangor River
ANFIS
SVM
  1. Ahmadi N., Moradinia S. F.  An approach for flood flow prediction utilizing new hybrids of ANFIS with several optimization techniques: a case study.  Hydrology Research.  55 (5), 560–575 (2024).
  2. Faruq A., Marto A., Izzaty N. K., Kuye A. T., Hussein S. F. M., Abdullah S. S.  Flood disaster and early warning: application of ANFIS for river water level forecasting.  Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control.  6 (1), 1–10 (2021).
  3. Jabbari A., Bae D.-H.  Application of Artificial Neural Networks for accuracy enhancements of real-time flood forecasting in the Imjin basin.  Water.  10 (11), 1626 (2018).
  4. Alexander A. A., Thampi S. G., Chithra N. R.  Development of hybrid wavelet-ANN model for hourly flood stage forecasting.  ISH Journal of Hydraulic Engineering.  24 (2), 266–274 (2018).
  5. Rezaeianzadeh M., Tabari H., Arabi Yazdi A., Isik S., Kalin L.  Flood flow forecasting using ANN, ANFIS and regression models.  Neural Computing and Applications.  25 (1), 25–37 (2014).
  6. Jang J.-S. R.  ANFIS: Adaptive-Network-Based Fuzzy Inference System.  IEEE Transactions on Systems, Man, and Cybernetics.  23 (3), 665–685 (1993).
  7. Najafzadeh M., Zahiri A.  Neuro-Fuzzy GMDH-Based Evolutionary Algorithms to Predict Flow Discharge in Straight Compound Channels.  Journal of Hydrologic Engineering.  20 (12), 04015035 (2015).
  8. Aziz K., Haque M. M., Rahman A., Shamseldin A. Y., Shoaib M.  Flood Estimation in Ungauged Catchments: Application of Artificial Intelligence Based Methods for Eastern Australia.  Stochastic Environmental Research and Risk Assessment.  31, 1499–1514 (2017).
  9. Kordrostami S., Alim M. A., Karim F., Rahman A.  Regional Flood Frequency Analysis Using an Artificial Neural Network Model.  Geosciences.  10 (4), 127 (2020).
  10. Jajarmizadeh M., Lafdani E. K., Harun S., Ahmadi A.  Application of SVM and SWAT Models for Monthly Streamflow Prediction, a Case Study in South of Iran.  KSCE Journal of Civil Engineering.  19 (1), 345–357 (2014).
  11. Najafzadeh M., Etemad-Shahidi A., Lim S. Y.  Scour Prediction in Long Contractions using ANFIS and SVM.  Ocean Engineering.  111, 128–135 (2016).
  12. Allahbakhshian-Farsani P., Vafakhah M., Khosravi-Farsani H., Hertig E.  Regional Flood Frequency Analysis Through Some Machine Learning Models in Semi-arid Regions.  Water Resources Management.  34, 2887–2909 (2020).
  13. Jang J.-S. R.  ANFIS: adaptive-network-based fuzzy inference system.  IEEE Transactions on Systems, Man, and Cybernetics.  23 (3), 665–685 (1993).
  14. Bozchaloei S. K., Vafakhah M.  Regional Analysis of Flow Duration Curves Using Adaptive Neuro-Fuzzy Inference System.  Journal of Hydrologic Engineering.  20 (12), 06015008 (2015).
  15. Garmdareh E. S., Vafakhah M., Eslamian S. S. Regional Flood Frequency Analysis Using Support Vector Regression in Arid and Semi-arid Regions of Iran.  Hydrological Sciences Journal.  63 (3), 426–440 (2018).
  16. Samantaray S., Sahoo A., Agnihotri A.  Prediction of flood discharge using hybrid PSO-SVM algorithm in Barak River Basin.  MethodsX.  10, 102060 (2023).
  17. Han D., Chan L., Zhu N.  Flood forecasting using support vector machines.  Journal of Hydroinformatics.  9 (4), 267–276 (2007).
  18. Firat M., Güngör M.  River flow estimation using adaptive neuro fuzzy inference system.  Mathematics and Computers in Simulation.  75 (3-4), 87–96 (2007).
  19. Esmaili M., Aliniaeifard S., Mashal M., Vakilian K. A., Ghorbanzadeh P., Azadegan B., Seif M., Didaran F.  Assessment of adaptive neuro-fuzzy inference system (ANFIS) to predict production and water productivity of lettuce in response to different light intensities and CO$_2$ concentrations.  Agricultural Water Management.  258, 107201 (2021).
  20. Seifi A., Riahi-Madvar H.  Improving one-dimensional pollution dispersion modeling in rivers using ANFIS and ANN-based GA optimized models.  Environmental Science and Pollution Research.  26, 867–885 (2019).
  21. Qasem S. N., Ebtehaj I., Madavar H. R.  Optimizing ANFIS for sediment transport in open channels using different evolutionary algorithms.  Journal of Applied Research in Water and Wastewater.  4 (1), 290–298 (2017).
  22. Kayhomayoon Z., Naghizadeh F., Malekpoor M., Azar N. A., Ball J., Milan S. G.  Prediction of evaporation from dam reservoirs under climate change using soft computing techniques.  Environmental Science and Pollution Research.  30 (10), 27912–27935 (2023).
  23. Milan S. G., Roozbahani A., Azar N. A., Javadi S.  Development of adaptive neuro fuzzy inference system Evolutionary algorithms hybrid models (ANFIS-EA) for prediction of optimal groundwater exploitation.  Journal of Hydrology.  598, 126258 (2021).
  24. Insom P., Cao C., Boonsrimuang P., Liu D., Saokarn A., Yomwan P., Xu Y.  A support vector machine-based particle filter method for improved flooding classification.  IEEE Geoscience and Remote Sensing Letters.  12 (9), 1943–1947 (2015).
  25. Dehghani M., Seifi A., Riahi-Madvar H.  Novel forecasting models for immediate-short-term to long-term influent flow prediction by combining ANFIS and grey wolf optimization.  Journal of Hydrology.  576, 698–725 (2019).
  26. Azar N. A., Milan S. G., Kayhomayoon Z.  Predicting monthly evaporation from dam reservoirs using LS-SVR and ANFIS optimized by Harris Hawks optimization algorithm.  Environmental Monitoring and Assessment.  193 (11), 695 (2021).
  27. Faruq A., Hussein S. F. M., Marto A., Abdullah S. S.  Flood River Water Level Forecasting using Ensemble Machine Learning for Early Warning Systems.  IOP Conference Series: Earth and Environmental Science.  1091 (1), 012041 (2022).
  28. Elkhrachy I., Yadav R. R,, Mabdeh A. N., Thanh P. N., Spalevic V., Dudic B.  Landslide susceptibility mapping and management in Western Serbia: an analysis of ANFIS-and SVM-based hybrid models.  Frontiers in Environmental Science.  11, 1218954 (2023).
  29. Dodangeh E., Panahi M., Rezaie F., Lee S., Bui D. T., Lee C.-W., Pradhan B.  Novel hybrid intelligence models for flood-susceptibility prediction: Meta optimization of the GMDH and SVR models with the genetic algorithm and harmony search.  Journal of Hydrology.  590, 125423 (2020).
  30. Yang T.-C., Yu P.-S., Lin K.-H., Kuo C.-M., Tseng H.-W.  Predictor selection method for the construction of support vector machine (SVM)-based typhoon rainfall forecasting models using a non-dominated sorting genetic algorithm.  Meteorological applications.  25 (4), 510–522 (2018).
  31. Liu K., Yao C., Chen J., Li Z., Sun Q. L.  Comparison of three updating models for real time forecasting: A case study of flood forecasting at the middle reaches of the Huai River in East China.  Stochastic Environmental Research and Risk Assessment.  31, 1471–1484 (2017).    
  32. Novitasari D. C. R., Rohayani H., Junaidi R., Setyowati R. D., Pramulya R., Setiawan F.  Weather parameters forecasting as variables for rainfall prediction using adaptive neuro fuzzy inference system (ANFIS) and support vector regression (SVR).  Journal of Physics: Conference Series.  1501 (1), 012012 (2020).