A novel approach for prediction of daily streamflow discharge data using correlation based feature selection and random forest method

Abstract

The accurate methods for the forecasting of hydrological characteristics are significantly important for water resource management and environmental aspects. In this study, a novel approach for daily streamflow discharge data forecasting is proposed. Streamflow discharge, temperature, and precipitation data were used for feature extraction which were systematically employed for forecasting studies. While the correlation-based feature selection (CFS) was used for feature selection, Random Forest (RF) model is employed for forecasting of following 7 days. Moreover, an accuracy comparison between the RF model and CFS-RF model is drawn by using streamflow discharge data. Acquired results confirmed the accuracy of CFS-RF model for both, middle and extended forecasting times compared to RF model which had similar accuracy values for the closer forecasting times. Moreover, the CFS-RF model proved to be much robust for extended forecasting durations.

Keywords

• Correlation-based feature selection
• Forecasting
• Random Forest
• Streamflow discharge

References

1. 1. Sharma, P. and D. Machiwal, Advances in streamflow forecasting: from traditional to modern approaches. 2021, USA: Elsevier, Inc.
2. 2. Peters, R.L., The greenhouse effect and nature reserves. Bioscience, 1985. 35(11): p.707-717.
3. 3. Rojas, I., O. Valenzuela, F. Roja, A. Guillén, L.J. Herrera, H. Pomares, L. Marquez, and M. Pasadas, Soft-computing techniques and ARMA model for time series prediction. Neurocomputing, 2008. 71(4-6): p. 519-537.
4. 4. Khandelwal, I., R. Adhikari, and G. Verma, Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science, 2015. 48: p. 173-179.
5. 5. Yaseen, Z. M., A. El-Shafie, O. Jaafar, H.A. Afan, and K.N. Sayl., Artificial intelligence based models for stream-flow forecasting: 2000–2015. Journal of Hydrology, 2015. 530: p. 829-844.
6. 6. Kisi, O., L. Latifoğlu, and F. Latifoğlu, Investigation of empirical mode decomposition in forecasting of hydrological time series. Water Resources Management, 2014. 28(12): p. 4045-4057.
7. 7. Latifoğlu, L., O. Kişi, and F. Latifoğlu, Importance of hybrid models for forecasting of hydrological variable. Neural Computing and Applications, 2015. 26(7): p. 1669-1680.
8. 8. Meshram, S.G., C. Meshram, C.A.G. Santos, B. Benzougagh, and K.M. Khedher, Streamflow prediction based on artificial intelligence techniques. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2021. p. 1-11.

9. 9. Nourani, V., N.J. Paknezhad, and H. Tanaka, Prediction interval estimation methods for artificial neural network (ANN)-based modeling of the hydro-climatic processes, a Review. Sustainability, 2021. 13(4): p. 1633.
10. 10. Adnan, R. M., X. Yuan, O. Kisi, and Y. Yuan, Streamflow forecasting using artificial neural network and support vector machine models. American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), 2017. 29(1): p. 286-294.
11. 11. Saraiva, S. V., F. de Oliveira Carvalho, C.A.G. Santos, L.C. Barreto, and P.K.D.M.M Freire, Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping. Applied Soft Computing, 2021. 102: p.107081.
12. 12. Pham, L. T., L. Luo, and A. Finley, Evaluation of random forests for short-term daily streamflow forecasting in rainfall-and snowmelt-driven watersheds. Hydrology and Earth System Sciences, 2021. 25(6): p. 2997-3015.
13. 13. Li, X., J. Sha, and Z.L. Wang, Comparison of daily streamflow discharge forecasts using extreme learning machines and the random forest method. Hydrological Sciences Journal, 2019. 64(15): p. 1857-1866.
14. 14. Lahouar A. and J.B.H. Slama, Day-ahead load forecast using random forest and expert input selection. Energy Conversion and Management, 2015. 103: p. 1040-1051.
15. 15. Huo, J., T. Shi and J. Chang., Comparison of random forest and SVM for electrical short-term load forecast with different data sources, in 7th IEEE International conference on software engineering and service science (ICSESS), 2016, Beijing: China. p. 1077-1080.
16. 16. Canopex hydrometeorological watershed database. [cited 2020 1 December]; Available from: http://canopex.etsmtl.net/
17. 17. Arsenault, R., R. Bazile, C. Dallaire-Ouellet, and F. Brissette, CANOPEX: A Canadian hydrometeorological watershed database. Hydrological Processes, 2016. 30(15): p. 2734-2736.
18. 18. Gopika, N. and A. Kowshalaya M.E, Correlation based feature selection algorithm for machine learning, in 3rd International Conference on Communication and Electronics Systems (ICCES), 2018, Coimbatore: India. p. 692-695.
19. 19. Breiman L., Random forests. Machine Learning, 2001, 45: p. 5–32.
20. 20. Liu Y., Y. Wang, and J. Zhang, New machine learning algorithm: Random forest, in International Conference on Information Computing and Applications, 2012, Chengde: China. p. 246-252.
21. 21. Samanataray, S., and A. Sahoo, A Comparative study on prediction of monthly streamflow using hybrid ANFIS-PSO approaches. KSCE Journal of Civil Engineering, 2021. 25(10): p. 4032-4043.
22. 22. Ali, M.H. and I. Abustan, A new novel index for evaluating model performance. Journal of Natural Resources and Development, 2014. 4: p. 1-9.
23. 23. Kumbur, H., V. Yamaçlı, and A. Küçükbahar, Mersin province water projections and water information and management system: Erdemli district model. International Advanced Researches and Engineering Journal, 2018. 2(3): p. 261-266.