Daily streamflow forecasting for Paraíba do Sul river using machine learning methods with hydrologic inputs

• Yulia Gorodetskaya UFJF
• Leonardo Goliatt da Fonseca UFJF
• Gisele Goulart Tavares UFJF
• Celso Bandeira de Melo Ribeiro UFJF

DOI: https://doi.org/10.5753/eniac.2018.4413

Resumo

The Paraíba do Sul river flows through the most important industrial region of Brazil and its basin is characterized by conflicts of multiple uses of its water resources. The prediction of its natural flow has strategic value for water management in this basin. This research investigates the applicability of the two machine learning methods (Random Forest and Artificial Neural Networks) for daily streamflow forecasting of the Paraíba do Sul River at lead times of 1-7 days. The impact of fluviometric and pluviometric data from other basin sites on the quality of the forecast is also evaluated.

Referências

[Asadi et al. 2013] Asadi, S., Shahrabi, J., Abbaszadeh, P., and Tabanmehr, S. (2013). A new hybrid artificial neural networks for rainfall–runoff process modeling. Neurocomputing, 121:470–480.

[Bhagwat and Maity 2012] Bhagwat, P. P. and Maity, R. (2012). Multistep-ahead river flow prediction using ls-svr at daily scale. Journal of Water Resource and Protection, 4(07):528.

[Breiman 2001] Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.

[Carlisle et al. 2010] Carlisle, D. M., Falcone, J.,Wolock, D. M., Meador, M. R., and Norris, R. H. (2010). Predicting the natural flow regime: models for assessing hydrologica alteration in streams. River Research and Applications, 26(2):118–136.

[Chai and Draxler 2014] Chai, T. and Draxler, R. R. (2014). Root mean square error (rmse) or mean absolute error (mae)?–arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247–1250.

[da Silva et al. 2011] da Silva, A. N., Chaves, M. B., Coelho, F. A., and de Oliveira Carvalho, F. (2011). Previs˜ao de vaz˜oes diárias utilizando redes neurais na bacia do rio mundaú/al.

[Hastie et al. 2009] Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning - Data Mining, Inference, and Prediction. Springer, Verlag, New York, 2 edition.

[Haykin et al. 2009] Haykin, S. S., Haykin, S. S., Haykin, S. S., and Haykin, S. S. (2009). Neural networks and learning machines, volume 3. Pearson Upper Saddle River, NJ, USA:.

[Karimi et al. 2016] Karimi, S., Shiri, J., Kisi, O., and Shiri, A. A. (2016). Short-term and long-term streamflow prediction by using’wavelet–gene expression’programming approach. ISH Journal of Hydraulic Engineering, 22(2):148–162.

[Khair et al. 2017] Khair, A. F., Awang, M. K., Zakaraia, Z. A., and Mazlan, M. (2017). Daily streamflow prediction on time series forecasting. Journal of Theoretical and Applied Information Technology, 95(4):804.

[Kinga and Adam 2015] Kinga, D. and Adam, J. B. (2015). A method for stochastic optimization. In International Conference on Learning Representations (ICLR).

[Kohavi et al. 1995] Kohavi, R. et al. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai, volume 14, pages 1137–1145. Montreal, Canada.

[Legates and McCabe 1999] Legates, D. R. and McCabe, G. J. (1999). Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water resources research, 35(1):233–241.

[Li et al. 2016] Li, B., Yang, G., Wan, R., Dai, X., and Zhang, Y. (2016). Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the poyang lake in china. Hydrology Research, 47(S1):69–83.

[McKinney 2010] McKinney,W. (2010). Data structures for statistical computing in python. In van der Walt, S. and Millman, J., editors, Proceedings of the 9th Python in Science Conference, pages 51 – 56.

[Nair and Hinton 2010] Nair, V. and Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), pages 807–814.

[Patel and Ramachandran 2015] Patel, S. S. and Ramachandran, P. (2015). A comparison of machine learning techniques for modeling river flow time series: the case of upper cauvery river basin. Water resources management, 29(2):589–602.

[Pedregosa et al. 2011] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. Journal of machine learning research, 12(Oct):2825–2830.

[Povak et al. 2013] Povak, N. A., Hessburg, P. F., Reynolds, K. M., Sullivan, T. J., McDonnell, T. C., and Salter, R. B. (2013). Machine learning and hurdle models for improving regional predictions of stream water acid neutralizing capacity. Water Resources Research, 49(6):3531–3546.

[Rasouli et al. 2012] Rasouli, K., Hsieh,W.W., and Cannon, A. J. (2012). Daily streamflowforecasting by machine learning methods with weather and climate inputs. Journal of Hydrology, 414:284–293.

[Ribeiro et al. 2014] Ribeiro, F. M., Mendes, E. M., and Lemos, A. P. (2014). Sistema de previs˜ao de afluência utilizando árvore de regress˜ao linear evolutiva nebulosa. In Anais do XX Congresso Brasileiro de Automática.

[Shafaei and Kisi 2016] Shafaei, M. and Kisi, O. (2016). Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models. Neural Computing and Applications, 28(1):15–28.

[Shortridge et al. 2016] Shortridge, J. E., Guikema, S. D., and Zaitchik, B. F. (2016). Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds. Hydrology and Earth System Sciences, 20(7):2611.

[Wang et al. 2015] Wang, Z., Lai, C., Chen, X., Yang, B., Zhao, S., and Bai, X. (2015). Flood hazard risk assessment model based on random forest. Journal of Hydrology, 527:1130–1141.

[Waskom et al. 2017] Waskom, M., Botvinnik, O., O’Kane, D., Hobson, P., Lukauskas, S., Gemperline, D. C., Augspurger, T., Halchenko, Y., Cole, J. B., Warmenhoven, J., de Ruiter, J., Pye, C., Hoyer, S., Vanderplas, J., Villalba, S., Kunter, G., Quintero, E., Bachant, P., Martin, M., Meyer, K., Miles, A., Ram, Y., Yarkoni, T., Williams, M. L., Evans, C., Fitzgerald, C., Brian, Fonnesbeck, C., Lee, A., and Qalieh, A. (2017). mwaskom/seaborn: v0.8.1 (september 2017).

[Zhao et al. 2012] Zhao, T., Yang, D., Cai, X., and Cao, Y. (2012). Predict seasonal low flows in the upper yangtze river using random forests model. Journal of Hydroelectric Engineering, 3(005).