Artificial neural networks applied to time series for flood prediction

• Laleska A. F. Mesquita Universidade de São Paulo
• Caetano M. Ranieri Universidade de São Paulo
• Jó Ueyama Universidade de São Paulo

DOI: https://doi.org/10.5753/eniac.2023.234355

Resumo

Extreme hydrological events and lack of urban planning can generate climate-related disasters. Several fields of study, including artificial intelligence, contribute to mitigate this problem and develop preventive solutions. This study focuses on flood forecasting the Xingu River using time series data. The main approach is to standardize the pure data from different stations using quantiles, and thus generate recurrence plots for the time series and then transform them into two-dimensional representations to be applied in the convolutional neural network model. The combination of recurrence plot with CNN provided data metrics in the prediction test with superior performance compared to the algorithms models implemented as LSTM, RNN.

Palavras-chave: flood prediction, neural networks, recurrence plot, time series

Referências

Aurelien, G. (2019). Mãos à Obra: Aprendizado de Máquina com Scikit-Lear & Tensor-Flow, volume 1. ”O’Reilly Media, Inc”, Rio de Janeiro.

Babichev, S., Lytvynenko, V., Wójcik, W., and Vyshemyrskaya, S. (2020). Lecture notes in computational intelligence and decision making. Poland.

Brasil (2018). Confederação nacional de municípios. Decretações de anormalidades causadas por desastres nos Municípios Brasileiros.

Chen, C., Hui, Q., Xie, W., Wan, S., Zhou, Y., and Pei, Q. (2021). Convolutional neural networks for forecasting flood process in internet-of-things enabled smart city. Computer Networks, 186:107744.

Dimitriev D, Saperova EV, D. A. K. Y. (2020). Recurrence quantification analysis of heart rate during mental arithmetic stress in young females. Front Physiol, 11:1–5.

Ebbehoj, A., Thunbo, M. , Andersen, O. E., Glindtvad, M. V., and Hulman, A. (2022). Transfer learning for non-image data in clinical research: A scoping review. PLOS Digital Health, 1(2):1–22.

Espinoza, J.-C., Marengo, J. A., Schongart, J., and Jimenez, J. C. (2022). The new historical flood of 2021 in the amazon river compared to major floods of the 21st century: Atmospheric features in the context of the intensification of floods. Weather and Climate Extremes, 35:100406.

Fathian, F., Mehdizadeh, S., Sales, A. K., and Safari, M. J. S. (2019). Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models. Journal of Hydrology, 575:1200–1213.

Fragkou, A., Charakopoulos, A., Karakasidis, T., and Liakopoulos, A. (2022). Non-linear analysis of river system dynamics using recurrence quantification analysis. Applied-Math, 2(1):1–15.

Guha, S., Jana, R. K., and Sanyal, M. K. (2022). Artificial neural network approaches for disaster management: A literature review. International Journal of Disaster Risk Reduction, 81:103276.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.

Hu, C., Wu, Q., Li, H., Jian, S., Li, N., and Lou, Z. (2018). Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water, 10(11):1543.

Iman, M., Arabnia, H. R., and Rasheed, K. (2023). A review of deep transfer learning and recent advancements. Technologies, 11(2).

Kai Feng, Z. and Jing Niu, W. (2021). Hybrid artificial neural network and cooperation search algorithm for nonlinear river flow time series forecasting in humid and semi-humid regions. Knowledge Based Systems, 211:49–53.

Kimura, N., Yoshinaga, I., Sekijima, K., Azechi, I., and Baba, D. (2019). Convolutional neural network coupled with a transfer-learning approach for time-series flood predictions. Water, 12(1):96.

Kirichenko, L., Zinchenko, P., and Radivilova, T. (2021). Classification of Time Realizations Using Machine Learning Recognition of Recurrence Plots, pages 687–696.

’L’heureux, A., Grolinger, K., and Capretz, M. A. M. (2017). Machine learning with big data: Challenges and approaches. IEEE Access, 5(2):7776 – 7797.

Maddala, G. S. and Lahiri, K. (2009). Introduction to Econometrics, volume 4. John Wiley Sons Ltd, UK.

Marwan, N., Romano, M. C., Thiel, M., and Kurths, J. (2007). Recurrence plots for the analysis of complex systems. Physics Reports, 438(5-6):237–329.

Packard, N. H., Crutchfield, J. P., Farmer, J. D., and Shaw, R. S. (1980). Geometry from a time series. Phys. Rev. Lett., 45:712–716.

Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.