Hybrid System for Forecasting Meteorological Time Series in Penedo, Alagoas

• Elmo Araújo Filho UFAL
• José Lucas Bispo dos Santos UFAL
• Marília G. F. de M. Oliveira UFRPE
• Augusto C. F. de M. Oliveira UPE
• Gustavo H. F. de M. Oliveira UFAL

DOI: https://doi.org/10.5753/eniac.2024.243676

Abstract

Weather forecasts are important for various sectors of society, impacting the adoption of strategies to improve agriculture and the management of natural disasters. This study focuses on this context, specifically on forecasting climate time series in the city of Penedo, Alagoas, due to the complex characteristics of its climate. As a method, a hybrid system was proposed that combines linear and non-linear forecasting models. The results demonstrated that the system achieved the best performance in six out of nine databases tested, standing out as a robust solution for climate prediction.

Keywords: hybrid system, time series forecasting, meteorological time series

References

Aly, H. H. (2020). An intelligent hybrid model of neuro wavelet, time series and recurrent kalman filter for wind speed forecasting. Sustainable Energy Technologies and Assessments, 41:100802.

BARROS, A. H. C., de Araújo Filho, J., Da Silva, A., and SANTIAGO, G. A. C. (2012). Climatologia do estado de alagoas. .

Bochenek, B. and Ustrnul, Z. (2022). Machine learning in weather prediction and climate analyses—applications and perspectives. Atmosphere, 13(2):180.

de Mattos Neto, P. S., de Oliveira, J. F. L., Júnior, D. S. d. O. S., Siqueira, H. V., Marinho, M. H. D. N., and Madeiro, F. (2020). A hybrid nonlinear combination system for monthly wind speed forecasting. IEEE Access, 8:191365–191377.

de Oliveira, J. F., Silva, E. G., and de Mattos Neto, P. S. (2021). A hybrid system based on dynamic selection for time series forecasting. IEEE Transactions on Neural Networks and Learning Systems, 33(8):3251–3263.

de Oliveira, J. F. L. and Ludermir, T. B. (2014). A hybrid evolutionary system for parameter optimization and lag selection in time series forecasting. In 2014 Brazilian Conference on Intelligent Systems, pages 73–78. IEEE.

Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine learning research, 7(Jan):1–30.

Faruk, D. Ö. (2010). A hybrid neural network and arima model for water quality time series prediction. Engineering applications of artificial intelligence, 23(4):586–594.

Figueiredo Filho, D. B. and Silva Júnior, J. A. (2009). Desvendando os mistérios do coeficiente de correlação de pearson (r). Revista Política Hoje, 18(1):115–146.

Freitas, C. (2023). Dataset e corpus. Processamento de linguagem natural: conceitos, técnicas e aplicações em português.

Han, S., Xu, J., Yan, M., and Liu, Z. (2022). Using multiple linear regression and bp neural network to predict critical meteorological conditions of expressway bridge pavement icing. Plos one, 17(2):e0263539.

Herbold, S. (2020). Autorank: A python package for automated ranking of classifiers. Journal of Open Source Software, 5(48):2173.

Morettin, P. A. and Toloi, C. M. d. C. (1985). Previsão de séries temporais. .

SILVA, H. B. d. (2018). Técnicas para redução de dimensionalidade de séries temporais e detecção de velocidades extremas do vento para geração eólica. Master’s thesis, Universidade Federal de Pernambuco.

Soares, A. C. et al. (2022). Análise de séries temporais com uso de redes neurais artificiais em dados meteorológicos para previsão de chuva e eventos climáticos severos. .

Zhang, G. P. (2003). Time series forecasting using a hybrid arima and neural network model. Neurocomputing, 50:159–175.