Climate-related variables may not improve monthly scale rainfall predictions by artificial neural networks for the metropolitan region of Belo Horizonte, Brazil

  • Mateus Alexandre da Silva Departamento de Recursos Hídricos. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
  • Marina Neves Merlo Departamento de Recursos Hídricos. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
  • Michael Silveira Thebaldi Departamento de Recursos Hídricos. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
  • Danton Diego Ferreira Departamento de Automática. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
  • Felipe Schwerz Departamento de Engenharia Agrícola. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
  • Fábio Ponciano de Deus Departamento de Recursos Hídricos. Universidade Federal de Lavras (UFLA), Trevo Rotatório Professor Edmir Sá Santos, s/n, CEP: 37203-202, Lavras, MG, Brazil.
DOI: https://doi.org/10.4136/ambi-agua.2879

Abstract

Artificial neural networks (ANNs) may experience problems due to insufficient or uninformative predictors, and these problems are common for complex predictions such as those for rainfall. However, some studies point to the use of climate variables and anomalies as predictors to make the forecast more accurate. This research aimed to predict the monthly rainfall, one month in advance, in four municipalities of the metropolitan region of Belo Horizonte using an ANN trained with different climate variables; additionally, it aimed to indicate the suitability of such variables as inputs to these models. The models were developed using the MATLAB® software Version R2011a using the NNTOOL toolbox. The ANNs were trained by the multilayer perceptron architecture and the feedforward and backpropagation algorithm using two combinations of input data, with two and six variables, and one combination of input data with the three most correlated variables to observed rainfall from 1970 to 1999 to predict the rainfall from 2000 to 2009. The climate variable most correlated with the rainfall of the following month was the average compensated temperature. Even when using the variables most correlated with precipitation as predictors (0.66 ≤ nt index ≤ 1.26), there was no notable improvement in the predictive capacity of the models when compared to those that did not use climate variables as predictors (0.55 ≤ nt index ≤ 0.80).

Keywords: artificial intelligence, ENSO, hydrological modelling.


Published
17/03/2023
Issue
Vol. 18 (2023)
Section
Papers

Authors maintain the copyrights for their work. However, they grant rights of first publication to Ambiente e Agua - An Interdisciplinary Journal of Applied Science. In compensation, the journal can transfer the copyrights, allowing non-commercial use of the article including the right of sending the article to other data bases or publication media. The journal uses the CC BY 4.0 license"