Comparison of neural networks and genetic algorithms to determine missing precipitation data (Case study: the city of Sari)

• Mahdavi, Ali ^[1] ; Najarchi, Mohsen ^[1] ; Hazaveie, Emadoddin ^[1] ; Mirhosayni Hazave, Seyed Mohammad ^[1] ; Mahdai Najafizadeh, Seyed Mohammad ^[1]
  1. [1] Islamic Azad University

     Islamic Azad University

     Irán

     
• Localización: Revista de la Universidad del Zulia, ISSN-e 2665-0428, ISSN 0041-8811, Vol. 11, Nº. 29, 2020 (Ejemplar dedicado a: Revista de la Universidad del Zulia, Número 29, Ciencias del Agro, Ingeniería y Tecnología), págs. 114-128
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • Neural networks and genetic programming in the investigation of new methods for predicting rainfall in the catchment area of the city of Sari. Various methods are used for prediction, such as the time series model, artificial neural networks, fuzzy logic, fuzzy Nero, and genetic programming. Results based on statistical indicators of root mean square error and correlation coefficient were studied. The results of the optimal model of genetic programming were compared, the correlation coefficients and the root mean square error 0.973 and 0.034 respectively for training, and 0.964 and 0.057 respectively for the optimal neural network model. Genetic programming has been more accurate than artificial neural networks and is recommended as a good way to accurately predict.