Affordable Access

Statistic Approach versus Artificial Intelligence for Rainfall Prediction Based on Data Series

Authors
Publication Date
Keywords
  • Rain Prediction
  • Arima
  • Astar
  • Ga-Nn
Disciplines
  • Computer Science

Abstract

This paper proposed a new idea in comparing two common predictors i.e. the statistic method and artificial intelligence (AI) for rainfall prediction using empirical data series. The statistic method uses Auto- Regressive Integrated Moving (ARIMA) and Adaptive Splines Threshold Autoregressive (ASTAR), most favorable statistic tools, while in the AI, combination of Genetic Algorithm-Neural Network (GA-NN) is chosen. The results show that ASTAR gives best prediction compare to others, in term of root mean square (RMSE) and following trend between prediction and actual.

There are no comments yet on this publication. Be the first to share your thoughts.