Rainfall intensity forecast using ensemble artificial neural network and data fusion for tropical climate

Noor Zuraidin, Mohd Safar and Ndzi, David and Hairulnizam, Mahdin and Ku Muhammad Naim, Ku Khalif (2020) Rainfall intensity forecast using ensemble artificial neural network and data fusion for tropical climate. In: Recent Advances on Soft Computing and Data Mining. Proceedings of the Fourth International Conference on Soft Computing and Data Mining (SCDM 2020), 22-23 January 2020 , Melaka, Malaysia. pp. 241-250., 978. ISBN 978-3-030-36056-6

[img]
Preview
Pdf
Rainfall intensity forecast using ensemble artificial neural network .pdf

Download (267kB) | Preview

Abstract

This paper proposes an ensemble method based on neural network architecture and stacking generalization. The objective is to develop a novel ensemble of Artificial Neural Network models with back propagation network and dynamic Recurrent Neural Network to improve prediction accuracy. Historical meteorological parameters and rainfall intensity have been used for predicting the rainfall intensity forecast. Hourly predicted rainfall intensity forecast are compared and analyzed for all models. The result shows that for 1 h of prediction, the neural network ensemble forecast model returns 94% of precision value. The study achieves that the ensemble neural network model shows significant improvement in prediction performance as compared to the individual neural network model.

Item Type: Conference or Workshop Item (Lecture)
Additional Information: Part of the Advances in Intelligent Systems and Computing book series
Uncontrolled Keywords: Rainfall forecasting; Artificial neural network; Recurrent neural network; Expert system; Ensemble learning; Tropical climate
Subjects: Q Science > QA Mathematics
T Technology > T Technology (General)
Faculty/Division: Faculty of Industrial Sciences And Technology
Depositing User: Mrs Norsaini Abdul Samat
Date Deposited: 16 Apr 2020 13:25
Last Modified: 16 Apr 2020 13:25
URI: http://umpir.ump.edu.my/id/eprint/28130
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item