Non-Linear Spatio-Temporal Input Selection for Rainfall Forecasting Using Recurrent Neural Networks

Ahmad Saikhu, Agus Zainal Arifin, Chastine Fatichah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Rainfall is an important component of the hydrologic cycle and is used for planning in various fields. Based on the White test it is known that some weather variables correlate non-linearly to rainfall. Meanwhile, from correlation testing it is known that the observed weather data from weather stations in a region are mutually correlated. Therefore, statistical modeling using autocorrelation and cross correlation is less appropriate because the assumption of linear correlation is not fulfilled. In this paper, a new framework is proposed for non-linear feature extraction using detrended partial crosscorrelation analysis and predictor input selection using symmetrical uncertainty as a way to determine optimal nonlinear input features in rainfall forecasting. Forecasting was performed simultaneously for 3 weather station locations in addition to taking into account the dependencies of observation time. This is called a non-linear spatio-Temporal recurrent neural network. The result of the forecasting method shows that the model performed better than univariate/multivariate time series forecasting and a recurrent neural network without input selection.

Original languageEnglish
Title of host publicationProceeding - 2018 International Seminar on Intelligent Technology and Its Application, ISITIA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages351-356
Number of pages6
ISBN (Electronic)9781538676547
DOIs
Publication statusPublished - 2 Jul 2018
Event2018 International Seminar on Intelligent Technology and Its Application, ISITIA 2018 - Bali, Indonesia
Duration: 30 Aug 201831 Aug 2018

Publication series

NameProceeding - 2018 International Seminar on Intelligent Technology and Its Application, ISITIA 2018

Conference

Conference2018 International Seminar on Intelligent Technology and Its Application, ISITIA 2018
Country/TerritoryIndonesia
CityBali
Period30/08/1831/08/18

Keywords

  • forecasting
  • rainfall
  • recurrent neural networks
  • spatiotemporal

Fingerprint

Dive into the research topics of 'Non-Linear Spatio-Temporal Input Selection for Rainfall Forecasting Using Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this