This is a Preprint and has not been peer reviewed. This is version 4 of this Preprint.
This is a Preprint and has not been peer reviewed. This is version 4 of this Preprint.
This article presents a novel data-driven approach for studying long-term temporal rainfall pattern over the central highlands of West Papua, Indonesia. Using wavelet transforms we found indications of negative temporal relationship of El Niño - Southern Oscillation (ENSO) and 12-month Standarized Precipitation Index (SPI-12). Based on this causal relationship, we perform dynamic causality modeling using the Nonlinear Autoregressive with Exogenous input (NARX) model to predict SPI-12 using the Multivariate ENSO Index (MEI) as an attribute variable. As a result, this dynamic neural network model is able to capture common features in the SPI-12 time series. This study has a profound impact for the future development of data-driven precipitation models for areas with complex topography in Indonesian Maritime Continent (IMC).
https://doi.org/10.31223/X50K7X
Physical Sciences and Mathematics
ENSO, NARX, SPI, wavelet transform
Published: 2021-04-06 04:22
Last Updated: 2021-04-09 10:07
CC BY Attribution 4.0 International
Conflict of interest statement:
None
Data Availability (Reason not available):
https://github.com/sandyherho/tsHydrochWP
There are no comments or no comments have been made public for this article.