MODEL DEBIT DAERAH ALIRAN SUNGAI JANGKOK BERDASARKAN HASIL PREDIKSI MODEL STATISTICAL DOWNSCALING NONPARAMETRIK KERNEL CURAH HUJAN DAN TEMPERATUR

*Mustika Hadijati  -  Program Studi Matematika, FMIPA, Universitas Mataram, Indonesia
Irwansyah Irwansyah  -  Program Studi Matematika, FMIPA, Universitas Mataram, Indonesia
Received: 7 Nov 2018; Published: 30 Dec 2019.
Open Access Copyright (c) 2019 MEDIA STATISTIKA
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Citation Format:
Article Info
Section: Articles
Language: EN
Full Text:
Statistics: 90 123
Abstract
River water discharge is important information for water resources management planning, so it is necessary to develop river water discharge model as basis of its predictions. In order to get the result of predictions of river water discharge with high accuracy, it is developed a model of river water discharge based on the predictions of local climate (local rainfall and temperature) that are influenced by global climate conditions. Prediction of local climate is based on the Kernel nonparametric statistical downscaling model by utilizing GCM data. GCM data is a high dimensional global data, so data pre-processing is needed to reduce data dimension. It is done by CART algorithm. Statistical downscaling model is used to predict local rainfall and temperature. The prediction results are quite good with relatively small RMSE value. They are used to develop model of river water discharge. Modeling river water discharge is carried out using the Kernel nonparametric approach. The model of river water discharge produced is quite good because it can be used to predict river water discharge with relatively small RMSE.
Keywords
Statistical Downscaling; GCM; CART; Kernel Nonparametric

Article Metrics: