APLIKASI METODE ENSEMBLE MEAN UNTUK MENINGKATKAN RELIABILITAS PREDIKSI HyBMG
DOI:
https://doi.org/10.31172/jmg.v17i1.381Keywords:
Ensemble Mean, curah hujan, TRMM, PrediksiAbstract
Tingginya variasi curah hujan di Indonesia mengakibatkan sulit untuk menentukan model prakiraan iklim yang memiliki validitas dan reliabilitas terbaik. Penelitian ini dilakukan untuk mendapatkan model prakiraan iklim dengan akurasi yang lebih baik dengan menggunakan metode ensemble mean. Metode ensemble mean menggabungkan hasil prediksi dari empat model prakiraan iklim berbasis statistik yang terintegrasi ke dalam software HyBMG, yaitu ARIMA, ANFIS, Wavelet ANFIS, dan Wavelet ARIMA. Berdasarkan hasil uji coba terhadap data curah hujan dari tahun 2003-2012, ensemble mean dapat meningkatkan performa dari hasil prakiraan iklim dengan single method; hasil prakiraan iklim untuk metode ARIMA dapat meningkat hingga 44.4%, ANFIS 43.4%, Wavelet ARIMA 55.6%, dan Wavelet ANFIS hingga 58.6%.
The high rainfall variability in Indonesia makes it difficult to determine the climate forecast models that have the best reliability and validity. This study was conducted to obtain climate forecasting model with better accuracy using the ensemble mean. This method combines prediction results from four statistical climate models integrated within the HyBMG software, i.e. ARIMA, ANFIS, ANFIS Wavelet and Wavelet ARIMA. Based on test results of the 2003-2012 rainfall data, the ensemble mean method is proven to improve the performance of climate forecasts results with only one single method; for ARIMA the improvement is up to 44.4%, ANFIS 43.4%, ARIMA Wavelet 55.6%, and Wavelet ANFIS 58.6%.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2016 Jurnal Meteorologi dan Geofisika
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.