Perbandingan JST Metode Backpropagation dan Metode Radial Basis dalam Memprediksi Curah Hujan Harian Bandara Internasional Minangkabau

Authors

  • Nursakinah Aulia Fitri Laboratorium Komputer, Jurusan Fisika Fakultas Matematika Ilmu Pengetahuan Alam, Universitas Andalas
  • Imam Taufiq Laboratorium Komputer, Jurusan Fisika Fakultas Matematika Ilmu Pengetahuan Alam, Universitas Andalas

DOI:

https://doi.org/10.25077/jfu.9.2.217-223.2020

Abstract

Telah dilakukan prediksi curah hujan harian menggunakan jaringan syaraf tiruan dengan beberapa fungsi pelatihan backpropagation dan radial basis. Penelitian ini menggunakan data curah hujan harian dari Badan Meteorologi Klimatologi dan Geofisika Stamet Kelas II Bandara Internasional Minangkabau Padang Pariaman dari tahun 2008 sampai tahun 2018. Penelitian ini bertujuan untuk membandingkan kinerja prediksi curah hujan jaringan syaraf tiruan Backpropagation dan Radial Basis dan menentukan arsitektur jaringan syaraf tiruan terbaik untuk prediksi curah hujan di Bandara Internasional Minangkabau. Untuk metode backpropagation optimisasi dilakukan terhadap jumlah lapisan tersembunyi, jumlah neuron pada lapisan tersembunyi, fungsi transfer, fungsi latih dan jumlah data masukan pada data latih. Untuk metode  radial basis optimisasi dilakukan pada jumlah neuron lapisan tersembunyi, jumlah data masukan pada data latih dan nilai spread. Dari penelitian ini ditemukan hasil terbaik untuk metode backpropagationadalah dengan menggunakan fungsi latih trainlm dan arsitektur (60-70-6-1) dengan tingkat ketepatan prediksi 86,4876%. Untuk metode radial basis hasil terbaiknya diperoleh nilai spread 0,01 dengan arsitektur (60-120-1) dan tingkat ketepatan prediksi 95,3107%. Dengan demikian dapat disimpulkan metode paling bagus untuk prediksi curah hujan harian pada daerah Bandara Internasional Minangkabau adalah metode radial basis.

 

Research on daily rainfall predictions have made by using artificial neural networks with some backpropagation and radial basis training functions. This study used daily rainfall data from the Meteorology Climatology and Geophysics Agency in Class II of the Minangkabau International Airport Padang Pariaman from 2008 to 2018. The purposes of the study is to compare the predicted performance of rainfall in Backpropagation and Radial Neural Networks and determine which one the best artificial neural network architecture for rainfall predictions at Minangkabau International Airport is. For the backpropagation method, optimization is performed on the number of hidden layers, the number of neurons in the hidden layer, the transfer function, the training function and the amount of input data on the training data. For the radial basis optimization method is performed on the number of hidden layer neurons, the amount of input data on the training data and the spread value. From this study found the best results for the backpropagation method were obtained with trainlm and architectural training functions (60-70-6-1) with a prediction accuracy level of 86.4876%. The best results for the radial basis method by value of a spread is 0.01 with architecture (60-120-1) and a predictive accuracy rate of 95.3107%. Thus the best method for the prediction of daily rainfall in the area of the Minangkabau International Airport is the radial basis method.

References

Halim, dan Wibisono, A.M., Analisis Intensitas Curah Hujan Wilayah Bandung Pada Awal 2010, JurnalMeteorologi dan Geofisika, 12(2), hal. 229-230, 2000.

Iwan, dan Sugeng., Pemodelan Curah Hujan-Limpasan Menggunakan Artificial Neural Network (ANN) dengan Metode Backpropagation, Jurnal Teknik Sipil, 12(4), hal. 35-36, Subang, 2014.

Indrabayu, dan Nadjamudin., Prediksi Curah Hujan dengan Jaringan Saraf Tiruan, Jurnal Teknik Sipil, 6(1), hal. 61-62, Makasar, 2012.

Jayanti, Rahadi, D.S, dan Onny., Perbaikan Metode Prakiraan Cuaca Bandara Abdulrahman Saleh dengan Algoritma Neural Network Backpropagation, Jurnal EECCIS, 7(1), hal. 65-66. Malang, 2013.

Minarti, dan Iman, S.B., Prediksi Terjadinya Hujan Harian dengan Metode Jariingan Syraf Tiruan di Stasiun Meteorologi Bandara Minangkabau, Jurnal Poli Rekayasa, 6(2), hal. 237-238, 2011.

Siang, J,J., Jaringan Syaraf Tiruan, Andi Offset, Yogyakarta, 2009.

Vivekanandan., Modelling of Annual Extreme Rainfall, Temperature and Wind Speed Using OSA of EV1 and EV2 Distributions, International Journal of Innovative Research in Computer Science & Technology (IJIRCS), 3(4), hal. 57-59, Maharashtra, 2015.

Downloads

Published

2020-11-09

How to Cite

Fitri, N. A., & Taufiq, I. (2020). Perbandingan JST Metode Backpropagation dan Metode Radial Basis dalam Memprediksi Curah Hujan Harian Bandara Internasional Minangkabau. Jurnal Fisika Unand, 9(2), 217–223. https://doi.org/10.25077/jfu.9.2.217-223.2020

Issue

Vol. 9 No. 2 (2020)

Section

Articles

License

Copyright (c) 2020 Nursakinah Aulia Fitri, Imam Taufiq

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Please find the rights and licenses in JFU (Jurnal Fisika Unand).

1. License

The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial 4.0 International License.

2. Authors Warranties

The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).

3. User Rights

JFU's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, JFU permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and JFU on distributing works in the journal.

4. Rights of Authors

Authors retain the following rights:

  • Copyright, and other proprietary rights relating to the article, such as patent rights,
  • The right to use the substance of the article in future own works, including lectures and books,
  • The right to reproduce the article for own purposes, provided the copies are not offered for sale,
  • The right to self-archive the article.

5. Co-Authorship

If the article was jointly prepared by other authors, the signatory of this form warrants that he/she has been authorized by all co-authors to sign this agreement on their behalf, and agrees to inform his/her co-authors of the terms of this agreement.

6. Termination

This agreement can be terminated by the author or JFU upon two months notice where the other party has materially breached this agreement and failed to remedy such breach within a month of being given the terminating partys notice requesting such breach to be remedied. No breach or violation of this agreement will cause this agreement or any license granted in it to terminate automatically or affect the definition of JFU.

7. Royalties

This agreement entitles the author to no royalties or other fees. To such extent as legally permissible, the author waives his or her right to collect royalties relative to the article in respect of any use of the article by JFU or its sublicensee.

8. Miscellaneous

JFU will publish the article (or have it published) in the journal if the articles editorial process is successfully completed and JFU or its sublicensee has become obligated to have the article published. JFU may conform the article to a style of punctuation, spelling, capitalization, referencing and usage that it deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers.