Implementasi Jaringan Syaraf Tiruan Recurrent Menggunakan Gradient Descent Adaptive Learning Rate and Momentum Untuk Pendugaan Curah Hujan

Authors

  • Afan Galih Salman Bina Nusantara University
  • Yen Lina Prasetio Bina Nusantara University

DOI:

https://doi.org/10.21512/comtech.v2i1.2707

Keywords:

artificial neural network, coefficient deteminationi (R2), root mean square error (RMSE), gradient descent adaptive learning rate and momentum, ENSO

Abstract

The artificial neural network (ANN) technology in rainfall prediction can be done using the learning approach. The ANN prediction accuracy is measured by the determination coefficient (R2) and root mean square error (RMSE). This research implements Elman’s Recurrent ANN which is heuristically optimized based on el-nino southern oscilation (ENSO) variables: wind, southern oscillation index (SOI), sea surface temperatur (SST) dan outgoing long wave radiation (OLR) to forecast regional monthly rainfall in Bongan Bali. The heuristic learning optimization done is basically a performance development of standard gradient descent learning algorithm into training algorithms: gradient descent momentum and adaptive learning rate. The patterns of input data affect the performance of Recurrent Elman neural network in estimation process. The first data group that is 75% training data and 25% testing data produce the maximum R2 leap 74,6% while the second data group that is 50% training data and 50% testing data produce the maximum R2 leap 49,8%.


Dimensions

Plum Analytics

References

Apriyanti, Novi. (2005). Optimasi Jaringan Syaraf Tiruan dengan Algoritma Genetika untuk Peramalan Curah Hujan. Bogor: Jurusan Ilmu Komputer FMIPA IPB.

Coulibaly, Rasmussen & Bobee. (2000). A Recurrent Neural Networks ApproachUsing Indices of Low Frequency Climatic Variability to Forecast Regional Annual Runoff. Hydrological Processes, 14, 2755-2777. Diakses dari http://www.science.mcmaster.ca/~geo/faculty/coulibaly/WRHML/Publications/Publications/Coulibaly_al_HP_14.pdf.

Effendy, Sobri. (2001). Urgensi Prediksi Cuaca dan Iklim di Bursa Komoditas Unggulan Pertanian. Makalah Falsafah Sains Program Pasca Sarjana/S3. Bogor: Institut Pertanian Bogor.

Fitriadi. (2004). Kombinasi Model Regresi Komponen Utama dan Arima dalam Statistical Downscaling. Bogor: Jurusan Ilmu Komputer FMIPA IPB.

Kristanto, Andri. (2004). Jaringan Syaraf Tiruan: Konsep Dasar, Algoritma dan Aplikasi. Yogyakarta: Penerbit Gava Media.

Kusumadewi, Sri. (2004). Membangun Jaringan Syaraf Tiruan menggunakan Matlab dan Excell Link. Yogyakarta: Penerbit Graha Ilmu.

Lakshmi, S. S., Tiwari, R.K. & Somvanshi, V.K. (2003). Prediction of Indian Rainfall Index (IRF) using the ENSO variability and Sunspot Cycles-An Artificial Neural Network Approach. Indian Geophysical Union, 7 (04), 173-181.

Normakristagaluh, P. (2004). Penerapan Jaringan Syaraf Tiruan untuk Peramalan Curah Hujan dalam Statistical Downscaling. Bogor: Jurusan Ilmu Komputer FMIPA IPB.

Walpole, E.R. (1995). Pengantar Statistika, (edisi ke-3). Jakarta: PT Gramedia Pustaka Utama.

Workshop JNB. (2002). Aplikasi Jaringan Neural Buatan Pada Pattern Recognition. Depok: Fakultas Ilmu Komputer Universitas Indonesia.

Yusmen, Dedi. (1998). Pengaruh ENSO terhadap Pola Curah, Hujan di Wilayah DAS Brantas Selatan-Jawa Timur. (Tugas Akhir). Bandung: Jurusan Geofisika dan Meteorologi, FMIPA ITB.

Downloads

Published

2011-06-01

Issue

Section

Articles
Abstract 534  .
PDF downloaded 578  .