Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Komunikasi Fisika Indonesia
Ester Kristianti
Universitas Jambi
Earth & Planetary Sciences Electrical & Electronics Engineering Energy Materials Science & Nanotechnology Physics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
ANALISIS PREDIKSI CURAH HUJAN MENGGUNAKAN METODE JARINGAN SARAF TIRUAN BACKPROPAGATION DI KABUPATEN MUARO JAMBI Rustan Rustan; Tika Restianingsih; Ester Kristianti
Komunikasi Fisika Indonesia Vol 20, No 1 (2023)
Publisher : Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31258/jkfi.20.1.31-38

Abstract

Rainfall is one of the important natural factors influencing flood and drought conditions, and directly affects regional water resources and agricultural production. In general, weather conditions in a place and time tend to vary, so information about weather conditions is needed through rainfall predictions. The prediction method used is the backpropagation artificial neural network (ANN) method which is arranged according to the learning algorithm that will be used. This study uses four stages, namely data collection, data preprocessing, data processing, and research data analysis. The secondary data used is rainfall from 2014-2022 in Muaro Jambi Regency. Based on the results of testing the number of neurons in the hidden layer, it shows that the more the number of neurons, the higher the error value generated. This is because the training function used is saturated. Where the training function used has parameters that can increase and decrease the value of the learning rate. Next, compare the predictions for 2022 between BMKG data and predictions for ANN backpropagation. Based on the analysis of predictions for 2022 for rainfall and humidity, an average accuracy of 97.82% is obtained. This shows that the result of the ANN method is quite good in predicting rainfall.
Co-Authors Rustan Tika Restianingsih