Rainfall Forecasting Using Backpropagation Neural Network
Rainfall already became vital observation object because it affects society life both in rural areas or urban areas. Because parameters to predict rainfall rates is very complex, using physics based model that need many parameters is not a good choice. Using alternative approach like time-series bas...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
University of Brawijaya
2017-11-01
|
Series: | JITeCS (Journal of Information Technology and Computer Science) |
Online Access: | http://jitecs.ub.ac.id/index.php/jitecs/article/view/9 |
_version_ | 1797242755612672000 |
---|---|
author | Andreas Nugroho Sihananto Wayan Firdaus Mahmudy |
author_facet | Andreas Nugroho Sihananto Wayan Firdaus Mahmudy |
author_sort | Andreas Nugroho Sihananto |
collection | DOAJ |
description | Rainfall already became vital observation object because it affects society life both in rural areas or urban areas. Because parameters to predict rainfall rates is very complex, using physics based model that need many parameters is not a good choice. Using alternative approach like time-series based model is a good alternative. One of the algorithm that widely used to predict future events is Neural Network Backpropagation. On this research we will use Nguyen-Widrow method to initialize weight of Neural Network to reduce training time. The lowest MSE achieved is {0,02815;Â 0,01686; 0,01934; 0,03196} by using 50 maximum epoch and 3 neurons on hidden layer. |
first_indexed | 2024-04-24T18:44:16Z |
format | Article |
id | doaj.art-782a6369044b4dd696ee5b293e1373ec |
institution | Directory Open Access Journal |
issn | 2540-9433 2540-9824 |
language | English |
last_indexed | 2024-04-24T18:44:16Z |
publishDate | 2017-11-01 |
publisher | University of Brawijaya |
record_format | Article |
series | JITeCS (Journal of Information Technology and Computer Science) |
spelling | doaj.art-782a6369044b4dd696ee5b293e1373ec2024-03-27T08:13:25ZengUniversity of BrawijayaJITeCS (Journal of Information Technology and Computer Science)2540-94332540-98242017-11-012210.25126/jitecs.201722919Rainfall Forecasting Using Backpropagation Neural NetworkAndreas Nugroho Sihananto0Wayan Firdaus Mahmudy1Faculty of Computer Science, Universitas BrawijayaUniversitas BrawijayaRainfall already became vital observation object because it affects society life both in rural areas or urban areas. Because parameters to predict rainfall rates is very complex, using physics based model that need many parameters is not a good choice. Using alternative approach like time-series based model is a good alternative. One of the algorithm that widely used to predict future events is Neural Network Backpropagation. On this research we will use Nguyen-Widrow method to initialize weight of Neural Network to reduce training time. The lowest MSE achieved is {0,02815;Â 0,01686; 0,01934; 0,03196} by using 50 maximum epoch and 3 neurons on hidden layer.http://jitecs.ub.ac.id/index.php/jitecs/article/view/9 |
spellingShingle | Andreas Nugroho Sihananto Wayan Firdaus Mahmudy Rainfall Forecasting Using Backpropagation Neural Network JITeCS (Journal of Information Technology and Computer Science) |
title | Rainfall Forecasting Using Backpropagation Neural Network |
title_full | Rainfall Forecasting Using Backpropagation Neural Network |
title_fullStr | Rainfall Forecasting Using Backpropagation Neural Network |
title_full_unstemmed | Rainfall Forecasting Using Backpropagation Neural Network |
title_short | Rainfall Forecasting Using Backpropagation Neural Network |
title_sort | rainfall forecasting using backpropagation neural network |
url | http://jitecs.ub.ac.id/index.php/jitecs/article/view/9 |
work_keys_str_mv | AT andreasnugrohosihananto rainfallforecastingusingbackpropagationneuralnetwork AT wayanfirdausmahmudy rainfallforecastingusingbackpropagationneuralnetwork |