Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Informatika dan Teknik Elektro Terapan

IMPLEMENTASI NEURAL NETWORK BACKPROPAGATION UNTUK MEMPREDIKSI TINGKAT CURAH HUJAN KOTA PADANG (STUDI KASUS: BMKG MARITIM TELUK BAYUR PADANG EE Lailatul Putri; Panji Wijonarko
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3.7567

Abstract

Rainfall is an important factor in weather monitoring as well as in understanding its impact on human life. By utilizing historical rainfall data from previous years, this study aims to predict the rainfall levels in the BMKG Padang City area. Several previous studies have widely used the Backpropagation method to predict rainfall levels in various regions, and the results have shown that this method can produce predictions with a relatively high level of accuracy. Therefore, the researcher is interested in applying the same method in the context of the BMKG Padang City area. In this study, historical rainfall data recorded in the BMKG Padang City area from 2022 to 2024 will be used as training and testing data to develop a rainfall prediction model using an Artificial Neural Network with the Backpropagation algorithm. The research results show that using a 3-13-1 network pattern yields the lowest MSE value of 0.00074166, a MAPE value of 2.1295, and an accuracy level of 97.8705%. The prediction model developed in this study is capable of providing accurate prediction results and has the potential to help in understanding and anticipating rainfall levels in the BMKG Padang City area. It is expected that this research can contribute to the field of weather monitoring and support the development of effective preventive measures against the impacts of rainfall.