Sea Level Prediction Using Gated Recurrent Unit and Bidirectional Long Short-Term Memory Methods

Authors

  • Anting B.N Sinurat Universitas Pendidikan Indonesia Author
  • Wildan Aprizal Arifin Author
  • Wenny Ananda Larasati Author

DOI:

https://doi.org/10.35314/r9bk6j70

Keywords:

BILSTM , GRU, sea level rise

Abstract

Coastal areas are areas that border between land and sea. One of the main threats to this area is flooding due to rising sea levels. The coastal areas in the South Lampung Waters are geographically located directly opposite the Sunda Strait. In this area, there are various economic activities of the community and settlements that are greatly influenced by sea dynamics, including tides. This study aims to predict sea level in the South Lampung Waters using the GRU method and compare the prediction results of the model with the BiLSTM model. This study involves steps such as data collection, data pre-processing, model training, modeling, evaluation and analysis. The data used is sea level data for one year, from June 1, 2023 to May 31, 2024, which is divided into training data (80%) and test data (20%). Evaluation of the test results and predictions of the two models is carried out using MAE and RMSE. The results of the research that has been carried out, the BiLSTM method is superior to the GRU method in predicting water levels. This can be seen from the MAE and RMSE values ​​obtained, where the BiLSTM method has the lowest MAE value of 0.0102 and RMSE of 0.0218, while the GRU method has a MAE value of 0.0164 and RMSE of 0.0277. So in this study it can be concluded that the BiLSTM method is more accurate and effective than the GRU method in predicting sea level in the South Lampung Waters.

Downloads

Download data is not yet available.

Downloads

Published

24-10-2024

Issue

Section

Articles

How to Cite

Sea Level Prediction Using Gated Recurrent Unit and Bidirectional Long Short-Term Memory Methods. (2024). INOVTEK Polbeng - Seri Informatika, 9(2), 753-764. https://doi.org/10.35314/r9bk6j70