<![CDATA[Indonesia is a country dominated by waters, so data on sea level rise, one of maritime weather is important. The Meteorology, Climatology, and Geophysics Agency one of its duties, namely conducting observations in meteorology. The Merak-Bakauheni Port serves the busiest crossing route in Indonesia and connects the islands of Java and Sumatra. If there is a disruption due to meteorological factors, shipping and sea transportation activities will be hampered and disrupted. The purpose of this study is to compare the performance of the BiLSTM and CNN-LSTM models in estimating sea water levels at Merak Port based on the results of the parameter analysis used. The steps begin with collecting, processing data, training the model, and analyzing the model. The data used is daily sea water level data over a period of six years from 2019 to 2024. Evaluation of MSE, MAE and RMSE values is used to see the performance of the two models. From this study, the BiLSTM model produced values of 0.0026 (MSE), 0.0224 (MAE), and 0.0512 (RMSE), the CNN-LSTM model values of 0.0044 (MSE), 0.0319 (MAE), and 0.0664 (RMSE), it can be seen that BiLSTM method has more optimal in predicting sea water levels of Merak Port.]]>
Copyrights © 2025
