Comparative Analysis of ARIMA and LSTM Methods for Sea Surface Temperature Forecasting in the Sunda Strait

The Sunda Strait is an important area for Indonesia because it is the main domestic and international transportation route. As a water area, the Sunda Strait has weather conditions that are greatly influenced by sea surface temperature (SST). Crucial SST forecasting is carried out to assist maritime transportation activities. This study aims to compare the performance of the ARIMA and LSTM methods in forecasting SST in the Sunda Strait. The data used in this study are daily SST data for the Sunda Strait from August 20, 2022, to January 1, 2024. The best ARIMA model obtained in this data modeling is ARIMA(1,1,1), where this model has significant overall parameters, the smallest AIC and BIC values, and model diagnostic results that meet the assumptions. Meanwhile, in LSTM modeling, the best combination of hyperparameters obtained is a neuron of 150, an epoch of 150, and a batch size of 32, where this combination produces the lowest MSE value of 0.003799. A comparison of the performance of the ARIMA and LSTM methods is carried out by considering the MAPE values ​​of the training data and test data. The LSTM method is superior to the ARIMA method, with a MAPE value of 0.512% for training data and 0.564 for testing data. The forecasting results using the LSTM method show a similar pattern in both training and testing data. Meanwhile, the forecasting results of the LSTM method for the following 30 periods show a fluctuating pattern throughout the day.