<![CDATA[Tropical atmospheric variability poses challenges for daily precipitation prediction at Soekarno–Hatta International Airport, with implications for aviation safety. This study aimed to compare the performance of three deep learning architectures—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Temporal Convolutional Network (TCN)—for daily precipitation prediction using meteorological observations from the BMKG Soekarno–Hatta Station for the period 2019–2025. A quantitative experimental approach was employed using a time-series split scheme to preserve the temporal structure of the data and reduce the risk of data leakage. Air temperature, relative humidity, atmospheric pressure, and wind speed were used as input variables, while precipitation was used as the target variable. Model performance was evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²). The results showed that TCN achieved the best predictive performance, with an RMSE of 10.32 mm, MAE of 7.15 mm, MAPE of 18.27%, and R² of 0.87, followed by LSTM and MLP. Permutation-based sensitivity analysis identified relative humidity and air temperature as the two most influential variables for model prediction. Overall, TCN demonstrated stronger performance in capturing temporal patterns in daily precipitation than LSTM and MLP and showed potential for future application in operational precipitation forecasting and extreme-weather early warning systems at airport environments.]]>
Copyrights © 2026
