<![CDATA[Increased intensity of extreme rainfall due to climate change has made Batang Regency prone to hydrometeorological disasters. This study aims to develop an hourly rainfall prediction model using Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) based on historical data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG). The model was evaluated using the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics. The results showed that LSTM had higher accuracy than RNN, with an MAE value of 0.0395 and an RMSE value of 0.0665. Meanwhile, RNN obtained an MAE value of 0.0439 and an RMSE of 0.0695. LSTM was also more stable in predicting temperature, wind direction, and wind speed variables. These findings indicate that LSTM is more effective for weather time series data and can be used as a basis for developing data-based early warning systems for disasters in local areas.]]>
Copyrights © 2025
